[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-9729":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":10,"languages":10,"totalLinesOfCode":10,"stars":11,"forks":12,"watchers":13,"openIssues":14,"contributorsCount":15,"subscribersCount":15,"size":15,"stars1d":16,"stars7d":17,"stars30d":18,"stars90d":15,"forks30d":15,"starsTrendScore":19,"compositeScore":20,"rankGlobal":10,"rankLanguage":10,"license":21,"archived":22,"fork":22,"defaultBranch":23,"hasWiki":22,"hasPages":22,"topics":24,"createdAt":10,"pushedAt":10,"updatedAt":38,"readmeContent":39,"aiSummary":40,"trendingCount":15,"starSnapshotCount":15,"syncStatus":41,"lastSyncTime":42,"discoverSource":43},9729,"awesome-ai-agents","e2b-dev\u002Fawesome-ai-agents","e2b-dev","A list of AI autonomous agents","https:\u002F\u002Fe2b.dev\u002Fdocs",null,28257,2995,327,121,0,18,108,485,81,45,"Other",false,"main",[25,26,27,28,29,30,31,32,33,34,35,36,37],"agent","ai","artificial-intelligence","autogpt","autonomous-agents","awesome","babyagi","copilot","gpt","gpt-4","gpt-engineer","openai","python","2026-06-12 02:02:11","\u003C!--\nTBD:\n- Add to visual:\n\n- LLM Stack\n- Promptly\n- Devon\n- vortic ai\n- UFO\n- GPT Swarm\n- Eidolon\n- NexusGPT\n- Brain Soup\n- L2MAC\n\n\nAdd to readme list:\n- Codeium\n- tinybio\n- Semantix AI Agents - add when they have english version\n- NoteWizard - only if it's AI agent - TBD test\n- Postbot (TBD - check more)\n\t-->\n\n\u003Ch1 align=\"center\">\n\t🔮 Awesome AI Agents\n\t\u003Cp align=\"center\">\n\t\t\u003Ca href=\"https:\u002F\u002Fdiscord.gg\u002FU7KEcGErtQ\" target=\"_blank\">\n\t\t\t\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fstatic\u002Fv1?label=Join&message=%20discord!&color=mediumslateblue\">\n\t\t\u003C\u002Fa>\n\t\t\u003Ca href=\"https:\u002F\u002Ftwitter.com\u002Fe2b\" target=\"_blank\">\n\t\t\t\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Ftwitter\u002Ffollow\u002Fe2b.svg?logo=twitter\">\n\t\t\u003C\u002Fa>\n\t\u003C\u002Fp>\n\u003C\u002Fh1>\n\u003Ch3 align=\"center\">\n  Add \u003Ca href=\"https:\u002F\u002Fe2b.dev\u002Fdocs?ref=awesome-sdks\">Code Interpreter\u003C\u002Fa> to your AI App\n\u003C\u002Fh3>\n\n\u003Ch5 align=\"center\">🌟 \u003Ca href=\"https:\u002F\u002Fe2b.dev\u002Fai-agents\">See this list in web UI\u003C\u002Fa>\u003C\u002Fh5>\n\u003Ch5 align=\"center\">👉 \u003Ca href=\"https:\u002F\u002Fforms.gle\u002FUXQFCogLYrPFvfoUA\">Submit new product here\u003C\u002Fa>\u003C\u002Fh5>\n\n\u003Cimg src=\"assets\u002Flandscape-latest.png\" width=\"100%\" alt=\"Chart of AI Agents Landscape\" \u002F>\n\nWelcome to our list of AI agents.\nWe structured the list into two parts:\n- [Open source projects](#open-source-projects)\n- [Closed-source projects and companies](#closed-source-projects-and-companies)\n  \nTo filter the products by categories and use-cases, see the 🌟 [web version of this list](https:\u002F\u002Fe2b.dev\u002Fai-agents). 🌟\n\nThe list is done according to our best knowledge, although definitely not comprehensive. Check out also \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fe2b-dev\u002Fawesome-sdks-for-ai-agents\">the Awesome List of SDKs for AI Agents\u003C\u002Fa>.\nDiscussion and feedback appreciated! :heart:\n\n## Have anything to add?\nCreate a pull request or fill in this [form](https:\u002F\u002Fforms.gle\u002FUXQFCogLYrPFvfoUA). Please keep the alphabetical order and in the correct category.\n\nFor adding AI agents'-related SDKs, frameworks and tools, please visit [Awesome SDKs for AI Agents](https:\u002F\u002Fgithub.com\u002Fe2b-dev\u002Fawesome-sdks-for-ai-agents). This list is only for AI assistants and agents.\n\n\u003C!---\n## Who's behind this?\nThis list is made by the team behind [e2b](https:\u002F\u002Fgithub.com\u002Fe2b-dev\u002Fe2b). E2b is building AWS for AI agents. We help developers to deploy, test, and monitor AI agents. E2b is agnostic to your tech stack and aims to work with any tooling for building AI agents.\n--->\n\n## Check out E2B - Code Interpreting for AI apps\n- Check out [Code Interpreter SDK](https:\u002F\u002Fe2b.dev\u002Fdocs?ref=awesome-sdk)\n- Explore examples in [E2B Cookbook](https:\u002F\u002Fgithub.com\u002Fe2b-dev\u002Fe2b-cookbook)\n- Read our [docs](https:\u002F\u002Fe2b.dev\u002Fdocs?ref=awesome-sdks)\n- Contact us at [hello@e2b.dev](mailto:hello@e2b.dev) or [on Discord](https:\u002F\u002Fdiscord.gg\u002F35NF4Y8WSE). Follow us on [X (Twitter)](https:\u002F\u002Ftwitter.com\u002Fe2b)\n\n# Open-source projects\n\n## [Adala](https:\u002F\u002Fgithub.com\u002FHumanSignal\u002FAdala)\nAdala: Autonomous Data (Labeling) Agent framework\n\n\u003Cdetails>\n\n![Image](https:\u002F\u002Fgithub.com\u002FHumanSignal\u002FAdala\u002Fraw\u002Fmaster\u002Fdocs\u002Fsrc\u002Fimg\u002Flogo-dark-mode.png)\n\n### Category\nGeneral purpose, Build your own, Multi-agent\n\n### Description\n\n- **Reliable agents**: Built on ground truth data for consistent, trustworthy results.\n- **Controllable output**: Tailor output with flexible constraints to fit your needs.\n- **Specialized in data processing**: Agents excel in custom data labeling and processing tasks.\n- **Autonomous learning**: Agents evolve through observations and reflections, not just automation.\n- **Flexible and extensible runtime**: Adaptable framework with community-driven evolution for diverse needs.\n- **Easily customizable**: Develop agents swiftly for unique challenges, no steep learning curve.\n\n### Links\n- [Documentation](https:\u002F\u002Fhumansignal.github.io\u002FAdala\u002F) \n- [Discord](https:\u002F\u002Fdiscord.gg\u002FQBtgTbXTgU)\n- [GitHub](https:\u002F\u002Fgithub.com\u002FHumanSignal\u002FAdala)\n\u003C\u002Fdetails>\n\n## [Agent4Rec](https:\u002F\u002Fgithub.com\u002FLehengTHU\u002FAgent4Rec)\nRecommender system simulator with 1,000 agents\n\n\u003Cdetails>\n\u003Cp>\u003Cimg src=\"https:\u002F\u002Fgithub.com\u002FLehengTHU\u002FAgent4Rec\u002Fraw\u002Fmaster\u002Fassets\u002Fsandbox.png\" alt=\"Image\" \u002F>\u003C\u002Fp>\n\n### Category\nGeneral purpose, Build your own, Multi-agent\n\n### Description\n- Agent4Rec is a recommender system simulator that utilizes 1,000 LLM-empowered generative agents.\n- These agents are initialized from the [MovieLens-1M](https:\u002F\u002Fgrouplens.org\u002Fdatasets\u002Fmovielens\u002F1m\u002F) dataset, embodying varied social traits and preferences.\n- Each agent interacts with personalized movie recommendations in a page-by-page manner and undertakes various actions such as watching, rating, evaluating, exiting, and interviewing. \n\n### Links\n- [Paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F2310.10108)\n\n\u003C\u002Fdetails>\n\n## [AgentForge](https:\u002F\u002Fgithub.com\u002FDataBassGit\u002FAgentForge)\nLLM-agnostic platform for agent building & testing\n\n\u003Cdetails>\n\n![Image](https:\u002F\u002Fpbs.twimg.com\u002Fprofile_images\u002F1667167265060528129\u002Fl8S9vtP2_400x400.jpg)\n\n### Category\nGeneral purpose, Build your own, Multi-agent\n\n### Description\n- A low-code framework designed for the swift creation, testing, and iteration of AI-powered autonomous agents and Cognitive Architectures, compatible with various LLM models.\n- Facilitates building custom agents and cognitive architectures with ease.\n- Supports multiple LLM models including OpenAI, Anthropic's Claude, and local Oobabooga, allowing flexibility in running different models for different agents based on specific requirements.\n- Provides customizable agent memory management and on-the-fly prompt editing for rapid development and testing.\n- Comes with a database-agnostic design ensuring seamless extensibility, with straightforward integration with different databases like ChromaDB for various AI projects.\n\n### Links\n- [GitHub](https:\u002F\u002Fgithub.com\u002FDataBassGit\u002FAgentForge)\n- [Web](https:\u002F\u002Fwww.agentforge.net\u002F)\n- [Discord](https:\u002F\u002Fdiscord.com\u002Finvite\u002FttpXHUtCW6)\n- [X](https:\u002F\u002Ftwitter.com\u002FAgentForge)\n\n\u003C\u002Fdetails>\n\n## [AgentGPT](https:\u002F\u002Fagentgpt.reworkd.ai\u002F)\nBrowser-based no-code version of AutoGPT\n\u003Cdetails>\n\n![Image](https:\u002F\u002Fraw.githubusercontent.com\u002Freworkd\u002FAgentGPT\u002Fmain\u002Fnext\u002Fpublic\u002Fbanner.png)\n\n\n### Category\nGeneral purpose\n\n### Description\n- A no-code platform\n- Process:\n\t- Assigning a goal to the agent\n\t- Witnessing its thinking process\n\t- Formulation of an execution plan\n\t- Taking actions accordingly\n- Uses OpenAI functions\n- Supports gpt-3.5-16k, pinecone and pg_vector databases\n- Stack\n\t- Frontend: NextJS + Typescript\n\t- Backend: FastAPI + Python\n\t- DB: MySQL through docker with the option of running SQLite locally\n\n\u003C!--\n### Features\n- Uses OpenAI **functions**\n- Supports gpt-3.5-16k, pinecone and pg_vector databases\n\n### Stack\n- Frontend: NextJS + Typescript\n- Backend: FastAPI + Python\n\t- DB: MySQL through docker with the option of running SQLite locally\n\t-->\n\n### Links\n- [Documentation](https:\u002F\u002Fdocs.reworkd.ai\u002F)\n- [Website](https:\u002F\u002Fagentgpt.reworkd.ai\u002F)\n- [GitHub](https:\u002F\u002Fgithub.com\u002Freworkd\u002FAgentGPT)\n\u003C\u002Fdetails>\n\n\u003C!