[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-72286":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":16,"stars7d":17,"stars30d":17,"stars90d":16,"forks30d":16,"starsTrendScore":16,"compositeScore":18,"rankGlobal":10,"rankLanguage":10,"license":19,"archived":20,"fork":20,"defaultBranch":21,"hasWiki":22,"hasPages":20,"topics":23,"createdAt":10,"pushedAt":10,"updatedAt":41,"readmeContent":42,"aiSummary":43,"trendingCount":16,"starSnapshotCount":16,"syncStatus":17,"lastSyncTime":44,"discoverSource":45},72286,"Devon","entropy-research\u002FDevon","entropy-research","Devon: An open-source pair programmer","",null,"Python",3448,283,31,26,0,2,60.56,"GNU Affero General Public License v3.0",false,"main",true,[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40],"agent","agent-based-framework","agent-based-model","ai","ai-developer","ai-software","ai-software-engineer","code-assistant","code-generation","developer-tool","developer-tools","gpt-4","gpt-4o","groq","llama3","ollama","vscode","2026-06-12 04:01:04","\n\u003C!-- PROJECT LOGO -->\n\u003Cdiv align=\"center\">\n  \u003Ch1 align=\"center\">Devon: An open-source pair programmer\u003C\u002Fh1>\n\u003C\u002Fdiv>\n\u003Cdiv align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fentropy-research\u002FDevon\u002Fgraphs\u002Fcontributors\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fcontributors\u002Fentropy-research\u002Fdevon?style=for-the-badge&color=lime\" alt=\"Contributors\">\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fentropy-research\u002FDevon\u002Fnetwork\u002Fmembers\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fentropy-research\u002Fdevon?style=for-the-badge&color=orange\" alt=\"Forks\">\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fentropy-research\u002FDevon\u002Fstargazers\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fentropy-research\u002Fdevon?style=for-the-badge&color=yellow\" alt=\"Stargazers\">\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fentropy-research\u002FDevon\u002Fissues\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fissues\u002Fentropy-research\u002Fdevon?style=for-the-badge&color=red\" alt=\"Issues\">\u003C\u002Fa>\n  \u003Cbr\u002F>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fentropy-research\u002FDevon\u002Fblob\u002Fmain\u002FLICENSE\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flicense\u002Fentropy-research\u002Fdevon?style=for-the-badge&color=blue\" alt=\"Apache 2.0 License\">\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fdiscord.gg\u002Fp5YpZ5vjd9\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FDiscord-Join%20Us-purple?logo=discord&logoColor=white&style=for-the-badge\" alt=\"Join our Discord community\">\u003C\u002Fa>\n  \u003Cbr\u002F>\n\n\nhttps:\u002F\u002Fgithub.com\u002Fentropy-research\u002FDevon\u002Fassets\u002F61808204\u002Ff3197a56-3d6d-479f-bc0e-9cffe69f159b\n\u003C\u002Fdiv>\n\n### How do y'all ship so quickly?\n\u003Ca href=\"https:\u002F\u002Fdiscord.gg\u002Fp5YpZ5vjd9\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FDiscord-Join%20Us-purple?logo=discord&logoColor=white&style=for-the-badge\" alt=\"Join our Discord community\">\u003C\u002Fa> \n← We have a __**community-driven Dev Team**__ for this repo. Come join us! It's great.