[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-93196":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":9,"totalLinesOfCode":9,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":9,"subscribersCount":16,"size":16,"stars1d":16,"stars7d":16,"stars30d":17,"stars90d":16,"forks30d":16,"starsTrendScore":16,"compositeScore":18,"rankGlobal":9,"rankLanguage":9,"license":9,"archived":19,"fork":19,"defaultBranch":20,"hasWiki":19,"hasPages":19,"topics":9,"createdAt":9,"pushedAt":9,"updatedAt":21,"readmeContent":22,"aiSummary":23,"trendingCount":16,"starSnapshotCount":16,"syncStatus":24,"lastSyncTime":25,"discoverSource":26},93196,"neuro-san-studio","cognizant-ai-lab\u002Fneuro-san-studio","cognizant-ai-lab","A playground for neuro-san",null,"https:\u002F\u002Fgithub.com\u002Fcognizant-ai-lab\u002Fneuro-san-studio","Python",783,229,17,81,0,8,48.89,false,"main","2026-07-22 04:02:08","# Neuro SAN Studio\n\n**Your launchpad for building intelligent multi-agent systems.** Neuro SAN Studio is a hands-on playground for the\n[Neuro SAN](https:\u002F\u002Fgithub.com\u002Fcognizant-ai-lab\u002Fneuro-san) framework, featuring ready-to-run examples, tutorials, and\ntools that let you design, test, and deploy sophisticated agent networks in minutes—not months. Whether you're a\nresearcher exploring adaptive AI systems, a developer prototyping production solutions, or a domain expert configuring\nagents without code, this studio handles the orchestration complexity so you can focus on solving real problems.\n\n---\n\n\u003C!-- pyml disable-next-line no-inline-html -->\n\u003Cp align=\"center\">\n  Neuro SAN is the open-source library powering the Cognizant Neuro® AI Multi-Agent Accelerator, allowing domain experts,\n  researchers and developers to immediately start prototyping and building agent networks across any industry vertical.\n\u003C\u002Fp>\n\n---\n\n\u003C!-- pyml disable-next-line no-inline-html -->\n\u003Cp align=\"center\">\n  \u003C!-- GitHub Stats -->\n  \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fcognizant-ai-lab\u002Fneuro-san-studio?style=social\" alt=\"GitHub stars\">\n  \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fcognizant-ai-lab\u002Fneuro-san-studio?style=social\" alt=\"GitHub forks\">\n  \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fwatchers\u002Fcognizant-ai-lab\u002Fneuro-san-studio?style=social\" alt=\"GitHub watchers\">\n\u003C\u002Fp>\n\u003Cp align=\"center\">\n  \u003C!-- GitHub Info -->\n  \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fcognizant-ai-lab\u002Fneuro-san-studio\" alt=\"Last Commit\">\n  \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fissues\u002Fcognizant-ai-lab\u002Fneuro-san-studio\" alt=\"Issues\">\n  \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fissues-pr\u002Fcognizant-ai-lab\u002Fneuro-san-studio\" alt=\"Pull Requests\">\n  \u003Ca href=\"https:\u002F\u002Fpepy.tech\u002Fprojects\u002Fneuro-san-studio\">\u003Cimg alt=\"PyPI Downloads\"\n  src=\"https:\u002F\u002Fstatic.pepy.tech\u002Fbadge\u002Fneuro-san-studio\" \u002F>\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fpypi.org\u002Fproject\u002Fneuro-san-studio\u002F\">\n  \u003Cimg alt=\"neuro-san-studio@PyPI\" src=\"https:\u002F\u002Fimg.shields.io\u002Fpypi\u002Fv\u002Fneuro-san-studio.svg?style=flat-square\">\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fdeepwiki.com\u002Fcognizant-ai-lab\u002Fneuro-san-studio\">\n  \u003Cimg src=\"https:\u002F\u002Fdeepwiki.com\u002Fbadge.svg\" alt=\"Ask DeepWiki: Neuro SAN Studio\" \u002F>\u003C\u002Fa>\n\n\u003C\u002Fp>\n\n\u003C!-- pyml disable-next-line no-inline-html -->\n\u003Cp align=\"center\">\n  \u003C!