-- This is a comment that appears only in the raw text -->\n\n## [AgentPilot](https:\u002F\u002Fgithub.com\u002Fjbexta\u002FAgentPilot)\nBuild, manage, and chat with agents in desktop app\n\n\n\u003Cdetails>\n\n![Image](https:\u002F\u002Fgithub.com\u002Fjbexta\u002FAgentPilot\u002Fraw\u002Fmaster\u002Fdocs\u002Fdemo.png)\n\n### Category\nGeneral purpose\n\n### Description\n\n- Integrated into Open Interpreter and MemGPT\n- Group chats feature\n\n\n\n### Links\n- [GitHub](https:\u002F\u002Fgithub.com\u002Fjbexta\u002FAgentPilot)\n- [X ](https:\u002F\u002Ftwitter.com\u002FAgentPilotAI)\n- \n  \n\u003C\u002Fdetails>\n\n## [Agents](https:\u002F\u002Fgithub.com\u002Faiwaves-cn\u002Fagents)\n\nLibrary\u002Fframework for building language agents\n\n\u003Cdetails>\n\n![Image](https:\u002F\u002Fgithub.com\u002Faiwaves-cn\u002Fagents\u002Fraw\u002Fmaster\u002Fassets\u002Fagents-logo.png)\n\n### Category\nGeneral purpose, Build your own, Multi-agent\n\n### Description\n-   **Long-short Term Memory**: Language agents in the library are equipped with both long-term memory implemented via VectorDB + Semantic Search and short-term memory (working memory) maintained and updated by an LLM.\n-   **Tool Usage**: Language agents in the library can use any external tools via  [function-calling](https:\u002F\u002Fplatform.openai.com\u002Fdocs\u002Fguides\u002Fgpt\u002Ffunction-calling)  and developers can add customized tools\u002FAPIs  [here](https:\u002F\u002Fgithub.com\u002Faiwaves-cn\u002Fagents\u002Fblob\u002Fmaster\u002Fsrc\u002Fagents\u002FComponent\u002FToolComponent.py).\n-   **Web Navigation**: Language agents in the library can use search engines to navigate the web and get useful information.\n-   **Multi-agent Communication**: In addition to single language agents, the library supports building multi-agent systems in which language agents can communicate with other language agents and the environment. Different from most existing frameworks for multi-agent systems that use pre-defined rules to control the order for agents' action,  **Agents**  includes a  _controller_  function that dynamically decides which agent will perform the next action using an LLM by considering the previous actions, the environment, and the target of the current states. This makes multi-agent communication more flexible.\n-   **Human-Agent interaction**: In addition to letting language agents communicate with each other in an environment, our framework seamlessly supports human users to play the role of the agent by himself\u002Fherself and input his\u002Fher own actions, and interact with other language agents in the environment.\n-   **Symbolic Control**: Different from existing frameworks for language agents that only use a simple task description to control the entire multi-agent system over the whole task completion process,  **Agents**  allows users to use an  **SOP (Standard Operation Process)**  that defines subgoals\u002Fsubtasks for the overall task to customize fine-grained workflows for the language agents.\n\n### Links\n- Author: [AIWaves Inc.](https:github.com\u002Faiwaves-cn)\n- [Paper](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2309.07870.pdf)\n- [GitHub Repository](https:\u002F\u002Fgithub.com\u002Faiwaves-cn\u002Fagents)\n- [Documentation](https:\u002F\u002Fagents-readthedocsio.readthedocs.io\u002Fen\u002Flatest\u002Findex.html)\n- [Tweet](https:\u002F\u002Ftwitter.com\u002Fwangchunshu\u002Fstatus\u002F1702512370785100133)\n\u003C\u002Fdetails>\n\n## [AgentVerse](https:\u002F\u002Fgithub.com\u002FOpenBMB\u002FAgentVerse)\nPlatform for task-solving & simulation agents\n\u003Cdetails>\n\n![Image](https:\u002F\u002Fpbs.twimg.com\u002Fcard_img\u002F1744672970822615040\u002Fm870GGf1?format=jpg&name=medium)\n\n### Category\nGeneral purpose, Build your own, Multi-agent\n\n### Description\n- Assembles multiple agents to collaboratively accomplish tasks.\n- Allows custom environments for observing or interacting with multiple agents.\n\n### Links\n- Paper: [AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors](https:\u002F\u002Farxiv.org\u002Fabs\u002F2308.10848)\n- [Twitter](https:\u002F\u002Ftwitter.com\u002FAgentverse71134)\n- [Discord](https:\u002F\u002Fdiscord.gg\u002FgDAXfjMw)\n- [Hugging Face](https:\u002F\u002Fhuggingface.co\u002Fspaces\u002FAgentVerse\u002FagentVerse)\n\n\u003C\u002Fdetails>\n\n## [AI Legion](https:\u002F\u002Fgithub.com\u002Feumemic\u002Fai-legion)\nMulti-agent TS platform, similar to AutoGPT\n\n\u003Cdetails>\n\n![Image](https:\u002F\u002Fres.cloudinary.com\u002Fapideck\u002Fimage\u002Fupload\u002Fw_1500,f_auto\u002Fv1681330426\u002Fmarketplaces\u002Fckhg56iu1mkpc0b66vj7fsj3o\u002Flistings\u002Fai-legion\u002Fscreenshots\u002FScreenshot_2023-04-12_at_22.13.24_d9kdoj.png)\n\n### Category\nMulti-agent, Build-your-own\n\n\n### Description\n- An LLM-powered autonomous agent platform\n- A framework for autonomous agents who can work together to accomplish tasks\n- Interaction with agents done via console direct messages\n\n### Links\n- Author: [eumemic](https:\u002F\u002Fgithub.com\u002Feumemic)\n- [Website](https:\u002F\u002Fgpt3demo.com\u002Fapps\u002Fai-legion)\n- [GitHub](https:\u002F\u002Fgithub.com\u002Feumemic\u002Fai-legion)\n- [Twitter](https:\u002F\u002Ftwitter.com\u002Fdysmemic)\n\u003C\u002Fdetails>\n\n## [Aider](https:\u002F\u002Fgithub.com\u002Fpaul-gauthier\u002Faider)\nUse command line to edit code in your local repo\n\n\u003Cdetails>\n\n\n![Image](https:\u002F\u002Frepository-images.githubusercontent.com\u002F638629097\u002F1d3d6251-f8be-4d11-bbb1-4e44b7364b74)\n\n### Category\nCoding, GitHub\n\n### Description\n- Aider is a command line tool that lets you pair program with GPT-3.5\u002FGPT-4, to edit code stored in your local git repository\n- You can start a new project or work with an existing repo. And you can fluidly switch back and forth between the aider chat where you ask GPT to edit the code and your own editor to make changes yourself\n- Aider makes sure edits from you and GPT are committed to git with sensible commit messages. Aider is unique in that it works well with pre-existing, larger codebases\n\n### Links  \n- [Website](https:\u002F\u002Faider.chat\u002F)\n- Author: [Paul Gauthier](https:\u002F\u002Fgithub.com\u002Fpaul-gauthier) (Github)\n- [Discord Invite](https:\u002F\u002Fdiscord.com\u002Finvite\u002FTv2uQnR88V)\n\n\u003C\u002Fdetails>\n\n## [AIlice](https:\u002F\u002Fgithub.com\u002Fmyshell-ai\u002FAIlice)\nCreate agents-calling tree to execute your tasks\n\u003Cdetails>\n\n![Image](https:\u002F\u002Fgithub.com\u002Fmyshell-ai\u002FAIlice\u002Fraw\u002Fmaster\u002FAIlice.png)\n\n### Category\nGeneral purpose, Personal assistant, Productivity\n\n### Description\n- \"An Agent in the form of a chatbot independently plans tasks given in natural language and dynamically creates an agents calling tree to execute tasks.\n- There is an interaction mechanism between agents to ensure fault tolerance.\n- External interaction modules can be automatically built for self-expansion.\n\n### Links  \n- [GitHub](https:\u002F\u002Fgithub.com\u002Fmyshell-ai\u002FAIlice)\n\n\u003C\u002Fdetails>\n\n## [AutoGen](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fautogen)\nMulti-agent framework with diversity of agents\n\u003Cdetails>\n\n![Image](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fautogen\u002Fraw\u002Fmain\u002Fwebsite\u002Fstatic\u002Fimg\u002Fautogen_agentchat.png)\n\n### Category\nGeneral purpose, Build your own, Multi-agent\n\n### Description\n- A framework for developing LLM (Large Language Model) applications with multiple conversational agents.\n- These agents can collaborate to solve tasks and can interact seamlessly with humans.\n- It simplifies complex LLM workflows, enhancing automation and optimization.\n- It offers a range of working systems across various domains and complexities.\n- It improves LLM inference with easy performance tuning and utility features like API unification and caching.\n- It supports advanced usage patterns, including error handling, multi-config inference, and context programming.\n\n### Links\n- Paper: [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation Framework](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2308.08155.pdf)\n- [Discord](https:\u002F\u002Fdiscord.gg\u002FpAbnFJrkgZ)\n- [Twitter thread describing the system](https:\u002F\u002Ftwitter.com\u002Fpyautogen)\n\n\n\u003C\u002Fdetails>\n\n## [AutoGPT](https:\u002F\u002Fagpt.co\u002F?utm_source=awesome-ai-agents)\nExperimental attempt to make GPT4 fully autonomous\n\n\u003Cdetails>\n\n![Image](https:\u002F\u002Fnews.agpt.co\u002Fwp-content\u002Fuploads\u002F2023\u002F04\u002FLogo_-_Auto_GPT-B-800x363.png)\n\n### Category\nGeneral purpose\n\n### Description\n- An experimental open-source attempt to make GPT-4 fully autonomous, with >140k stars on GitHub\n- Chains together LLM \"thoughts\", to autonomously achieve whatever goal you set\n- Internet access for searches and information gathering\n- Long-term and short-term memory management\n- Can execute many commands such as Google Search, browse websites, write to files, and execute Python files and much more\n- GPT-4 instances for text generation\n- Access to popular websites and platforms\n- File storage and summarization with GPT-3.5\n- Extensibility with Plugins\n- \"A lot like BabyAGI combined with LangChain tools\"\n- Features added in release 0.4.0\n\t- File reading\n\t- Commands customization\n\t- Enhanced testing\n\n\u003C!