\n  \n# Installation\n\n## Prerequisites\n\n1. `node.js` and `npm`\n2. `pipx`, if you don't have this go [here](https:\u002F\u002Fpipx.pypa.io\u002Fstable\u002Finstallation\u002F)\n3. API Key \u003Csamp>(just one is required)\u003C\u002Fsamp>\n   - [**Anthropic**](https:\u002F\u002Fconsole.anthropic.com\u002Fsettings\u002Fkeys)\n    - [**OpenAI**](https:\u002F\u002Fplatform.openai.com\u002Fapi-keys)\n\n> We're currently working on supporting Windows! (Let us know if you can help)\n\n## Installation commands\n\nTo install using `pipx` + `npm`:\n\n```bash\n# Step 1: Ensure directory where pipx stores apps is in your PATH environment variable\npipx ensurepath\n\n# Step 2: For the backend\npipx install devon_agent\n\n# Step 3: For the main UI (install and run)\nnpx devon-ui\n```\n\n\n> If you already have devon_agent installed, update it by running:\n> ```pipx install --force devon_agent```\n\n### Thats it! Happy building :)\n\n\n# Running the agent\n\nThen to *run* the main ui, the command is:\n```bash\nnpx devon-ui\n```\n\nIt's that simple.\n\n# Terminal UI\n> If you'd like to use the terminal interface, follow these steps:\n### Install\n1. Make sure you have the backend installed\n```bash\n# For the backend\npipx install devon_agent\n```\n2. Install the tui\n```bash\n# For the tui\nnpm install -g devon-tui\n```\n> [!NOTE]\n> If you already have devon-tui installed, update it by running:\n```bash\nnpm uninstall -g devon-tui\nnpm install -g devon-tui\n```\n\n### Run\n\n1. Navigate to your project folder and open the terminal.\n2. Set your Anthropic API or OpenAI API key as an environment variable:\n\n```bash\nexport ANTHROPIC_API_KEY=sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx\n\n#OR\n\nexport OPENAI_API_KEY=sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx\n\n#OR\n\nexport GROQ_API_KEY=sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx\n```\n\n3. Then to *run* the terminal-ui, the command is:\n```bash\ndevon-tui\n```\n\nIt's as easy as that.\n\n> [!NOTE]\n> Don't worry, the agent will be able to only access files and folders in the directory you started it from. You can also correct it while it's performing actions.\n\n---\n\nTo run in *debug* mode, the command is:\n```bash\ndevon-tui --debug\n```\n\n---\n\nTo run in *local* mode:\n> [!WARNING]\n> The current version of local model support is not mature, proceed with caution, and expect the performance to degrade significantly compared to the other options.\n\n1. Get deepseek running with [ollama](https:\u002F\u002Follama.com\u002Flibrary\u002Fdeepseek-coder:6.7b)\n\n2. Start the local ollama server by running\n```\nollama run deepseek-coder:6.7b\n```\n\n4. Then configure devon to use the model\n```bash\ndevon-tui configure\n\nConfiguring Devon CLI...\n? Select the model name: \n  claude-opus \n  gpt4-o \n  llama-3-70b \n❯ ollama\u002Fdeepseek-coder:6.7b\n```\n\n4. And finally, run it with:\n```\ndevon-tui --api_key=FOSS\n```\n\n---\n\nFor a list of all commands available:\n```bash\ndevon-tui --help\n```\n\n# Features\n- Multi-file editing\n- Codebase exploration\n- Config writing\n- Test writing\n- Bug fixing\n- Architecture exploration\n- Local model support\n\n### Limitations\n- Minimal functionality for non-Python languages\n- Sometimes have to specify the file where you want the change to happen\n- Local mode is not good right now. Please try to avoid using it.\n\n# Progress\n\n### This project is still super early and \u003Cins>we would love your help\u003C\u002Fins> to make it great!