-- Neuro SAN Stats -->\n  Neuro SAN library \u003Cbr>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fcognizant-ai-lab\u002Fneuro-san\">\u003Cimg alt=\"GitHub Repo\"\n  src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FGitHub-Repo-green.svg\" \u002F>\u003C\u002Fa>\n  \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fcommit-activity\u002Fm\u002Fcognizant-ai-lab\u002Fneuro-san\" alt=\"commit activity\">\n  \u003Ca href=\"https:\u002F\u002Fpepy.tech\u002Fprojects\u002Fneuro-san\">\u003Cimg alt=\"PyPI Downloads\"\n  src=\"https:\u002F\u002Fstatic.pepy.tech\u002Fbadge\u002Fneuro-san\" \u002F>\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fpypi.org\u002Fproject\u002Fneuro-san\u002F\">\n  \u003Cimg alt=\"neuro-san@PyPI\" src=\"https:\u002F\u002Fimg.shields.io\u002Fpypi\u002Fv\u002Fneuro-san.svg?style=flat-square\">\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fdeepwiki.com\u002Fcognizant-ai-lab\u002Fneuro-san\">\n  \u003Cimg src=\"https:\u002F\u002Fdeepwiki.com\u002Fbadge.svg\" alt=\"Ask DeepWiki: Neuro SAN\" \u002F>\u003C\u002Fa>\n\u003C\u002Fp>\n\n## What is Neuro SAN?\n\n[**Neuro AI system of agent networks (Neuro SAN)**](https:\u002F\u002Fgithub.com\u002Fcognizant-ai-lab\u002Fneuro-san) is an open-source,\ndata-driven multi-agent orchestration framework designed to simplify and accelerate the development of collaborative AI\nsystems. It allows users—from machine learning engineers to business domain experts—to quickly build sophisticated\nmulti-agent applications without extensive coding, using declarative configuration files (in HOCON format).\n\nNeuro SAN enables multiple large language model (LLM)-powered agents to collaboratively solve complex tasks, dynamically\ndelegating subtasks through adaptive inter-agent communication protocols. This approach addresses the limitations inherent\nto single-agent systems, where no single model has all the expertise or context necessary for multifaceted problems.\n\n\u003C!-- pyml disable line-length -->\n| Build a multi-agent network in minutes                                              | Neuro SAN overview                                                                     | Quick start                                                              |\n|-------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------|--------------------------------------------------------------------------|\n| [![Build](.\u002Fdocs\u002Fimages\u002Fdesigner.png)](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=wGxvPBN34Mk) | [![Overview](.\u002Fdocs\u002Fimages\u002Foverview.png)](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=NmniQWQT6vI) | [![Start](.\u002Fdocs\u002Fimages\u002Fnsflow_thumb.png)](https:\u002F\u002Fyoutu.be\u002Fgfem8ylphWA) |\n\n\u003C!-- pyml enable line-length -->\n---\n\n### ✨ Key Features\n\n* **🗂️ Data-Driven Configuration**: Entire agent networks are defined declaratively via simple HOCON files, empowering\ntechnical and non-technical stakeholders to design agent interactions intuitively.\n* **🔀 Adaptive Communication ([AAOSA Protocol](https:\u002F\u002Farxiv.org\u002Fabs\u002Fcs\u002F9812015))**: Agents autonomously determine how\nto delegate tasks, making interactions fluid and dynamic with decentralized decision-making.\n* **🔒 Sly-Data**: Sly Data facilitates safe handling and transfer of sensitive data between agents without exposing it\ndirectly to any language models.\n* **🧩 Dynamic Agent Network Designer**: Includes a meta-agent called the Agent Network Designer – essentially, an agent\nthat creates other agent networks. Provided as an example with Neuro SAN, it can take a high-level description of a\nuse-case as input and generate a new custom agent network for it.\n* **🛠️ Flexible Tool Integration**: Integrate custom Python-based \"coded tools,\" APIs, databases, and even external\nagent ecosystems (Agentforce, Agentspace, CrewAI, MCP, A2A agents, LangChain tools and more) seamlessly into your agent workflows.\n* **📈 Robust Traceability**: Detailed logging, tracing, and session-level metrics enhance transparency, debugging, and\noperational monitoring.