--\n### Features added in release 0.4.0\n- File reading\n- Commands customization\n- Enhanced testing\n-->\n\n### Links\n- [Twitter](https:\u002F\u002Ftwitter.com\u002FAuto_GPT\u002F?utm_source=awesome-ai-agents)\n- [GitHub](https:\u002F\u002Fgithub.com\u002FSignificant-Gravitas\u002FAuto-GPT\u002F?utm_source=awesome-ai-agents)\n- [Facebook](https:\u002F\u002Fwww.facebook.com\u002Fgroups\u002F1330282574368178\u002F?utm_source=awesome-ai-agents)\n- [Linkedin](https:\u002F\u002Fwww.linkedin.com\u002Fcompany\u002Fautogpt\u002F?utm_source=awesome-ai-agents)\n- [Discord](https:\u002F\u002Fdiscord.gg\u002Fautogpt\u002F?utm_source=awesome-ai-agents)\n- Author: [Significant Gravitas](https:\u002F\u002Ftwitter.com\u002FSigGravitas\u002F?utm_source=awesome-ai-agents)\n\u003C\u002Fdetails>\n\n\n\n## [Automata](https:\u002F\u002Fgithub.com\u002Femrgnt-cmplxty\u002Fautomata)\nGenerate code based on your project context\n\n\u003Cdetails>\n\n\n![Image](https:\u002F\u002Fgithub.com\u002Femrgnt-cmplxty\u002FAutomata\u002Fassets\u002F68796651\u002F61fe3c33-9b7a-4c1b-9726-a77140476b83)\n\n### Category\nCoding\n\n### Description\n- Model: GPT 4\n- Automata takes your project as a context, receives tasks, and executes the instructions seamlessly.\n- Features\n\t- Automata aims to evolve into a fully autonomous, self-programming Artificial Intelligence system.\n\t- It's designed for seamless integration with all available agent platforms and LLM providers.\n\t- Utilizes the novel code search algorithm, SymbolRank, and associated tools to build superior coding intelligence.\n\t- Modular, fully configurable design with minimal reliance on external dependencies\n\n### Links\n- [GitHub](https:\u002F\u002Fgithub.com\u002Femrgnt-cmplxty\u002Fautomata)\n- [Docs](https:\u002F\u002Fautomata.readthedocs.io\u002Fen\u002Flatest\u002F)\n- Author: [Owen Colegrove](https:\u002F\u002Ftwitter.com\u002Focolegro)\n\u003C!--\n\n### Features\n- Automata aims to evolve into a fully autonomous, self-programming Artificial Intelligence system.\n- It's designed for seamless integration with all available agent platforms and LLM providers.\n- Utilizes the novel code search algorithm, SymbolRank, and associated tools to build superior coding intelligence.\n- Modular, fully configurable design with minimal reliance on external dependencies.\n\n-->\n\n\u003C\u002Fdetails>\n\n## [AutoPR](https:\u002F\u002Fgithub.com\u002Firgolic\u002FAutoPR)\nAI-generated pull requests agent that fixes issues\n\n\u003Cdetails>\n\n![Image](https:\u002F\u002Fgithub.com\u002Firgolic\u002FAutoPR\u002Fraw\u002Fmain\u002Fwebsite\u002Fstatic\u002Fimg\u002FAutoPR_Mark_color.png)\n\n### Category\nCoding, GitHub\n\n### Description\n- Triggered by adding a label containing AutoPR to an issue, AutoPR will:\n\t- Plan a fix\n\t- Write the code\n\t- Push a branch\n\t- Open a pull request\n\n### Links\n- [Discord](https:\u002F\u002Fdiscord.com\u002Finvite\u002Fykk7Znt3K6)\n\n\u003C\u002Fdetails>\n\n## [Autonomous HR Chatbot](https:\u002F\u002Fgithub.com\u002Fstepanogil\u002Fautonomous-hr-chatbot)\nAgent that answers HR-related queries using tools\n\n\u003Cdetails>\n\n![Image](https:\u002F\u002Fgithub.com\u002Fstepanogil\u002Fautonomous-hr-chatbot\u002Fraw\u002Fmain\u002Fassets\u002Fsample_chat.png)\n\n### Category\nHR, Business intelligence, Productivity\n\n### Description\n- A prototype enterprise application - an Autonomous HR Assistant powered by GPT-3.5.\n- An agent that can answer HR related queries autonomously using the tools it has on hand.\n- Powered by GPT-3.5\n- Current tools assigned to the agent (with more on the way):\n\t- Timekeeping Policy\n\t- Employee Data\n\t- Calculator\n\n### Links\n- Medium: [Creating a (mostly) Autonomous HR Assistant with ChatGPT and LangChain’s Agents and Tools](https:\u002F\u002Fpub.towardsai.net\u002Fcreating-a-mostly-autonomous-hr-assistant-with-chatgpt-and-langchains-agents-and-tools-1cdda0aa70ef)\n- [GitHub](https:\u002F\u002Fgithub.com\u002Fstepanogil\u002Fautonomous-hr-chatbot)\n- Author: [Stephen Bonifacio](https:\u002F\u002Ftwitter.com\u002FStepanogil)\n- [YouTube demo](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=id7XRcEIBvg&ab_channel=StephenBonifacio)\n- [Blog post](https:\u002F\u002Fpub.towardsai.net\u002Fcreating-a-mostly-autonomous-hr-assistant-with-chatgpt-and-langchains-agents-and-tools-1cdda0aa70ef)\n\u003C\u002Fdetails>\n\n## [BabyAGI](https:\u002F\u002Fgithub.com\u002Fyoheinakajima\u002Fbabyagi)\nA simple framework for managing tasks using AI\n\u003Cdetails>\n\n![Image](https:\u002F\u002Fuser-images.githubusercontent.com\u002F21254008\u002F235015461-543a897f-70cc-4b63-941a-2ae3c9172b11.png)\n\n### Category\nGeneral purpose\n\n### Description\n- A pared-down version of the original [Task-Driven Autonomous Agent](https:\u002F\u002Ftwitter.com\u002Fyoheinakajima\u002Fstatus\u002F1640934493489070080?s=20)\n- Creates tasks based on the result of previous tasks and a predefined objective.\n- The script then uses OpenAI's NLP capabilities to create new tasks based on the objective\n- Leverages OpenAI's GPT-4, pinecone vector search, and LangChainAI framework\n- Default model is OpenAI GPT3-turbo\n- The system maintains a task list for managing and prioritizing tasks\n- It autonomously creates new tasks based on completed results and reprioritizes the task list accordingly, showcasing the adaptability of AI-powered language models\n\n\n### Links\n- Paper: [Task-driven Autonomous Agent Utilizing GPT-4, Pinecone, and LangChain for Diverse Applications](https:\u002F\u002Fyoheinakajima.com\u002Ftask-driven-autonomous-agent-utilizing-gpt-4-pinecone-and-langchain-for-diverse-applications\u002F)\n- [Discord](https:\u002F\u002Fdiscord.com\u002Finvite\u002FTMUw26XUcg)\n- [Founder's Twitter](https:\u002F\u002Ftwitter.com\u002Fyoheinakajima)\n- [Twitter thread describing the system](https:\u002F\u002Ftwitter.com\u002Fyoheinakajima\u002Fstatus\u002F1640934493489070080)\n\n\n\u003C\u002Fdetails>\n\n\n## [BabyBeeAGI](https:\u002F\u002Fyoheinakajima.com\u002Fbabybeeagi-task-management-and-functionality-expansion-on-top-of-babyagi\u002F)\nTask management & functionality BabyAGI expansion\n\n\u003Cdetails>\n\n![Image](https:\u002F\u002Fyoheinakajima.com\u002Fwp-content\u002Fuploads\u002F2023\u002F04\u002Fimage.png)\n\n### Category\nGeneral purpose, Productivity\n\n### Description\n- A more advanced version of the original BabyAGI code\n- - Improves upon the original framework, by introducing a more complex task management prompt, allowing for more comprehensive analysis and synthesis of information\n- Designed to handle multiple functions within one task management prompt\n- Built on top of the GPT-4 architecture, resulting in slower processing speeds and occasional errors\n- Provides a framework that can be further built upon and improved, paving the way for more sophisticated AI applications\n- One of the significant differences between BabyAGI and BabyBeeAGI is the complexity of the task management prompt\n\n### Links\n- [Tweet](https:\u002F\u002Ftwitter.com\u002Fyoheinakajima\u002Fstatus\u002F1652732735344246784)\n- [GitHub](https:\u002F\u002Fgithub.com\u002Fyoheinakajima\u002Fbabyagi\u002Fblob\u002Fmain\u002Fclassic\u002FBabyBeeAGI.py)\n- [Replit](https:\u002F\u002Freplit.com\u002F@YoheiNakajima\u002FBabyBeeAGI?v=1)\n- Author: [@yoheinakajima](https:\u002F\u002Ftwitter.com\u002Fyoheinakajima) (Twitter)\n\n\u003C\u002Fdetails>\n\n\n## [BabyCatAGI](https:\u002F\u002Freplit.com\u002F@YoheiNakajima\u002FBabyCatAGI)\nBabyCatAGI is a mod of BabyBeeAGI\n\u003Cdetails>\n\n![Image](https:\u002F\u002Fpbs.twimg.com\u002Fmedia\u002FFwBwoRracAI99iP?format=jpg&name=medium)\n\n### Category\nGeneral purpose\n\n### Description\n- Just 300 lines of code\n- This was built as a d iteration on the original BabyAGI code in a lightweight way. Differences to BabyAGI include the following:\n\t- Task Creation Agent runs once\n\t- Execution Agent loops through tasks\n\t- Task dependencies for pulling relevant results\n\t- Two tools: search tool and text completion\n\t- “Mini-agent” as tool\n\t- Search tool combines search, scrape, chunking, and extraction.\n\t- Results combined to create summary report\n\n\n\u003C!--\n### How to use\n- Fork this into a private Repl\n- Add your OpenAI API Key (required) and SerpAPI Key (optional)\n- Update the OBJECTIVE variable\n- Press \"Run\" at the top.\n-->\n\n### Links\n- [Tweet](https:\u002F\u002Ftwitter.com\u002Fyoheinakajima\u002Fstatus\u002F1657448504112091136)\n- [GitHub](https:\u002F\u002Fgithub.com\u002Fyoheinakajima\u002Fbabyagi\u002Fblob\u002Fmain\u002Fclassic\u002FBabyCatAGI.py)\n- [Replit](https:\u002F\u002Freplit.com\u002F@YoheiNakajima\u002FBabyCatAGI)\n- Author: [@yoheinakajima](https:\u002F\u002Ftwitter.com\u002Fyoheinakajima) (Twitter)\n\n\u003C\u002Fdetails>\n\n## [BabyDeerAGI](https:\u002F\u002Ftwitter.com\u002Fyoheinakajima\u002Fstatus\u002F1666313838868992001)\nMod of BabyAGI with only ~350 lines of code\n\n\u003Cdetails>\n\n![Image](https:\u002F\u002Fpbs.twimg.com\u002Fmedia\u002FFx_tr0yaUAYP1Q0?format=jpg&name=medium)\n\n### Category\nGeneral purpose\n\n### Category\nGeneral purpose\n\n### Description\n- Features\n\t- Parallel tasks (making it faster)\n\t- 3.5-turbo only (GPT-4 not required)\n\t- User input tool\n\t- Query rewrite in web search tool\n\t- Saves results\n\n\n### Links\n- [Tweet](https:\u002F\u002Ftwitter.com\u002Fyoheinakajima\u002Fstatus\u002F1666313838868992001)\n- [GitHub](https:\u002F\u002Fgithub.com\u002Fyoheinakajima\u002Fbabyagi\u002Fblob\u002Fmain\u002Fclassic\u002FBabyDeerAGI.py)\n- [Replit](https:\u002F\u002Freplit.com\u002F@YoheiNakajima\u002FBabyDeerAGI)\n- Author: [@yoheinakajima](https:\u002F\u002Ftwitter.com\u002Fyoheinakajima) (Twitter)\n\n\u003C\u002Fdetails>\n\n## [BabyElfAGI](https:\u002F\u002Ftwitter.com\u002Fyoheinakajima\u002Fstatus\u002F1678443482866933760)\nMod of BabyDeerAGI, with ~895 lines of code\n\u003Cdetails>\n\n![Image](https:\u002F\u002Fpbs.twimg.com\u002Fmedia\u002FF0sHc04aMAEVn3D?format=jpg&name=medium)\n\n### Category\nGeneral purpose\n\n### Description\n- Features\n\t- Skills class allows for creation of new skills\n\t- 'Dynamic task list' example with vector search\n\t- Beta reflection agent\n\t- Can read, write, and review its own code\n\n\n### Links\n- [Tweet](https:\u002F\u002Ftwitter.com\u002Fyoheinakajima\u002Fstatus\u002F1678443482866933760)\n- [GitHub](https:\u002F\u002Fgithub.com\u002Fyoheinakajima\u002Fbabyagi\u002Fblob\u002Fmain\u002Fclassic\u002FBabyElfAGI\u002Fmain.py)\n- [Replit](https:\u002F\u002Freplit.com\u002F@YoheiNakajima\u002FBabyElfAGI)\n- Author: [@yoheinakajima](https:\u002F\u002Ftwitter.com\u002Fyoheinakajima) (Twitter)\n\n\u003C\u002Fdetails>\n\n\n## [BabyCommandAGI](https:\u002F\u002Fgithub.com\u002Fsaten-private\u002FBabyCommandAGI)\nTest what happens when you combine CLI and LLM\n\u003Cdetails>\n\n![Image](https:\u002F\u002Fgithub.com\u002Fsaten-private\u002FBabyCommandAGI\u002Fraw\u002Fmain\u002Fdocs\u002FArchitecture.png)\n\n### Category\nGeneral purpose, Coding\n\n### Description\n- gent designed to test what happens when you combine CLI and LLM, which are more traditional interfaces than GUI (created by @saten-private)\n- An AI agent based on @yoheinakajima's [BabyAGI](https:\u002F\u002Fgithub.com\u002Fyoheinakajima\u002Fbabyagi) which executes shell commands\n- Automatic Programming, Successfully created an app automatically just by providing feedback. The procedure can be found [here](https:\u002F\u002Ftwitter.com\u002Fsaten_work\u002Fstatus\u002F1674855573412810753).