Skip to content
Back to search

neuro-san-studio

A playground for neuro-san

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

It has changed since its scan on 11 Nov 2026.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/cognizant-ai-lab/neuro-san-studio with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/cognizant-ai-lab/neuro-san-studio'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/cognizant-ai-lab--neuro-san-studio/badge.svg)](/listings/cognizant-ai-lab--neuro-san-studio)

HTML

<a href="/listings/cognizant-ai-lab--neuro-san-studio"><img src="/api/listings/cognizant-ai-lab--neuro-san-studio/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

These instructions are for Linux and macOS systems. Please adjust the commands accordingly for Windows.

Install `uv`

[`uv`](https://docs.astral.sh/uv/) is a fast Python package and project manager built by Astral.

Official installation docs: 👉 [https://docs.astral.sh/uv/getting-started/installation/](https://docs.astral.sh/uv/getting-started/installation/)

Create a new Python project

Create a folder for your project:

mkdir my_project
cd my_project

Create a virtual environment, initialize a git repo and install `neuro-san-studio`

uv init
uv venv
source .venv/bin/activate
uv add neuro-san-studio

Initialize neuro-san-studio

Run `ns init` to initialize a Neuro SAN Studio project. `ns` stands for Neuro SAN. You can also use the long command `neuro-san-studio` instead. It will: * let you choose an LLM provider * create a `config` folder with your choice of LLM models and plugins configuration * create an `mcp` folder with a list of MCP tools * create a `registries` folder with a simple agent network and the [Agent Network Designer](#agent-network-designer), so you can start designing your own networks right away * create `coded_tools` and `middleware` folders with the Python code those agent networks need

To learn more about the `ns` command run `ns --help`.

ns init
Which LLM providers do you want to enable?

#  Provider       Default model
1  OpenAI         gpt-5.2 (default)
2  Anthropic      claude-sonnet
3  Google Gemini  gemini-3-flash

Enter numbers separated by commas (default: 1):

**Note:** To access all Neuro SAN Studio capabilities, clone this repository and follow the setup instructions in the [docs/dev_guide.md](docs/dev_guide.md).

Set your LLM API key(s)

1. Set your provider key, e.g. `OPENAI_API_KEY`, `ANTHROPIC_API_KEY` or `GOOGLE_API_KEY` (or create a `.env` file in the current directory). See [docs/api_key.md](docs/api_key.md) for details and other providers.

   export OPENAI_API_KEY="XXX"

2. Check your LLM API keys are correctly configured:

```bash ns check-llm-keys ```

3. Check your `config/llm_config.hocon` is working:

```bash ns check-config ```

If the configuration is valid you will get a `hello` response from the configured LLMs.

Import agent networks

`ns init` already installs the Agent Network Designer, so you can start building right away. Use `ns import` to add any of the other agent network examples that ship with `neuro-san-studio`.

Run it with no arguments to pick from an interactive list:

ns import

Or name a group or a single network directly:

ns import basic         # every network in the "basic" group
ns import hello_world   # a single network

Each imported network brings its dependencies with it -- coded tools, middleware, sub-networks -- and is registered in `registries/manifest.hocon`. A running server picks it up within a few seconds.

See [`docs/cli/import.md`](docs/cli/import.md) for the full set of options.

Start the developer UI

You can start a `neuro-san` server and the `nsflow` UI with the `ns run` command:

ns run

The Neuro SAN server listens on `localhost:8080`.

The nsflow UI is served at [http://localhost:4173/](http://localhost:4173/).

Logs land under `logs/` (`server.log`, `nsflow.log`, `thinking_dir/`).

Screenshot:

Agent Network Designer

Use the Agent Network Designer to create your own agent network.

1. From the `nsflow` UI, click the `NEW` button at the top, center of the screen. 2. In the new window that opens, type your prompts in the text box in the bottom right corner of the screen. Then Agent Network Designer: * Creates the agents * Links them together * Writes instructions for each agent * Generates a few sample queries you can ask this agent network * Saves the agent network in the `registries/generated` folder