\n* **🌐 Extensible and Cloud-Agnostic**: Compatible with a wide variety of LLM providers (OpenAI, Anthropic, Azure, Ollama,\netc.) and deployable in diverse environments (local machines, containers, or cloud infrastructures).\n\n---\n\n### Use Cases\n\nHere are a few examples of use-cases that have been implemented with Neuro SAN.\nFor more examples, check out [docs\u002Fexamples.md](docs\u002Fexamples.md).\n\u003C!-- pyml disable no-inline-html -->\n\u003Ctable>\n  \u003Cthead>\n    \u003Ctr>\n      \u003Cth>Agent Network\u003C\u002Fth>\n      \u003Cth>Use-Case\u003C\u002Fth>\n      \u003Cth>Description\u003C\u002Fth>\n    \u003C\u002Ftr>\n  \u003C\u002Fthead>\n  \u003Ctbody>\n    \u003Ctr>\n      \u003Ctd>🧬 \u003Cstrong>Agent Network Designer\u003C\u002Fstrong>\u003C\u002Ftd>\n      \u003Ctd>Automated generation of multi-agent HOCON configurations.\u003C\u002Ftd>\n      \u003Ctd>Generates complex multi-agent configurations from natural language input, simplifying the creation of intricate\n      agent workflows.\u003C\u002Ftd>\n    \u003C\u002Ftr>\n    \u003Ctr>\n      \u003Ctd>🛫 \u003Cstrong>Airline Policy Assistance\u003C\u002Fstrong>\u003C\u002Ftd>\n      \u003Ctd>Customer support for airline policies.\u003C\u002Ftd>\n      \u003Ctd>Agents interpret and explain airline policies, assisting customers with inquiries about baggage allowances, cancellations,\n      and travel-related concerns.\u003C\u002Ftd>\n    \u003C\u002Ftr>\n    \u003Ctr>\n      \u003Ctd>🏦 \u003Cstrong>Banking Operations & Compliance\u003C\u002Fstrong>\u003C\u002Ftd>\n      \u003Ctd>Automated financial operations and regulatory compliance.\u003C\u002Ftd>\n      \u003Ctd>Automates tasks such as transaction monitoring, fraud detection, and compliance reporting, ensuring adherence to\n      regulations and efficient routine operations.\u003C\u002Ftd>\n    \u003C\u002Ftr>\n    \u003Ctr>\n      \u003Ctd>🛍️ \u003Cstrong>Consumer Packaged Goods (CPG)\u003C\u002Fstrong>\u003C\u002Ftd>\n      \u003Ctd>Market analysis and product development in CPG.\u003C\u002Ftd>\n      \u003Ctd>Gathers and analyzes market trends, customer feedback, and sales data to support product development and strategic\n      marketing.\u003C\u002Ftd>\n    \u003C\u002Ftr>\n    \u003Ctr>\n      \u003Ctd>🛡️ \u003Cstrong>Insurance Agents\u003C\u002Fstrong>\u003C\u002Ftd>\n      \u003Ctd>Claims processing and risk assessment.\u003C\u002Ftd>\n      \u003Ctd>Automates claims evaluation, assesses risk factors, ensures policy compliance, and improves claim-handling efficiency\n      and customer satisfaction.\u003C\u002Ftd>\n    \u003C\u002Ftr>\n    \u003Ctr>\n      \u003Ctd>🏢 \u003Cstrong>Intranet Agents\u003C\u002Fstrong>\u003C\u002Ftd>\n      \u003Ctd>Internal knowledge management and employee support.\u003C\u002Ftd>\n      \u003Ctd>Provides employees with quick access to policies, HR, and IT support, enhancing internal communications and resource\n      accessibility.\u003C\u002Ftd>\n    \u003C\u002Ftr>\n    \u003Ctr>\n      \u003Ctd>🛒 \u003Cstrong>Retail Operations & Customer Service\u003C\u002Fstrong>\u003C\u002Ftd>\n      \u003Ctd>Enhancing retail customer experience and operational efficiency.\u003C\u002Ftd>\n      \u003Ctd>Handles customer inquiries, inventory management, and supports sales processes to optimize operations and service\n      quality.\u003C\u002Ftd>\n    \u003C\u002Ftr>\n    \u003Ctr>\n      \u003Ctd>📞 \u003Cstrong>Telco Network Support\u003C\u002Fstrong>\u003C\u002Ftd>\n      \u003Ctd>Technical support and network issue resolution.\u003C\u002Ftd>\n      \u003Ctd>Diagnoses network problems, guides troubleshooting, and escalates complex issues, reducing downtime and enhancing\n      customer service.\u003C\u002Ftd>\n    \u003C\u002Ftr>\n    \u003Ctr>\n      \u003Ctd>📞 \u003Cstrong>Therapy Vignette Supervision\u003C\u002Fstrong>\u003C\u002Ftd>\n      \u003Ctd>Generates treatment plan for a given therapy vignette.