\n- Automatic Environment Setup, Successfully installed a Flutter environment on Linux in a container, created the Flutter app, and launched it. The procedure can be found [here](https:\u002F\u002Ftwitter.com\u002Fsaten_work\u002Fstatus\u002F1667126272072491009).\n- Aside from setting up the environment, it seems to be able to handle a bit of general tasks such as [Generating text, like poems, code, scripts, musical pieces, email, and letters, translating languages](https:\u002F\u002Fanyaitools.com\u002Fbabycommandagi\u002F?utm_source=SocialAutoPoster&utm_medium=Social&utm_campaign=Twitter)\n- There is a risk of breaking the environment. Please run in a virtual environment such as Docker.\n- GPT-4 or higher is recommended\n\n### Links\n- [Founder's Twitter](https:\u002F\u002Ftwitter.com\u002Fsaten_work)\n- [Twitter thread describing the system](https:\u002F\u002Ftwitter.com\u002Fsaten_work\u002Fstatus\u002F1654571194111393793)\n\n\u003C\u002Fdetails>\n\n\n## [BabyFoxAGI](https:\u002F\u002Fgithub.com\u002Fyoheinakajima\u002Fbabyagi\u002Ftree\u002Fmain\u002Fclassic\u002Fbabyfoxagi)\nMod of BabyAGI with a new parallel UI panel\n\n\n\u003Cdetails>\n\n![Image](https:\u002F\u002Fpbs.twimg.com\u002Fmedia\u002FF2Vpt4EbIAAa326?format=jpg&name=medium)\n\n### Category\nGeneral purpose\n\n### Description\n- A mod of BabyElfAGI, in a series of mods w the naming of Baby\u003Canimal>AGI in alphabetical order\n- Self-improving task lists (FOXY method)\n   \t- By storing a final reflection at the end, and pulling the most relevant reflection to guide future runs, BabyAGI slowly generates better and better tasks lists\n- Novel Chat UI w parallel tasks\n  \t- You can chat w BabyAGI! It has an experimental UI where the chat is separate from the tasks\u002Foutput panel, allowing you to request multiple tasks in parallel\n  \t- The Chat UI can use a single skill quickly, or chain multiple skills together using a tasklist\n-  New skills\n\t- 🎨 DALLE skill with prompt assist\n \t- 🎶 Music player w Deezer\n\t- 📊 Airtable search (add your own table\u002Fbase ID)\n\t- 🔍 Startup Analyst (example of beefy function call as a skill)\n-  It’s own README\n\n\n### Links\n- [Author's Twitter](https:\u002F\u002Ftwitter.com\u002Fyoheinakajima)\n- [Twitter thread describing the system](https:\u002F\u002Ftwitter.com\u002Fyoheinakajima\u002Fstatus\u002F1697539193768116449)\n- [Replit](https:\u002F\u002Freplit.com\u002F@YoheiNakajima)\n\n\u003C\u002Fdetails>\n\n\n\n## [BambooAI](https:\u002F\u002Fgithub.com\u002Fpgalko\u002FBambooAI)\nData exploration and analysis for non-programmers\n\n\u003Cdetails>\n\n![Image](https:\u002F\u002Fpbs.twimg.com\u002Fcard_img\u002F1745187734602313730\u002Ff-W5kbIU?format=jpg&name=medium)\n\n### Category\nData analysis\n\n### Description\n- BambooAI runs in a loop (until user decides to end it).\n- Allows mixing of different models with different capabilities, token costs and context windows for different tasks.\n- Maintains the memory of previous conversations.\n- Builds the prompts dynamically utilising relevant context from Pinecone vector DB.\n- Offers a narrative or asks follow up questions if required.\n- For codified responses, the task is broken down into a list of steps and a pseudo-code algorithm is built.\n- Based on the algorithm, it ises the python code for dataset analysis, modeling or plotting.\n- Debugs the code which then executes, auto-corrects if needs to, and displays the output to user.\n- Ranks the final answers, and asks user for feedback.\n- Builds a vector DB knowledge-base, based on the rank and the user feedback.\n\n### Links\n- [GitHub](https:\u002F\u002Fgithub.com\u002Fpgalko\u002FBambooAI)\n- [Creators's Twitter](https:\u002F\u002Ftwitter.com\u002Fpgalko)\n\n\u003C\u002Fdetails>\n\n\n## [BeeBot](https:\u002F\u002Fgithub.com\u002FAutoPackAI\u002Fbeebot)\nEarly-stage project for wide range of tasks\n\n\u003Cdetails>\n\n![Image](https:\u002F\u002Fcamo.githubusercontent.com\u002F72231056f7393fa18ee2baa5cedf2688d1fc15478bb6131936e222e5d23ccbb6\u002F68747470733a2f2f6572696b6c702e636f6d2f6d6173636f742e706e67)\n\n### Category\nGeneral purpose, Productivity\n\n### Description\n- \"BeeBot is currently a work in progress and should be treated as an early stage research project. Its focus is not on production usage at this time.\"\n\n\t\n### Links\n- [GitHub](https:\u002F\u002Fgithub.com\u002FAutoPackAI\u002Fbeebot)\n- [Tweet](https:\u002F\u002Ftwitter.com\u002FDouglas_Schon\u002Fstatus\u002F1681094815021187072?s=20)\n\u003C\u002Fdetails>\n\n\n## [Blinky](https:\u002F\u002Fgithub.com\u002Fseahyinghang8\u002Fblinky)\nAn open-source AI debugging agent for VSCode\n\n\u003Cdetails>\n\n![Banner](https:\u002F\u002Fgithub.com\u002Fseahyinghang8\u002Fblinky\u002Fraw\u002Fmaster\u002Fmedia\u002Fbanner.png)\n\n### Category\nCoding, Debugging\n\n### Description\n- Blinky is an open-source AI debugging agent for VSCode that uses LLMs to help identify and fix backend code errors (inspired by SWE-agent).\n- Blinky leverages the VSCode API, Language Server Protocol (LSP), and print statement debugging to triangulate and address bugs in real-world backend systems.\n\n\t\n### Links\n- [VSCode Extension](https:\u002F\u002Fmarketplace.visualstudio.com\u002Fitems?itemName=blinky.blinky)\n- [Discord](https:\u002F\u002Fdiscord.gg\u002Fd3AUNHDb)\n- [GitHub](https:\u002F\u002Fgithub.com\u002Fseahyinghang8\u002Fblinky)\n\u003C\u002Fdetails>\n\n\n## [Bloop](https:\u002F\u002Fbloop.ai\u002F)\nAI code search, works for Rust and Typescript\n\n\u003Cdetails>\n\n![Image](https:\u002F\u002Fbloop.ai\u002F_next\u002Fstatic\u002Fmedia\u002Flogo_white.b3bdedc0.svg)\n\n### Category\nCoding\n\n### Description\n- A GPT-4 powered semantic code search engine that uses an AI agent\n- Precise code navigation\n- Built on stack graphs and scope queries\n- Fast code search and regex matching engine written in Rust\n- Allows to find Code on Rust and Typescript\n- Allows to stage changes\n- The agent searches both your local and remote repositories with natural language, regex and filtered queries\n- Bloop can be run via app (easy to download via GitHub)\n\n### Links\n- [GitHub](https:\u002F\u002Fgithub.com\u002FBloopAI\u002Fbloop)\n- [\"Getting started\" guide](https:\u002F\u002Fbloop.ai\u002Fdocs\u002Fgetting-started)\n- [Bloop apps](https:\u002F\u002Fgithub.com\u002FBloopAI\u002Fbloop\u002Freleases)\n\n\u003C\u002Fdetails>\n\n## [BondAI](https:\u002F\u002Fbondai.dev\u002F)\nCode interpreter with CLI & RESTful\u002FWebSocket API\n\n\u003Cdetails>\n\n![Image](https:\u002F\u002Fbondai.dev\u002Fassets\u002Fimages\u002Fbondai-logo-9bec7e27b93b804d375221ff8fb6d336.png)\n\n### Category\nCoding\n\n### Description\n- A highly capable, autonomous AI Agent with an easy to use CLI, RESTful\u002FWebSocket API, Pre-built Docker image and a robust suite of integrated tools.\n- Support for all GPT-N, Embeddings and Dall-E OpenAI Models\n- Support for Azure OpenAI Services\n- Easy to use SDK for integration into any application\n- Powerful **Code Interpreter** capabilities\n- Powerful data query capabilities via Postgres DB integration\n- Pre-built Docker image provides safe execution environment for code generation\u002Fexecution\n- Support for telephony applications (via BlandAI)\n- Support for stock trading (via Alpaca Markets)\n- Integrates with Gmail and Google Search\n- Easy to install `pip install bondai`\n- To start the CLI just run `bondai`\n- To start the RESTful\u002FWebSocket API just run `bondai --server`\n\n### Links\n- [BondAI Homepage\u002FDocumentation](https:\u002F\u002Fbondai.dev)\n- [Github Repository](https:\u002F\u002Fgithub.com\u002Fkrohling\u002Fbondai)\n- [Docker Image](https:\u002F\u002Fhub.docker.com\u002Fr\u002Fkrohling\u002Fbondai)\n\n\u003C\u002Fdetails>\n\n## [bumpgen](https:\u002F\u002Fgithub.com\u002Fxeol-io\u002Fbumpgen)\nAI agent that keeps npm dependencies up-to-date\n\n\u003Cdetails>\n\n![demo](\u003Chttps:\u002F\u002Fassets-global.website-files.com\u002F65af8f02f12662528cdc93d6\u002F662e6061d42954630a191417_tanstack-ezgif.com-speed%20(1).gif>)\n\n### Category\nCoding\n\n### Description\n- Put dependency management and upgrades on autopilot\n- bumpgen BUMPs an npm package's version up then GENerates the code fixes for breaking changes\n- Supports gpt-4-turbo\n- Easy install > `npm install -g bumpgen`\n- Easy start > `bumpgen @tanstack\u002Freact-query 5.28.14`\n\n### Links\n- [Repo](https:\u002F\u002Fgithub.com\u002Fxeol-io\u002Fbumpgen)\n- [Docs](https:\u002F\u002Fdocs.xeol.io\u002Fbumpgen\u002Fhome)\n\n\u003C\u002Fdetails>\n\n## [Cal.ai](https:\u002F\u002Fcal.ai)\nOpen-source scheduling assistant built on Cal.com\n\n\u003Cdetails>\n\n![Image](https:\u002F\u002F3620107743-files.gitbook.io\u002F~\u002Ffiles\u002Fv0\u002Fb\u002Fgitbook-x-prod.appspot.com\u002Fo\u002Fspaces%2FpmUOqZjfGqNkiPmqgnMv%2Fuploads%2F9Qaq1hlaTcqKfrc9k4OG%2Fimage.png?alt=media&token=1ffe8530-19ff-4aea-b020-a99cdc224ce1)\n\n### Category\nProductivity\n\n### Description\n- Cal.ai can book meetings, summarize your week, and find time with others based on natural language.