\n\n### Current goals\n- Multi-model support\n  - [x] Claude 3.5 Sonnet\n  - [x] GPT4-o\n  - [x] Groq llama3-70b\n  - [x] Ollama deepseek-6.7b\n  - [ ] Google Gemini 1.5 Pro\n- Launch plugin system for tool and agent builders\n- Improve our self-hostable Electron app\n- Set SOTA on [SWE-bench Lite](https:\u002F\u002Fwww.swebench.com\u002Flite.html)\n\n> View our current thoughts on next steps [**here**](https:\u002F\u002Fdocs.google.com\u002Fdocument\u002Fd\u002Fe\u002F2PACX-1vTjLCQcWE_n-uUHFhtBkxTCIJ4FFe5ftY_E4_q69SjXhuEZv_CYpLaQDh3HqrJlAxsgikUx0sTzf9le\u002Fpub)\n\n### Star history\n\u003Cp align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fstar-history.com\u002F#entropy-research\u002FDevon&Date\">\n    \u003Cimg src=\"https:\u002F\u002Fapi.star-history.com\u002Fsvg?repos=entropy-research\u002FDevon&type=Date\" width=\"500\" alt=\"Star History Chart\">\n  \u003C\u002Fa>\n\u003C\u002Fp>\n\n### Past milestones\n\n- [x] **June 28, 2024** - File and code referencing, improve steerability, Claude Sonnet support v0.0.16\n- [x] **June 14, 2024** - Launch Electron UI v0.0.13\n- [x] **June 1, 2024** - Devon V2 Beta Electron UI\n- [x] **May 19, 2024** - GPT4o support + better interface support v0.1.7\n- [x] **May 12, 2024** - Complete interactive agent v0.1.0\n- [x] **May 10, 2024** - Add steerability features\n- [x] **May 8, 2024** - Beat AutoCodeRover on SWE-Bench Lite\n- [x] **Mid April, 2024** - Add repo level code search tooling\n- [x] **April 2, 2024** - Begin development of v0.1.0 interactive agent\n- [x] **March 17, 2024** - Launch non-interactive agent v0.0.1\n\n> [!NOTE]\n> If you already have the tui installed, run a clean reinstall:\n```bash\nnpm uninstall -g devon-tui\nnpm install -g devon-tui\n```\n\n## Current development priorities\n\n1. Improve context gathering and code indexing abilities ex:\n    - Adding memory modules\n    - Improved code indexing\n2. Add alternative models and agents to:\n    - a) Reduce end user cost and\n    - b) Reduce end user latency\n3. Electron app\n    - Save and load in project overviews for agent context\n    - Revert & \"step back\" timeline interface\n    - Better code diff view\n    - Send user file events\u002Fchanges to Devon\n\n\n\n# How can I contribute?\n\nDevon and the entropy-research org are community-driven, and we welcome contributions from everyone!\nFrom tackling issues to building features to creating datasets, there are many ways to get involved:\n\n- **Core functionality:** Help us develop the core agents, user experience, tool integrations, plugins, etc.\n- **Research:** Help us research agent performance (including benchmarks!), build data pipelines, and finetune models.\n- **Feedback and Testing:** Use Devon, report bugs, suggest features, or provide feedback on usability.\n\nFor details, please check [CONTRIBUTING.md](.\u002FCONTRIBUTING.md).\n\nIf you would like to contribute to the project, please join the discord: [Discord](https:\u002F\u002Fdiscord.gg\u002Fp5YpZ5vjd9)\n\n# Feedback\n\nWe would love feedback! Feel free to drop us a note on our [Discord](https:\u002F\u002Fdiscord.gg\u002Fp5YpZ5vjd9) in the #feedback channel, or [create issues](https:\u002F\u002Fgithub.com\u002Fentropy-research\u002FDevon\u002Fissues)!\n\nWe collect basic event type (i.e. \"tool call\") and failure telemetry to solve bugs and improve the user experience, but if you want to reach out, we would love to hear from you!\n\nTo disable telemetry, set the environment variable `DEVON_TELEMETRY_DISABLED` to `true` \n```bash\nexport DEVON_TELEMETRY_DISABLED=true\n```\n\n# Community\n\nJoin our Discord server and say hi!\n[Discord](https:\u002F\u002Fdiscord.gg\u002Fp5YpZ5vjd9)\n\n\n# License\n\nDistributed under the AGPL License. See [`LICENSE`](.\u002FLICENSE) for more information.\n","Devon 是一个开源的编程助手，旨在通过 AI 技术帮助开发者提高编码效率。它基于 Python 开发，集成了 GPT-4、Llama3 等先进的 AI 模型，能够提供代码生成、代码审查等核心功能。此外，Devon 支持多种开发工具如 VSCode，并且提供了图形界面和终端界面两种使用方式，以满足不同开发者的需求。该项目适合需要快速原型设计、代码重构或希望在日常开发中获得智能辅助的软件工程师使用。","2026-06-11 03:41:12","high_star"]