\u003C\u002Ftd>\n      \u003Ctd>A good example of using multiple different expert agents working together to come up with a single plan.\u003C\u002Ftd>\n    \u003C\u002Ftr>\n  \u003C\u002Ftbody>\n\u003C\u002Ftable>\n\u003C!-- pyml enable no-inline-html -->\n\nAnd many more: check out [docs\u002Fexamples.md](docs\u002Fexamples.md).\n\n---\n\n## High level Architecture\n\n\u003C!-- pyml disable no-inline-html -->\n\u003Cp align=\"left\">\n  \u003Cimg src=\".\u002Fdocs\u002Fimages\u002Fneuroai_arch_diagram.png\" alt=\"neuro-san architecture\" width=\"800\"\u002F>\n\u003C\u002Fp>\n\u003C!-- pyml enable no-inline-html -->\n\n---\n\n## Install\n\nThese instructions are for Linux and macOS systems. Please adjust the commands accordingly for Windows.\n\n### Install `uv`\n\n[`uv`](https:\u002F\u002Fdocs.astral.sh\u002Fuv\u002F) is a fast Python package and project manager built by Astral.\n\nOfficial installation docs:  \n👉 [https:\u002F\u002Fdocs.astral.sh\u002Fuv\u002Fgetting-started\u002Finstallation\u002F](https:\u002F\u002Fdocs.astral.sh\u002Fuv\u002Fgetting-started\u002Finstallation\u002F)\n\n### Create a new Python project\n\nCreate a folder for your project:\n\n```bash\nmkdir my_project\ncd my_project\n```\n\nCreate a virtual environment, initialize a git repo and install `neuro-san-studio`\n\n```bash\nuv init\nuv venv\nsource .venv\u002Fbin\u002Factivate\nuv add neuro-san-studio\n```\n\n### Initialize neuro-san-studio\n\nRun `ns init` to initialize a Neuro SAN Studio project. `ns` stands for Neuro SAN. You can also use the long command\n`neuro-san-studio` instead. It will:\n* let you choose an LLM provider\n* create a `config` folder with your choice of LLM models and plugins configuration\n* create an `mcp` folder with a list of MCP tools\n* create a `registries` folder with a simple agent network\n\nTo learn more about the `ns` command run `ns --help`.\n\n```bash\nns init\n```\n\n```bash\nWhich LLM providers do you want to enable?\n\n#  Provider       Default model\n1  OpenAI         gpt-5.2 (default)\n2  Anthropic      claude-sonnet\n3  Google Gemini  gemini-3-flash\n\nEnter numbers separated by commas (default: 1):\n```\n\n### Set your LLM API key(s)\n\n1. Set your provider key, e.g. `OPENAI_API_KEY`, `ANTHROPIC_API_KEY` or `GOOGLE_API_KEY`\n(or create a `.env` file in the current directory).\nSee [docs\u002Fapi_key.md](docs\u002Fapi_key.md) for details and other providers.\n\n   ```bash\n   export OPENAI_API_KEY=\"XXX\"\n   ```\n\n2. Check your LLM API keys are correctly configured:\n\n    ```bash\n    ns check-llm-keys\n    ```\n\n3. Check your `config\u002Fllm_config.hocon` is working:\n\n    ```bash\n    ns check-config\n    ```\n\n    If the configuration is valid you will get a `hello` response from the configured LLMs.\n\n### Import agent networks\n\nYou can import the agent networks that ship with `neuro-san-studio` using the `ns import` command.\nIt will run an interactive prompt. You can for instance import the `root` agent networks to use the\nAgent Network Designer to create your own agent network.\n\nSee [`docs\u002Fcli\u002Fimport.md`](docs\u002Fcli\u002Fimport.md) for details.\n\n```bash\nns import\n```\n\nShows the following prompt:\n\n```bash\n[info]  Discovering available agent networks...\n\n? What do you want to import? (Use arrow keys)\n   Basic (17)\n   Experimental (9)\n   Industry (22)\n » Root (6)\n   Tools (28)\n   ---------------\n   Custom selection\n   All (82)\n```\n\nChoose `root` and press Enter. Confirm with `Y` to import the agent networks that are listed.\n\nFrom `Experimental`, also import:\n\n```bash\n   ● cruse_theme_agent\n » ● cruse_widget_agent\n````\n\nto enable CRUSE, the interactive UI that adapts the UI to the user\u002Fagents' needs.