\n- Responds flexibly to unseen tasks eg. \"move my second-last meeting to tomorrow morning\".\n- Uses GPT-4 and LangChain Agent Executor under the hood.\n- [GitHub](https:\u002F\u002Fgithub.com\u002Fcalcom\u002Fcal.com\u002Ftree\u002Fmain\u002Fapps\u002Fai)\n\n### Links\n- Authors: [Cal.com core team](https:\u002F\u002Fgithub.com\u002Fcalcom\u002Fcal.com\u002Fgraphs\u002Fcontributors), [Dexter Storey](https:\u002F\u002Fgithub.com\u002Fdexterstorey), [Ted Spare](https:\u002F\u002Fgithub.com\u002Ftedspare)\n\n\u003C\u002Fdetails>\n\n\n## [CAMEL](https:\u002F\u002Fgithub.com\u002Fcamel-ai\u002Fcamel)\nArchitecture for “Mind” Exploration of agents\n\n\u003Cdetails>\n\n![Image](https:\u002F\u002Fraw.githubusercontent.com\u002Fcamel-ai\u002Fcamel\u002Fmaster\u002Fmisc\u002Flogo.png)\n\n### Category\nGeneral purpose\n\n### Description\n- CAMEL is an open-source library designed for the study of autonomous and communicative agents.\n1)AI user agent: give instructions to the AI assistant with the goal of completing the task.\n2) AI assistant agent: follow AI user’s instructions and respond with solutions to the task\n- CAMEL also has an open-source community dedicated to the study of autonomous and communicative agents\n\n### Links\n- [Web](https:\u002F\u002Fwww.camel-ai.org\u002F)\n- [Paper - CAMEL: Communicative Agents for “Mind”\nExploration of Large Scale Language Model Society](https:\u002F\u002Fghli.org\u002Fcamel.pdf)\n- [Colab demo](https:\u002F\u002Fcolab.research.google.com\u002Fdrive\u002F1AzP33O8rnMW__7ocWJhVBXjKziJXPtim?usp=sharing)\n- [GitHub](https:\u002F\u002Fgithub.com\u002Fcamel-ai\u002Fcamel)\n- [Hugging face datasets](https:\u002F\u002Fhuggingface.co\u002Fcamel-ai)\n- [Slack](https:\u002F\u002Fcamel-kwr1314.slack.com\u002Fjoin\u002Fshared_invite\u002Fzt-1vy8u9lbo-ZQmhIAyWSEfSwLCl2r2eKA#\u002Fshared-invite\u002Femail)\n- [Twitter](https:\u002F\u002Ftwitter.com\u002Fintent\u002Ffollow?original_referer=https%3A%2F%2F1508613885-atari-embeds.googleusercontent.com%2F&ref_src=twsrc%5Etfw%7Ctwcamp%5Ebuttonembed%7Ctwterm%5Efollow%7Ctwgr%5ECamelAIOrg&screen_name=CamelAIOrg)\n- Authors: Guohao Li∗ Hasan Abed Al Kader Hammoud* Hani Itani* Dmitrii Khizbullin, Bernard Ghanem\n\n\u003C\u002Fdetails>\n\n## [ChatArena](https:\u002F\u002Fwww.chatarena.org\u002F)\nA chat tool for multi agent interaction\n\n\u003Cdetails>\n\n![image](https:\u002F\u002Fgithub.com\u002FFarama-Foundation\u002Fchatarena\u002Fraw\u002Fmain\u002Fdocs\u002Fimages\u002Fchatarena_architecture.png)\n\n### Category\nDesign, Build-your-own, SDK for AI apps, Multi-agent\n\n### Description\n- ChatArena (or Chat Arena) is a Multi-Agent Language Game Environments for LLMs. The goal is to develop communication and collaboration capabilities of AIs.\nChatArena provides:\n- A general framework for building interactive environments for multiple large language models (LLMs). \n- A collection of pre-built or community-created  environments.\n- User-friendly interfaces with both Web UI and commandline interfaces.\n\n### Links\n- [Web](https:\u002F\u002Fwww.chatarena.org\u002F)\n- [GitHub](https:\u002F\u002Fgithub.com\u002FFarama-Foundation\u002Fchatarena)\n- [X](https:\u002F\u002Ftwitter.com\u002F_chatarena)\n- [Slack channel](https:\u002F\u002Fchatarena.slack.com\u002Fjoin\u002Fshared_invite\u002Fzt-1t5fpbiep-CbKucEHdJ5YeDLEpKWxDOg#\u002Fshared-invite\u002Femail)\n  \n\u003C\u002Fdetails>\n\n## [ChatDev](https:\u002F\u002Fgithub.com\u002FOpenBMB\u002FChatDev)\nCommunicative agents for software development\n\n\u003Cdetails>\n\n![Image](https:\u002F\u002Fgithub.com\u002FOpenBMB\u002FChatDev\u002Fraw\u002Fmain\u002Fmisc\u002Flogo1.png)\n\n### Category\nCoding, Multi-agent\n\n### Description\n- ChatDev is a virtual software company driven by a multitude of intelligent agents assuming different roles such as CEO, CPO, CTO, programmer, reviewer, tester, and art designer, each represented by unique icons.\n- These agents collaborate in a structured organizational environment, fulfilling the company's mission to \"revolutionize the digital world through programming.\" They engage in functional seminars focusing on design, coding, testing, and documentation.\n- ChatDev aims to provide an accessible, modular, and extensible platform based on large language models, facilitating the study of collective intelligence in a controlled setting.\n- The framework allows for extensive customization, empowering users to tailor the software development process, define phases, and establish specific roles within the virtual company.\n- ChatDev is committed to open-source principles, encouraging contributions from the community and sharing advancements transparently.\n\n### Links\n- [Paper - ChatDev: Communicative Agents for Software Development](https:\u002F\u002Farxiv.org\u002Fabs\u002F2307.07924)\n- [Local demo](https:\u002F\u002Fgithub.com\u002FOpenBMB\u002FChatDev\u002Fblob\u002Fmain\u002Fwiki.md#local-demo)\n- [GitHub](https:\u002F\u002Fgithub.com\u002FOpenBMB\u002FChatDev)\n\n\u003C\u002Fdetails>\n\n## [ChemCrow](https:\u002F\u002Fgithub.com\u002Fur-whitelab\u002Fchemcrow-public)\nLangChain agent for chemistry-related tasks\n\n\u003Cdetails>\n\n![Image](https:\u002F\u002Fgithub.com\u002Fur-whitelab\u002Fchemcrow-public\u002Fraw\u002Fmain\u002Fassets\u002Fchemcrow_dark_bold.png)\n\n### Category\nScience, Chemistry\n\n### Description\n- ChemCrow is an open source package for the accurate solution of reasoning-intensive chemical tasks\n- It integrates 13 expert-design tools to augment LLM performance in chemistry and demonstrate effectiveness in automating chemical tasks\n- Built with Langchain\n- The LLM is provided with a list of tool names, descriptions of their utility, and details about the expected input\u002Foutput. It is then instructed to answer a user-given prompt using the tools provided when necessary. The instruction suggests the model to follow the ReAct format - Thought, Action, Action Input, Observation. One interesting observation is that while the LLM-based evaluation concluded that GPT-4 and ChemCrow perform nearly equivalently, human evaluations with experts oriented towards the completion and chemical correctness of the solutions showed that ChemCrow outperforms GPT-4 by a large margin. This indicates a potential problem with using LLM to evaluate its own performance on domains that requires deep expertise. The lack of expertise may cause LLMs not knowing its flaws and thus cannot well judge the correctness of task results. (Source: [Weng, Lilian. (Jun 2023). LLM-powered Autonomous Agents\". Lil’Log. https:\u002F\u002Flilianweng.github.io\u002Fposts\u002F2023-06-23-agent\u002F.](https:\u002F\u002Flilianweng.github.io\u002Fposts\u002F2023-06-23-agent\u002F))\n\n### Links\n- [Paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F2304.05376)\n- [GitHub](https:\u002F\u002Fgithub.com\u002Fur-whitelab\u002Fchemcrow-public)\n- [HackerNews Discussion](https:\u002F\u002Fnews.ycombinator.com\u002Fitem?id=35607616)\n\n\u003C\u002Fdetails>\n\n## [Clippy](https:\u002F\u002Fgithub.com\u002Fennucore\u002Fclippy\u002F)\nAgent that can plan, write, debug, and test code\n\n\u003Cdetails>\n\n![Image](https:\u002F\u002Flev.la\u002Fimages\u002Fclippy.jpg)\n\n### Category\nCoding\n\n### Description\n- The purpose of Clippy is to elop code for or with the user.\n- It can plan, write, debug, and test some projects autonomously.\n- For harder tasks, the best way to use it is to look at its work and provide feedback to it.\n\n### Links\n- [GitHub](https:\u002F\u002Fgithub.com\u002Fennucore\u002Fclippy\u002F)\n- Author: [Lev Chizhov](http:\u002F\u002Flev.la\u002F) \n\n\u003C\u002Fdetails>\n\n## [CodeFuse-ChatBot](https:\u002F\u002Fgithub.com\u002Fcodefuse-ai\u002Fcodefuse-chatbot)\nAgent serving entire SW development lifecycle\n\u003Cdetails>\n\n![Image](https:\u002F\u002Fgithub.com\u002Fcodefuse-ai\u002Fcodefuse-chatbot\u002Fraw\u002Fmain\u002Fsources\u002Fdocs_imgs\u002Fobjective_v4.png)\n\n### Category\nCoding\n\n### Description\n- An intelligent assistant serving the entire software development lifecycle, powered by a Multi-Agent Framework, working with DevOps Toolkits, Code&Doc Repo RAG, etc.\n\n### Links\n- [GitHub](https:\u002F\u002Fgithub.com\u002Fcodefuse-ai\u002Fcodefuse-chatbot)\n\n\u003C\u002Fdetails>\n\n## [Cody by ajhous44](https:\u002F\u002Fgithub.com\u002Fajhous44\u002Fcody)\nQuery and navigate your codebase\n\n\u003Cdetails>\n\n![Image](https:\u002F\u002Fgithub.githubassets.com\u002Fassets\u002FGitHub-Mark-ea2971cee799.png)\n\n### Category\nCoding\n\n### Description\n- An AI assistant designed to let you interactively query your codebase using natural language.\n- By utilizing vector embeddings, chunking, and OpenAI's language models, Cody can help you navigate through your code in an efficient and intuitive manner.