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 454 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. <!-- pyml disable-next-line first-line-heading -->
  2. <!-- Badges -->
  3. <!-- pyml disable-next-line no-inline-html -->
  4. <p align="center">
  5. <!-- GitHub Stats -->
  6. <img src="https://img.shields.io/github/stars/cognizant-ai-lab/neuro-san-studio?style=social" alt="GitHub stars">
  7. <img src="https://img.shields.io/github/forks/cognizant-ai-lab/neuro-san-studio?style=social" alt="GitHub forks">
  8. <img src="https://img.shields.io/github/watchers/cognizant-ai-lab/neuro-san-studio?style=social" alt="GitHub watchers">
  9. </p>
  10. <p align="center">
  11. <!-- GitHub Info -->
  12. <img src="https://img.shields.io/github/last-commit/cognizant-ai-lab/neuro-san-studio" alt="Last Commit">
  13. <img src="https://img.shields.io/github/issues/cognizant-ai-lab/neuro-san-studio" alt="Issues">
  14. <img src="https://img.shields.io/github/issues-pr/cognizant-ai-lab/neuro-san-studio" alt="Pull Requests">
  15. <a href="https://github.com/cognizant-ai-lab/neuro-san-studio/blob/main/LICENSE.txt"><img alt="License"
  16. src="https://img.shields.io/github/license/cognizant-ai-lab/neuro-san-studio"></a>
  17. <a href="https://pepy.tech/projects/neuro-san-studio"><img alt="PyPI Downloads"
  18. src="https://static.pepy.tech/badge/neuro-san-studio" /></a>
  19. <a href="https://pypi.org/project/neuro-san-studio/">
  20. <img alt="neuro-san-studio@PyPI" src="https://img.shields.io/pypi/v/neuro-san-studio.svg?style=flat-square"></a>
  21. <a href="https://deepwiki.com/cognizant-ai-lab/neuro-san-studio">
  22. <img src="https://img.shields.io/badge/Ask-DeepWiki-blue" alt="Ask DeepWiki: Neuro SAN Studio" /></a>
  23. </p>
  24. <!-- pyml disable-next-line no-inline-html -->
  25. <p align="center">
  26. <!-- Neuro SAN Stats -->
  27. Neuro SAN library <br>
  28. <a href="https://github.com/cognizant-ai-lab/neuro-san"><img alt="GitHub Repo"
  29. src="https://img.shields.io/badge/GitHub-Repo-green.svg" /></a>
  30. <img src="https://img.shields.io/github/commit-activity/m/cognizant-ai-lab/neuro-san" alt="commit activity">
  31. <a href="https://github.com/cognizant-ai-lab/neuro-san/blob/main/LICENSE.txt"><img alt="License"
  32. src="https://img.shields.io/github/license/cognizant-ai-lab/neuro-san"></a>
  33. <a href="https://pepy.tech/projects/neuro-san"><img alt="PyPI Downloads"
  34. src="https://static.pepy.tech/badge/neuro-san" /></a>
  35. <a href="https://pypi.org/project/neuro-san/">
  36. <img alt="neuro-san@PyPI" src="https://img.shields.io/pypi/v/neuro-san.svg?style=flat-square"></a>
  37. <a href="https://deepwiki.com/cognizant-ai-lab/neuro-san">
  38. <img src="https://img.shields.io/badge/Ask-DeepWiki-blue" alt="Ask DeepWiki: Neuro SAN" /></a>
  39. </p>
  40. # Neuro SAN Studio
  41. **Your launchpad for building intelligent multi-agent systems.** Neuro SAN Studio is a hands-on playground for the
  42. [Neuro SAN](https://github.com/cognizant-ai-lab/neuro-san) framework, featuring ready-to-run examples, tutorials, and
  43. tools that let you design, test, and deploy sophisticated agent networks in minutes—not months. Whether you're a
  44. researcher exploring adaptive AI systems, a developer prototyping production solutions, or a domain expert configuring
  45. agents without code, this studio handles the orchestration complexity so you can focus on solving real problems.
  46. <!-- pyml disable-next-line no-inline-html -->
  47. <h3 align="center">
  48. 🚀 Try Neuro SAN now, no install required:
  49. <a href="https://neuro-san.evolution.ml/">https://neuro-san.evolution.ml/</a>
  50. </h3>
  51. <!-- pyml disable-next-line no-inline-html -->
  52. <p align="center">
  53. <a href="https://neuro-san.evolution.ml/"><img alt="Launch Neuro SAN"
  54. src="https://img.shields.io/badge/Launch_Neuro_SAN-2ea44f?style=for-the-badge" /></a>
  55. </p>
  56. <!-- pyml disable-next-line no-inline-html -->
  57. <p align="center">
  58. This is a Bring Your Own Key (BYOK) instance, so you will need an API key from OpenAI, Anthropic or Gemini.
  59. </p>
  60. ---
  61. <!-- pyml disable-next-line no-inline-html -->
  62. <p align="center">
  63. Neuro SAN is the open-source library powering the Cognizant Neuro® AI Multi-Agent Accelerator, allowing domain experts,
  64. researchers and developers to immediately start prototyping and building agent networks across any industry vertical.
  65. </p>
  66. ## What is Neuro SAN?
  67. [**Neuro AI system of agent networks (Neuro SAN)**](https://github.com/cognizant-ai-lab/neuro-san) is an open-source,
  68. data-driven multi-agent orchestration framework designed to simplify and accelerate the development of collaborative AI
  69. systems. It allows users—from machine learning engineers to business domain experts—to quickly build sophisticated
  70. multi-agent applications without extensive coding, using declarative configuration files (in HOCON format).
  71. Neuro SAN enables multiple large language model (LLM)-powered agents to collaboratively solve complex tasks, dynamically
  72. delegating subtasks through adaptive inter-agent communication protocols. This approach addresses the limitations inherent