\n\n### Start the developer UI\n\nYou can start a `neuro-san` server and the `nsflow` UI with the `ns run` command:\n\n```bash\nns run\n```\n\nThe Neuro SAN server listens on `localhost:8080`.\n\nThe nsflow UI is served at\n[http:\u002F\u002Flocalhost:4173\u002F](http:\u002F\u002Flocalhost:4173\u002F).\n\nLogs land under `logs\u002F` (`server.log`, `nsflow.log`, `thinking_dir\u002F`).\n\nScreenshot:\n\n![NSFlow UI Snapshot](https:\u002F\u002Fraw.githubusercontent.com\u002Fcognizant-ai-lab\u002Fnsflow\u002Fmain\u002Fdocs\u002Fsnapshot01.png)\n\n### Agent Network Designer\n\nUse the Agent Network Designer to create your own agent network.\n\n1. From the `nsflow` UI, click the `NEW` button at the top, center of the screen.\n![AND Button](docs\u002Fimages\u002Fagent_network_designer_new_button.png)\n2. In the new window that opens, type your prompts in the text box in the bottom right\ncorner of the screen. Then Agent Network Designer:\n   * Creates the agents\n   * Links them together\n   * Writes instructions for each agent\n   * Generates a few sample queries you can ask this agent network\n   * Saves the agent network in the `registries\u002Fgenerated` folder\n3. Once the Agent Network Designer is done and comes back with an answer in the chat window,\nyou can continue the design by asking it to make changes\n4. Once you're happy with the design, test it! Click the blue `Launch` button at the top\ncenter of the screen. It opens a new window from which you can chat with the agent network.\n5. If you want to make modifications, go back to the editor window and ask for changes.\n6. You can also edit any agent network by clicking the pen icon next to its name in the main window.\n\n### Import a project from a file \u002F Export to a file\n\nYou can import a project from a .hocon file or from a zip file using the `ns import \u003CPATH>`.\n\n```bash\nns import ~\u002FDownloads\u002Fmy_project.hocon\n```\n\nSimilarly, you can export an agent network and all its dependencies using the `ns export` command:\n\n```bash\nns export my_project.hocon\n```\n\nSee [`docs\u002Fcli\u002Fexport.md`](docs\u002Fcli\u002Fexport.md) for details.\n\n### Command reference\n\n\u003C!-- pyml disable line-length -->\n\n| Command             | Purpose                                                          | Key flags                                                                                                                                                                       |\n|---------------------|------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| `ns init`           | Scaffold a starter project in the current dir.                   | `--providers openai,anthropic,google`                                                                                                                                           |\n| `ns run`            | Start the Neuro SAN server and nsflow UI.                        | `--server-host`, `--server-http-port`, `--nsflow-port`, `--log-level`, `--client-only`, `--server-only`                                                                         |\n| `ns chat`           | Chat with an agent network directly (no server needed).          | Positional: agent name, `--connection`,  `--host`, `--port`, `--one-shot`, `--list`.                                                                                            |\n| `ns import`         | Import agent networks into the current project.                  | Positional: space-separated group names, network names, or `all`; or local `.hocon` \u002F `.zip` paths (don't mix the two). `--force` to overwrite. Omit args for interactive mode. |\n| `ns export`         | Bundle a network from the current project into a shareable file. | Positional: network name (e.g. `music_nerd` or `basic\u002Fmusic_nerd`). `-o` \u002F `--output` to set the output path. Omit args for interactive picker.                                 |\n| `ns check-llm-keys` | Validate LLM API keys \u002F env vars.                                | `--tier 1` (placeholder), `--tier 2` (format), `--tier 3` (live API call, default)                                                                                              |\n| `ns check-config`   | Validate the LLM configurations in a HOCON file.                 | `--hocon-path` (defaults to `config\u002Fllm_config.hocon`)                                                                                                                          |\n\n\u003C!-- pyml enable line-length -->\n\nUse `ns \u003Ccommand> --help` for the full flag list of any subcommand.\n\n---\n\n## User guide\n\nReady to dive in? Check out the [user guide](docs\u002Fuser_guide.md) for a detailed overview of the neuro-san library\nand its features.\n\n---\n\n## Tutorial\n\nFor a detailed tutorial, refer to [docs\u002Ftutorial.md](docs\u002Ftutorial.md).\n\n---\n\n## Examples\n\nFor examples of agent networks, check out [docs\u002Fexamples.md](docs\u002Fexamples.md).\n\n---\n\n## Developer Guide\n\nFor the development guide, check out [docs\u002Fdev_guide.md](docs\u002Fdev_guide.md).\n\n---\n\n## Community Projects\n\n### Applications\n\n* [Climate Change](https:\u002F\u002Fgithub.com\u002Fcognizant-ai-lab\u002Fneuro-san-cc):\na tool to answer questions about COP, the Paris Agreement or the Kyoto Protocol using UNFCCC documents.\n* [Enterprise Access Portal](https:\u002F\u002Fgithub.com\u002FM-Elsaied\u002Fenterprise-access-portal):\nan AI-powered multi-agent system for managing enterprise application access requests and IT operations.\n* [F1 fans eval](https:\u002F\u002Fgithub.com\u002Fdeepsaia\u002Ff1-fan-eval):\nan app that evaluates F1 fan submissions about why they are the biggest F1 fans.\n* [PDF Knowledge Assistant](https:\u002F\u002Fgithub.com\u002FM-Elsaied\u002Fneuro-san-studio\u002Ftree\u002Fpdf-knowledge-base\u002Fapps\u002Fpdf_knowledge_assistant):\na Flask web app that queries PDFs using RAG with topic-based long-term memory synthesis across documents.\n* [Loopy Agents](https:\u002F\u002Fgithub.com\u002Fbabakatwork\u002Floopy_agent):\nrun Neuro SAN agents continuously or on triggers through a separate service, with asynchronous messaging.\n* [Annual Report Reader](https:\u002F\u002Fgithub.com\u002Fshrushtiimehta\u002Fneuro-san-annual-report-reader):\nanalyzes a LinkedIn profile and delivers a personalized summary of Cognizant's 2024 Annual Report,\nsurfacing content most relevant to the user's industry and seniority level.\n* [Tochiro File Organizer](https:\u002F\u002Fgithub.com\u002Fofrancon\u002Ftochiro):\na macOS file organization assistant with a dedicated UI to analyze a folder,\ncreate a plan for moving the files, ask for approval and execute the moves.\n\n### Utilities\n\n* [Neuro SAN Web Client](https:\u002F\u002Fgithub.com\u002Fcognizant-ai-lab\u002Fneuro-san-web-client):\na basic Flask web client interface for Neuro SAN.\n* [Neuro SAN Slack app](.\u002Fapps\u002Fslack\u002FREADME.md)\na Slack integration that lets you interact with Neuro SAN directly from your workspace.\n\n---\n\n## Links\n\n* Website: [Cognizant AI Lab](https:\u002F\u002Fwww.cognizant.com\u002Fus\u002Fen\u002Fai-lab)\n* YouTube: [Decision AI](https:\u002F\u002Fwww.youtube.com\u002F@decision-ai)\n* X: [@cognizantailab](https:\u002F\u002Fx.com\u002Fcognizantailab)\n* LinkedIn: [Cognizant AI Lab](https:\u002F\u002Fwww.linkedin.com\u002Fshowcase\u002Fcognizant-ai-lab)\n\n---\n\n## More details\n\nFor more information, check out the [Cognizant AI Lab Neuro SAN landing page](https:\u002F\u002Fwww.cognizant.com\u002Fus\u002Fen\u002Fai-lab\u002Fneuro-san).\n","Neuro SAN Studio 是一个面向多智能体系统的快速原型开发与实验平台，基于 Neuro SAN 框架构建，提供开箱即用的示例、交互式教程和可视化编排工具，支持低代码\u002F无代码方式设计、调试与部署智能代理网络。其核心特点包括轻量级运行时、模块化代理组件、任务驱动的协同机制及跨行业可配置性。适用于金融风控、企业流程自动化、智能客服编排、科研验证等需快速验证多智能体协作逻辑的场景。",2,"2026-07-12 02:30:09","trending"]