\n\n### Links\n- [GitHub](https:\u002F\u002Fgithub.com\u002Fajhous44\u002Fcody)\n- Author: [@ajhous44](https:\u002F\u002Fgithub.com\u002Fajhous44\u002F) (Github)\n\n\u003C\u002Fdetails>\n\n## [Cody by Sourcegraph](https:\u002F\u002Fdocs.sourcegraph.com\u002Fcody)\nAgent that writes code and answers your questions\n\n\u003Cdetails>\n\n![Image](https:\u002F\u002Fsourcegraph.com\u002F.assets\u002Fimg\u002Fsourcegraph-mark.svg?v2)\n\n### Category\nCoding\n\n### Description\nAn AI code assistant from Sourcegraph that writes code and answers questions for you by reading your entire codebase and the code graph.\n\n### Links\n- [GitHub](https:\u002F\u002Fgithub.com\u002Fsourcegraph\u002Fsourcegraph\u002Ftree\u002Fmain\u002Fclient\u002Fcody)\n- Author: [@sourcegraph](https:\u002F\u002Ftwitter.com\u002Fsourcegraph) (Twitter)\n\n\u003C\u002Fdetails>\n\n## [Continue](https:\u002F\u002Fcontinue.dev\u002F)\nOpen-source autopilot for software development\n\n\u003Cdetails>\n\n![Image](https:\u002F\u002Fcontinue.dev\u002Fdocs\u002Fassets\u002Fimages\u002Fcontinue-cover-logo-aa135cc83fe8a14af480d1633ed74eb5.png)\n\n### Category\nCoding\n\n### Description\n- An open-source autopilot for software development—bring the power of ChatGPT to VS Code\n- Features:\n\t- Answer coding questions\n   \t- Edit in natural language\n   \t- Generate files from scratch\n\n\n### Links\n- [Website](https:\u002F\u002Fcontinue.dev\u002F)\n- [GitHub](https:\u002F\u002Fgithub.com\u002Fcontinuedev\u002Fcontinue)\n- [Documentation](https:\u002F\u002Fcontinue.dev\u002Fdocs\u002Fintro)\n- [Twitter](https:\u002F\u002Ftwitter.com\u002Fcontinuedev)\n\n\u003C\u002Fdetails>\n\n## [CrewAI](https:\u002F\u002Fgithub.com\u002Fjoaomdmoura\u002Fcrewai)\nFramework for orchestrating role-playing agents\n\u003Cdetails>\n\n![Image](https:\u002F\u002Fgithub.com\u002Fjoaomdmoura\u002FcrewAI\u002Fraw\u002Fmain\u002Fdocs\u002Fcrewai_logo.png)\n\n### Category\nBuild-your-own, SDK for agents, Multi-agent\n\n### Description\n- Cutting-edge framework for orchestrating role-playing, autonomous AI agents.\n- By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.\n- Crew AI is a multi-agent framework built on LangChain, aiming to empower engineers to harness the collective power of AI agents. In contrast to traditional automation methods, Crew AI introduces a new approach to collaborative decision-making, enhanced creativity, and solving complex problems.\n- The design philosophy of Crew AI advocates simplicity through modularity. Its main components include agents, tools, tasks, processes, and crews. Each agent is akin to a team member, possessing specific roles, background stories, goals, and memories. Through modular design, we make the intricate world of AI agents accessible, manageable, and more engaging.\n\n\n### Links\n- [GitHub](https:\u002F\u002Fgithub.com\u002Fjoaomdmoura\u002Fcrewai)\n- [Founder's X](https:\u002F\u002Ftwitter.com\u002Fjoaomdmoura)\n- [Blog post: How to use Crew AI](https:\u002F\u002Fcrewai.net\u002Fposts\u002Fhow-to-use-crew-ai)\n- [Crew AI Wiki with examples and guides](https:\u002F\u002Fgithub.com\u002Fjoaomdmoura\u002FCrewAI\u002Fwiki)\n- [Docs](https:\u002F\u002Fgithub.com\u002Fjoaomdmoura\u002FCrewAI\u002Fwiki)\n- [Discord](https:\u002F\u002Fdiscord.com\u002Finvite\u002FX4JWnZnxPb)\n\n\u003C\u002Fdetails>\n\n## [data-to-paper](https:\u002F\u002Fgithub.com\u002FTechnion-Kishony-lab\u002Fdata-to-paper)\nAI-driven research from data to human-verifiable research papers\n\u003Cdetails>\n\n\u003Cbr>\n\u003Cimg src=\"https:\u002F\u002Fgithub.com\u002FTechnion-Kishony-lab\u002Fdata-to-paper\u002Fassets\u002F65530510\u002Fe33bcb52-5f4e-4fd0-8be9-ebd64607c449\" width=\"400\" align=\"center\">\n\u003Cbr>\n\t\n### Category\nScience, Research, Multi-agent\n\n### Description\n[*data-to-paper*](https:\u002F\u002Farxiv.org\u002Fabs\u002F2404.17605) is a framework for systematically navigating the power of AI to perform complete end-to-end \nscientific research, starting from raw data and concluding with comprehensive, transparent, and human-verifiable \nscientific papers.\n\nTowards this goal, *data-to-paper* systematically guides interacting \nLLM and rule-based agents through the conventional scientific path, from annotated data, through creating \nresearch hypotheses, conducting literature search, writing and debugging data analysis code, \ninterpreting the results, and ultimately the step-by-step writing of a complete research paper.\n\nThe *data-to-paper* framework is created as a research project to understand the \ncapacities and limitations of LLM-driven scientific research, and to develop ways of harnessing LLM to accelerate \nresearch while maintaining, and even enhancing, key scientific values, such as transparency, traceability and verifiability, \nand while allowing scientist to oversee and direct the process \n[see also: [living guidelines](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fd41586-023-03266-1)].\n\n\n### Links\n- [GitHub](https:\u002F\u002Fgithub.com\u002FTechnion-Kishony-lab\u002Fdata-to-paper)\n- [arXiv preprint](https:\u002F\u002Farxiv.org\u002Fabs\u002F2404.17605)\n- [Demo video](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=Nt_460MmM8k)\n\n\u003C\u002Fdetails>\n\n\n## [Databerry](https:\u002F\u002Fwww.databerry.ai\u002F)\n(Pivoted to Chaindesk) No-code chatbot building\n\n\u003Cdetails>\n\n![Image](https:\u002F\u002Fwww.chaindesk.ai\u002F_next\u002Fimage?url=%2Fapp-logo-icon.png&w=256&q=75)\n\n### Category\nBuild-your-own\n\n### Description\n- A super-easy no-code platform for creating AI chatbots trained on your own data\n- After creating new agent, picking a model, data and other settings, they are ready to be deployed to website, Slack, Crisp, or Zapier\n- Limit of agent in the free version\n- Stack\n\t- Next.js\n\t- Joy UI\n\t- LangchainJS\n\t- PostgreSQL\n\t- Prisma\n\t- Qdrant\n- Features\n\t- Streamline customer support, onboard new team members, and more\n\t- Load data from anywhere\n\t- No-code: User-friendly interface to manage your datastores and chat with your data\n\t- Secured API endpoint for querying your data\n\t- Auto sync data sources (coming soon)\n\t- Auto generates a ChatGPT Plugin for each datastore\n\n### Links\n- [Documentation](https:\u002F\u002Fdocs.chaindesk.ai\u002Fintroduction)\n- [Discord](https:\u002F\u002Fdiscord.com\u002Finvite\u002FFSWKj49ckX)\n- [GitHub](https:\u002F\u002Fgithub.com\u002Fgmpetrov\u002Fdataberry)\n\n\u003C\u002Fdetails>\n\n## [DemoGPT](https:\u002F\u002Fgithub.com\u002Fmelih-unsal\u002FDemoGPT)\nGenerates demo of a new app (of any purpose)\n\n\u003Cdetails>\n\n![Image](https:\u002F\u002Fgithub.com\u002Fmelih-unsal\u002FDemoGPT\u002Fraw\u002Fmain\u002Fassets\u002Fbanner_small.png)\n\n### Category\nBuild-your-own, General purpose\n\n### Description\n- DemoGPT leverages the power of Language Models (LLMs) to provide fast and effective demo creation for applications.\n- Automates the prototyping process, making it more efficient and saving valuable time.\n- Understands and processes the given prompts to generate relevant applications.\n- Integrated with LangChain for generating application code through iterative parsing of LangChain's documentation with a \"Tree of Transformations\" (ToT) approach.\n- The roadmap for DemoGPT includes constant updates and improvements based on user feedback and real-world application, working towards refining the technology and solving the hallucination problem.\n- \"We are planning to introduce features that will further enhance the application generation process, making it more user-friendly and efficient.\"\n\n### Links\n- [Github](https:\u002F\u002Fgithub.com\u002Fmelih-unsal\u002FDemoGPT)\n- [Website](https:\u002F\u002Fwww.demogpt.io\u002F)\n- [Twitter](https:\u002F\u002Ftwitter.com\u002Fdemo_gpt)\n- [Streamlit App](https:\u002F\u002Fdemogpt.streamlit.app\u002F)\n- [Hugging Face Space](https:\u002F\u002Fhuggingface.co\u002Fspaces\u002Fmelihunsal\u002Fdemogpt)\n\n\u003C\u002Fdetails>\n\n## [DevGPT](https:\u002F\u002Fgithub.com\u002Fjina-ai\u002Fdev-gpt)\nTeam of virtual developers\n\n\u003Cdetails>\n\n![Image](https:\u002F\u002Fpbs.twimg.com\u002Fprofile_images\u002F1684472754597142529\u002FtyM92sRA_400x400.jpg)\n### Category\nCoding, Multi-agent\n\n### Description\n- \"Tell your AI team what microservice you want to build, and they will do it for you. Your imagination is the limit!!\n- Welcome to Dev-GPT, where we bring your ideas to life with the power of advanced artificial intelligence! Our automated development team is designed to create microservices tailored to your specific needs, making your software development process seamless and efficient. Comprised of a virtual Product Manager, Developer, and DevOps, our AI team ensures that every aspect of your project is covered, from concept to deployment.\n\n### Links\n- [Discord](https:\u002F\u002Fdiscord.com\u002Finvite\u002FAWXCCC6G2P)\n\n\u003C\u002Fdetails>\n\n## [Devika](https:\u002F\u002Fgithub.com\u002Fstitionai\u002Fdevika)\nAgentic AI Software Engineer\n\n\u003Cdetails>\n\n![Image](https:\u002F\u002Fgithub.com\u002Fstitionai\u002Fdevika\u002Fraw\u002Fmain\u002F.assets\u002Fdevika-screenshot.png)\n### Category\nCoding, general purpose\n\n### Description\n- Devika is an Agentic AI Software Engineer that can understand high-level human instructions, break them down into steps, research relevant information, and write code to achieve the given objective.\n- Devika aims to be a competitive open-source alternative to Devin by Cognition AI.\n\n### Links\n- [GitHub](https:\u002F\u002Fgithub.com\u002Fstitionai\u002Fdevika)\n\n\u003C\u002Fdetails>\n\n## [Devon](https:\u002F\u002Fgithub.com\u002Fentropy-research\u002FDevon)\nOpen-source Devin alternative\n\n\u003Cdetails>\n\n![Image]()\n### Category\nCoding, general purpose\n\n### Description\n- Open-source alternative to Devin by Entropy research\n\n### Links\n- [GitHub](https:\u002F\u002Fgithub.com\u002Fentropy-research\u002FDevon)\n\n\u003C\u002Fdetails>\n\n## [DevOpsGPT](https:\u002F\u002Fgithub.com\u002Fkuafuai\u002FDevOpsGPT)\nAI-Driven SW Development Automation Solution\n\n\u003Cdetails>\n\n![Image](https:\u002F\u002Fgithub.com\u002Fkuafuai\u002FDevOpsGPT\u002Fraw\u002Fmaster\u002Fdocs\u002Ffiles\u002Fintro-flow-simple.png)\n\n### Category\nCoding\n\n### Description\nWelcome to the AI Driven Software Development Automation Solution, abbreviated as DevOpsGPT. We combine LLM (Large Language Model) with DevOps tools to convert natural language requirements into working software. This innovative feature greatly improves development efficiency, shortens development cycles, and reduces communication costs, resulting in higher-quality software delivery.\n\n### Features and Benefits\n* Improved development efficiency: No need for tedious requirement document writing and explanations. Users can interact directly with DevOpsGPT to quickly convert requirements into functional software.\n* Shortened development cycles: The automated software development process significantly reduces delivery time, accelerating software deployment and iterations.\n* Reduced communication costs: By accurately understanding user requirements, DevOpsGPT minimizes the risk of communication errors and misunderstandings, enhancing collaboration efficiency between development and business teams.\n* High-quality deliverables: DevOpsGPT generates code and performs validation, ensuring the quality and reliability of the delivered software.\n* [Enterprise Edition] Existing project analysis: Through AI, automatic analysis of existing project information, accurate decomposition and development of required tasks on the basis of existing projects.\n* [Enterprise Edition] Professional model selection: Support language model services stronger than GPT in the professional field to better complete requirements development tasks, and support private deployment.\n* [Enterprise Edition] Support more DevOps platforms: can connect with more DevOps platforms to achieve the development and deployment of the whole process.\n\n### Links\n- [Creator Website](https:\u002F\u002Fwww.kuafuai.net\u002F)\n- [Demo Video](https:\u002F\u002Fyoutu.be\u002FIWUPbGrJQOU)\n\n\u003C\u002Fdetails>\n\n## [dotagent](https:\u002F\u002Fgithub.com\u002Fdot-agent\u002Fdotagent)\nDeploy agents on cloud, PCs, or mobile devices\n\n\u003Cdetails>\n\n![Image](https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F133483033?s=200&v=4)\n\n### Category\nBuild-your-own\n\n### Description\n- An agent management system that facilitates the creation of robust AI applications and experimental autonomous agents through a rich suite of developer tools.\n- Enables the deployment of agents across multiple platforms including cloud, PCs, or mobile devices, and extends functionality through Python or plain English integrations.\n- Advances prompt engineering with a powerful prompt compiler, offering a higher degree of control over Language Models, significantly optimizing the response generation process.\n- Allows seamless export of agents into portable files for execution in any environment, along with an optional Agentbox feature for optimized computing resource management within a sandboxed environment.\n\n### Links\n- [YouTube video](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=uE_fykl8AVI&ab_channel=FahdMirza)\n\n\u003C\u002Fdetails>\n\n## [Eidolon](https:\u002F\u002Feidolonai.com\u002F)\nMulti Agent SDK with pluggable, modular components\n\n\u003Cdetails>\n\n![Image](https:\u002F\u002Fwww.eidolonai.com\u002F_astro\u002Fdefault.jKAYXmpI_ZWVg5E.webp)\n\n### Category\nBuild-your-own (agent-builing frameworks and platforms), SDK for AI apps\n\n### Description\n- Eidolon is an open source SDK for AI agents\n\n### Links\n- [Web](https:\u002F\u002Feidolonai.com\u002F)\n- [GitHub](https:\u002F\u002Fgithub.com\u002Feidolon-ai\u002Feidolon)\n- [LinkedIn](https:\u002F\u002Fwww.linkedin.com\u002Fcompany\u002Faugust-data\u002F)\n- [Dave Brewster - LinkedIn](https:\u002F\u002Fwww.linkedin.com\u002Fin\u002Fdave-brewster-first\u002F)\n- [Ravi Ramachandran - LinkedIn](https:\u002F\u002Fwww.linkedin.com\u002Fin\u002Fravi-nextlevelgtm\u002F)\n- [Luke Lalor - LinkedIn](https:\u002F\u002Fwww.linkedin.com\u002Fin\u002Flukehlalor\u002F)\n\n\u003C\u002Fdetails>\n\n## [English Compiler](https:\u002F\u002Fgithub.com\u002Fuilicious\u002Fenglish-compiler)\nConverting markdown specs into functional code\n\n\u003Cdetails>\n\n![Image](https:\u002F\u002Fgithub.com\u002Fuilicious\u002Fenglish-compiler\u002Fraw\u002Fmain\u002Fnotes\u002Fimgs\u002FEnglishCommand-CLI-help.png)\n\n### Category\nCoding\n\n### Description\n- OC AI based Compiler, for converting english based markdown specs, into functional code\n- \"We know that all great™ projects start with awesome™ detailed functional specifications. Which is typically written in English, or its many other spoken language alternatives.\n- So what if, instead of writing code from functional specs, we simply compile it directly to code?\n- Into a future, where we replace nearly everything, with just written text.\"\n\n### Links\n- [Creator's Twitter](https:\u002F\u002Ftwitter.com\u002Fpicocreator)\n\n\u003C\u002Fdetails>\n\n## [evo.ninja](https:\u002F\u002Fevo.ninja\u002F)\nAI agent that adapts its persona to achive tasks\n\n\u003Cdetails>\n\n![Image](https:\u002F\u002Fcamo.githubusercontent.com\u002F3333c49067bddef0b208e36e22cf6ec8066f5be1da1dc327532427a395ed8069\u002F68747470733a2f2f6861636b6d642e696f2f5f75706c6f6164732f4279576a4c4b41686e2e706e67)\n\n### Category\nGeneral purpose, Research, Multi-agent\n\n### Description\n- What makes evo.ninja special is that it adapts itself in real-time, based on the tasks at hand.\n- Evo utilizes pre-defined agent personas that are tailored to specific domains of tasks.\n- Each iteration of evo's execution loop it will select and adopt the persona that fits the task at hand best.\n\n### Links\n- [Web](https:\u002F\u002Fevo.ninja\u002F)\n- [GitHub](https:\u002F\u002Fgithub.com\u002Fpolywrap\u002Fevo.ninja\u002F)\n- [Discord](https:\u002F\u002Fdiscord.com\u002Finvite\u002Fr3rwh69cCa)\n\n\u003C\u002Fdetails>\n\n## [FastAgency](https:\u002F\u002Ffastagency.ai\u002Flatest\u002F)\nThe fastest way to deploy multi-agent workflows\n\n\u003Cdetails>\n\n![Image](https:\u002F\u002Ffastagency.ai\u002Flatest\u002Fassets\u002Fimg\u002Flogo.svg)\n\n### Category\nBuild-your-own (agent-builing frameworks and platforms), SDK for AI apps, Multi-agent, Supports open-source models\n\n### Description\n- \"FastAgency is an open-source framework designed to accelerate the transition from prototype to production for multi-agent AI workflows.\n- For developers who use the AutoGen framework, FastAgency enables you to seamlessly scale Jupyter notebook prototypes into fully functional, production-ready applications.\n- With multi-framework support, a unified programming interface, and powerful API integration capabilities, FastAgency streamlines the deployment process, saving time and effort while maintaining flexibility and performance.\n\n### Links\n- [Web](https:\u002F\u002Ffastagency.ai\u002Flatest\u002F)\n- [GitHub](https:\u002F\u002Fgithub.com\u002Fairtai\u002Ffastagency)\n\n\u003C\u002Fdetails>\n\n## [Flowise](https:\u002F\u002Fflowiseai.com\u002F)\nLow code Agent builder\n\n\u003Cdetails>\n\n![Image](https:\u002F\u002Fflowiseai.com\u002F_next\u002Fimage?url=%2F_next%2Fstatic%2Fmedia%2Flogo-color-high.e60de2f8.png&w=384&q=75)\n\n### Category\nBuild-your-own (agent-builing frameworks and platforms)\n\n### Description\n- Flowise is an open source low-code tool for developers to build customized LLM orchestration flow & AI agents\n\n### Links\n- [Web](https:\u002F\u002Fflowiseai.com\u002F)\n- [GitHub](https:\u002F\u002Fgithub.com\u002FFlowiseAI\u002FFlowise)\n- [X (Twitter)](https:\u002F\u002Fx.com\u002FFlowiseAI)\n- [LinkedIn](https:\u002F\u002Fwww.linkedin.com\u002Fcompany\u002Fflowiseai\u002F)\n\n\u003C\u002Fdetails>\n\n\n## [Friday](https:\u002F\u002Fgithub.com\u002Famirrezasalimi\u002Ffriday\u002F)\nAI developer assistant for Node.js\n\n\u003Cdetails>\n\n![Image](https:\u002F\u002Fgithub.com\u002Famirrezasalimi\u002Ffriday\u002Fraw\u002Fmain\u002Fscreenshot.png)\n\n### Category\nCoding\n\n### Description\n- A developer assistant able to make whole nodejs project with unlimited prompts\n- Provides a core prompt for building the foundation of your application\n- Allows you to add unlimited sections, each of which is a prompt representing a specific part of your app\n- Features\n\t- Friday utilizes GPT-4 for AI assistance, but it has been tested and optimized with GPT-4-32k for improved speed and better results.\n\t- It requires 2 small requests for your app's base and 1 request per section you provide.\n\t- Friday employs esbuild behind the scenes for every app created by it.\n\n### Links\n- **Author:** [Amirreza Salimi](https:\u002F\u002Ftwitter.com\u002Famirsalimiiii)\n\n\u003C\u002Fdetails>\n\n## [GeniA](https:\u002F\u002Fgithub.com\u002Fgenia-dev\u002FGeniA)\nEngineering platform engineering AI team member\n\n\u003Cdetails>\n\n![Image](https:\u002F\u002Fgithub.com\u002Fgenia-dev\u002FGeniA\u002Fraw\u002Fmain\u002Fmedia\u002Fgenia_title.png)\n\n### Category\nCoding\n\n### Description\n- GeniA is able to work along side you on your production enviroment, executing tasks on your behalf in your dev & cloud environments, AWS\u002Fk8s\u002FArgo\u002FGitHub etc.\n- Allows you to enhance the platform by integrating your own tools and APIs.\n- Slack App Bot integration.\n- Supports GPT-3.5 & GPT-4.\n\n### Links\n- Authors: [Uri Shamay](https:\u002F\u002Fgithub.com\u002Fcmpxchg16), [Shlomi Shemesh](https:\u002F\u002Fgithub.com\u002Fshlomsh)\n\n\u003C\u002Fdetails>\n\n## [Godmode](https:\u002F\u002Fgodmode.space\u002F)\nInspired by AutoGPT and BabyAGI, with nice UI\n\n\u003Cdetails>\n\n![Image](https:\u002F\u002Ftoolpulse.ai\u002Fwp-content\u002Fuploads\u002F2023\u002F11\u002Fgodmode-ai.jpg)\n\n### Category\nGeneral purpose\n\n### Description\n- Godmode is a project inspired by Auto-GPT and BabyAGI, conducting  various kinds of tasks via nice UI\n- A web platform inspired by AutoGPT and BabyAGI\n- What it can do:\n\t- Order your coffee at Starbucks\n\t- Perform market analysis\n\t- Find and negotiate a lease\n- Supports GPT-3.5 & GPT-4\n\n### Links\n- [GitHub](https:\u002F\u002Fgithub.com\u002FFOLLGAD\u002FGodmode-GPT)\n- Authors: [Emil Ahlbäck](https:\u002F\u002Ftwitter.com\u002Femilahlback), [Lonis](https:\u002F\u002Ftwitter.com\u002F_Lonis_)\n- [Discord](https:\u002F\u002Fdiscord.com\u002Finvite\u002FvSzCcDDwz3)\n- [Tweet](https:\u002F\u002Ftwitter.com\u002F_Lonis_\u002Fstatus\u002F1646641412182536196)\n\n\u003C\u002Fdetails>\n\n## [GPT Discord](https:\u002F\u002Fgithub.com\u002FKav-K\u002FGPTDiscord)\nThe ultimate AI agent integration for Discord\n\n\u003Cdetails>\n\n![image](https:\u002F\u002Fcamo.githubusercontent.com\u002Fc02e68bf20c853637e8cfb02c9406bd2b3b20637ea4ed95b7d68819e94a01dfe\u002F68747470733a2f2f692e696d6775722e636f6d2f425a644f52544c2e706e67)\n\n### Category\nContent creation, Productivity, General purpose, Discord\n\n### Description\n- GPT Discord is a robust, all-in-one GPT interface for Discord.\n- GPT Discord supports everything from multi-modality image understanding, code interpretation, advanced data analysis, Q&A on your own documents, internet-connected chat with Wolfram Alpha and Google access, AI-moderation, image generation with DALL-E, and much more!\n- Featuring code execution and environment manipulation by E2B\n- ![image](https:\u002F\u002Fcamo.githubusercontent.com\u002F6806eb5cd7f4a14e693bc732a304f18c5413a493c92b4b73202ec3205017b9c8\u002F68747470733a2f2f692e696d6775722e636f6d2f547366677455322e706e67)\n- LLMs\u002Fmodel providers supported:\n  - OpenAI models\n\n### Links\n- [GitHub](https:\u002F\u002Fgithub.com\u002FKav-K\u002FGPTDiscord)\n- [Kaveen Kumarasinghe - founder of GPT Discord - website](https:\u002F\u002Fkaveenk.com\u002F)\n- [Kaveen Kumarasinghe - founder of GPT Discord - LinkedIn](https:\u002F\u002Fwww.linkedin.com\u002Fin\u002Fkaveenk\u002F)\n\n  \n\u003C\u002Fdetails>\n\n## [GPT Engineer](https:\u002F\u002Fgptengineer.app\u002F)\nGenerates entire codebase based on a prompt\n\n\u003Cdetails>\n\n![Image](https:\u002F\u002Fpbs.twimg.com\u002Fmedia\u002FGDA3bYrXYAE5XDQ?format=jpg&name=4096x4096)\n\n### Category\nCoding\n\n### Description\nGPT Engineer is an AI agent that generates an entire codebase based on a prompt.\n- Model: GPT 4\n- Specify your project, and the AI agent asks for clarification, and then constructs the entire code base\n- Features\n\t- Made to be easy to adapt, extend, and make your agent learn how you want your code to look. It generates an entire codebase based on a prompt\n\t- You can specify the \"identity\" of the AI agent by editing the files in the identity folder\n\t- Editing the identity and evolving the main prompt is currently how you make the agent remember things between projects\n\t- Each step in steps.py will have its communication history with GPT4 stored in the logs folder, and can be rerun with scripts\u002Frerun_edited_message_logs.py\n\n\n### Links\n- [Web](https:\u002F\u002Fgptengineer.app)\n- [GitHub](https:\u002F\u002Fgithub.com\u002FAntonOsika\u002Fgpt-engineer)\n- [Discord](https:\u002F\u002Fdiscord.com\u002Finvite\u002F8tcDQ89Ej2)\n- Author: [Anton Osika](https:\u002F\u002Ftwitter.com\u002Fantonosika)\n- [Twitter review by @Attack](https:\u002F\u002Ftwitter.com\u002FAttack\u002Fstatus\u002F1671165869064609792)\n\n\u003C\u002Fdetails>\n\n## [GPT Migrate](https:\u002F\u002Fgithub.com\u002F0xpayne\u002Fgpt-migrate)\nMigrate codebase between frameworks\u002Flanguages\n\n\u003Cdetails>\n\n![Image](https:\u002F\u002Fopengraph.githubassets.com\u002F678543c5159118a70ea974db32bb95b310a3fbb6ad4296e97d54335031f8df82\u002Fjoshpxyne\u002Fgpt-migrate)\n\n### Category\nCoding\n\n### Description\nGOT Migrate easily migrates your codebase from one framework or language to another.\n- Pick from different LLMs\n- Ability to allow GPT Migration to generate and run unit tests for the new codebase\n- Ability to select source and target language of the migration\n- Ability to customize the agent's workflow (setup -> migrate -> test)\n- GPT Migrate team is working on adding [benchmarks](https:\u002F\u002Fgithub.com\u002F0xpayne\u002Fgpt-migrate#-benchmarks) for the agent\n\n### Links\n- [Website](https:\u002F\u002Fgpt-migrate.com\u002F)\n- Author: [Josh Payne](https:\u002F\u002Ftwitter.com\u002Fjoshpxyne)\n- [Announcement](https:\u002F\u002Ftwitter.com\u002Fjoshpxyne\u002Fstatus\u002F1675254164165910528)\n\n\n\u003C\u002Fdetails>\n\n## [GPT Pilot](https:\u002F\u002Fgithub.com\u002FPythagora-io\u002Fgpt-pilot)\nCode the entire scalable app from scratch\n\n\u003Cdetails>\n\n![Image](https:\u002F\u002Ftechcrunch.com\u002Fwp-content\u002Fuploads\u002F2023\u002F08\u002Fgpt_pilot_logo.png?w=150)\n\n### Category\nCoding\n\n### Description\nGPT Pilot is an AI agent that codes the entire app as you oversee the code being written\n- Dev tool that writes scalable apps from scratch while the developer oversees the implementation\n- A research project to see how can GPT-4 be utilized to generate fully working, production-ready, apps\n- The main idea is that AI can write most of the code for an app (maybe 95%) but for the rest 5%, a developer is and will be needed until we get full AGI\n\n### Links\n- [GitHub](https:\u002F\u002Fgithub.com\u002FPythagora-io\u002Fgpt-pilot)\n- [Discord](https:\u002F\u002Fdiscord.com\u002Finvite\u002FHaqXugmxr9)\n\n\n\u003C\u002Fdetails>\n\n\n## [GPT Researcher](https:\u002F\u002Fgithub.com\u002Fassafelovic\u002Fgpt-researcher)\nAgent that researches entire internet on any topic\n\n\u003Cdetails>\n\n![Image](https:\u002F\u002Fcamo.githubusercontent.com\u002Fb3ab3e2b5612657816d64e174672498cd50027b75aa0a795833aee2ddab585b2\u002F68747470733a2f2f636f7772697465722d696d616765732e73332e616d617a6f6e6177732e636f6d2f6172636869746563747572652e706e67)\n\n### Category\nResearch, Science\n\n### Description\nGPT Researcher is a GPT-based autonomous agent that does online comprehensive research on any given topic\n- Can produce detailed, factual and unbiased research reports\n- Offers customization options for focusing on relevant resources, outlines, and lessons\n- Addresses issues of speed and determinism, offering a more stable performance and increased speed through parallelized agent work, as opposed to synchronous operation\n- Inspired by AutoGPT and the Plan-and-Solve paper\n- The main idea is to run \"planner\" and \"execution\" agents, whereas the planner generates questions to research, and the execution agents seek the most related information based on each generated research question\n\n### Links\n- [Website](https:\u002F\u002Ftavily.com\u002F)\n- [Discord](https:\u002F\u002Fdiscord.com\u002Finvite\u002F2pFkc83fRq)\n- Author: [Assaf Elovic](https:\u002F\u002Ftwitter.com\u002Fassaf_elovic)\n\n\n\u003C\u002Fdetails>\n\n## [GPT Runner](https:\u002F\u002Fgithub.com\u002Fnicepkg\u002Fgpt-runner)\nAgent that converses with your files\n\n\u003Cdetails>\n\n![image](https:\u002F\u002Frepository-images.githubusercontent.com\u002F640476297\u002F30741f73-caac-48bc-b500-1b7d6efde4c4)\n\n### Category\nResearch, Science\n\n### Description\n- Conversation with your files which selected by you, no embedding, no vector database!\n- It's also a AI Prompt Storybook. You can use it to manage some AI preset with your team. It support any IDE and language developer. We provide cli to run web and VSCode extension, Jetbrains plugin is coming soon.\n- Private first, all data is local.\n- We support both OpenAI and Anthropic (Claude-2)\n- It support support for multiple languages.\n\n### Links\n- [Website](https:\u002F\u002Fgithub.com\u002Fnicepkg\u002Fgpt-runner)\n- Author: [Jinming Yang](https:\u002F\u002Fgithub.com\u002F2214962083)\n\n\n\u003C\u002Fdetails>\n\n## [GPTSwarm](https:\u002F\u002Fgptswarm.org\u002F)\nLanguage Agents as Optimizable Graphs\n\n\u003Cdetails>\n\n![image](https:\u002F\u002Fgptswarm.org\u002Fimages\u002Fgptswarm.png)\n\n### Category\nBuild-your-own (agent-builing frameworks and platforms), General purpose, Multi-agent\n\n### Description\n- 🐝 GPTSwarm is a graph-based framework for LLM-based agents, providing two high-level features:\n  - It lets you build LLM-based agents from graphs.\n  - It enables the customized and automatic self-organization of agent swarms with self-improvement capabilities.\n- Various human-designed prompt engineering techniques have been proposed to improve problem solvers based on Large Language Models (LLMs), yielding many disparate code bases. We unify these approaches by describing LLM-based agents as computational graphs. Each node implements a function to process multim","awesome-ai-agents 是一个收录了众多自主 AI 代理的列表。该项目的核心功能是提供一个全面且分类清晰的开源与闭源 AI 代理项目目录，涵盖了从自动数据标注到代码生成等多个应用场景。技术特点包括支持多种编程语言和框架，并且持续更新以囊括最新的AI代理工具。适合开发者、研究人员以及对人工智能领域感兴趣的任何人使用，无论是寻找合适的AI代理解决方案还是探索最新的人工智能技术趋势，都能从中受益。",2,"2026-06-11 03:24:28","top_topic"]