  73. to single-agent systems, where no single model has all the expertise or context necessary for multifaceted problems.
  74. <!-- pyml disable line-length -->
  75. | Build a multi-agent network in minutes | Neuro SAN overview | Quick start |
  76. |-------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------|--------------------------------------------------------------------------|
  77. | [![Build](./docs/images/designer.png)](https://www.youtube.com/watch?v=wGxvPBN34Mk) | [![Overview](./docs/images/overview.png)](https://www.youtube.com/watch?v=NmniQWQT6vI) | [![Start](./docs/images/nsflow_thumb.png)](https://youtu.be/gfem8ylphWA) |
  78. <!-- pyml enable line-length -->
  79. ---
  80. ### ✨ Key Features
  81. * **🗂️ Data-Driven Configuration**: Entire agent networks are defined declaratively via simple HOCON files, empowering
  82. technical and non-technical stakeholders to design agent interactions intuitively.
  83. * **🔀 Adaptive Communication ([AAOSA Protocol](https://arxiv.org/abs/cs/9812015))**: Agents autonomously determine how
  84. to delegate tasks, making interactions fluid and dynamic with decentralized decision-making.
  85. * **🔒 Sly-Data**: Sly Data facilitates safe handling and transfer of sensitive data between agents without exposing it
  86. directly to any language models.
  87. * **🧩 Dynamic Agent Network Designer**: Includes a meta-agent called the Agent Network Designer – essentially, an agent
  88. that creates other agent networks. Provided as an example with Neuro SAN, it can take a high-level description of a
  89. use-case as input and generate a new custom agent network for it.
  90. * **🛠️ Flexible Tool Integration**: Integrate custom Python-based "coded tools," APIs, databases, and even external
  91. agent ecosystems (Agentforce, Agentspace, CrewAI, MCP, A2A agents, LangChain tools and more) seamlessly into your agent workflows.
  92. * **📈 Robust Traceability**: Detailed logging, tracing, and session-level metrics enhance transparency, debugging, and
  93. operational monitoring.
  94. * **🌐 Extensible and Cloud-Agnostic**: Compatible with a wide variety of LLM providers (OpenAI, Anthropic, Azure, Ollama,
  95. etc.) and deployable in diverse environments (local machines, containers, or cloud infrastructures).
  96. ---
  97. ### Use Cases
  98. Here are a few examples of use-cases that have been implemented with Neuro SAN.
  99. For more examples, check out [docs/examples.md](docs/examples.md).
  100. <!-- pyml disable no-inline-html -->
  101. <table>
  102. <thead>
  103. <tr>
  104. <th>Agent Network</th>
  105. <th>Use-Case</th>
  106. <th>Description</th>
  107. </tr>
  108. </thead>
  109. <tbody>
  110. <tr>
  111. <td>🧬 <strong>Agent Network Designer</strong></td>
  112. <td>Automated generation of multi-agent HOCON configurations.</td>
  113. <td>Generates complex multi-agent configurations from natural language input, simplifying the creation of intricate
  114. agent workflows.</td>
  115. </tr>
  116. <tr>
  117. <td>🛫 <strong>Airline Policy Assistance</strong></td>
  118. <td>Customer support for airline policies.</td>
  119. <td>Agents interpret and explain airline policies, assisting customers with inquiries about baggage allowances, cancellations,
  120. and travel-related concerns.</td>
  121. </tr>
  122. <tr>
  123. <td>🏦 <strong>Banking Operations & Compliance</strong></td>
  124. <td>Automated financial operations and regulatory compliance.</td>
  125. <td>Automates tasks such as transaction monitoring, fraud detection, and compliance reporting, ensuring adherence to
  126. regulations and efficient routine operations.</td>
  127. </tr>
  128. <tr>
  129. <td>🛍️ <strong>Consumer Packaged Goods (CPG)</strong></td>
  130. <td>Market analysis and product development in CPG.</td>
  131. <td>Gathers and analyzes market trends, customer feedback, and sales data to support product development and strategic
  132. marketing.</td>
  133. </tr>
  134. <tr>
  135. <td>🛡️ <strong>Insurance Agents</strong></td>
  136. <td>Claims processing and risk assessment.</td>
  137. <td>Automates claims evaluation, assesses risk factors, ensures policy compliance, and improves claim-handling efficiency
  138. and customer satisfaction.</td>
  139. </tr>
  140. <tr>
  141. <td>🏢 <strong>Intranet Agents</strong></td>
  142. <td>Internal knowledge management and employee support.</td>
  143. <td>Provides employees with quick access to policies, HR, and IT support, enhancing internal communications and resource
  144. accessibility.</td>
  145. </tr>
  146. <tr>
  147. <td>🛒 <strong>Retail Operations & Customer Service</strong></td>
  148. <td>Enhancing retail customer experience and operational efficiency.</td>
  149. <td>Handles customer inquiries, inventory management, and supports sales processes to optimize operations and service
  150. quality.</td>
  151. </tr>
  152. <tr>
  153. <td>📞 <strong>Telco Network Support</strong></td>
  154. <td>Technical support and network issue resolution.</td>
  155. <td>Diagnoses network problems, guides troubleshooting, and escalates complex issues, reducing downtime and enhancing
  156. customer service.</td>
  157. </tr>
  158. <tr>
  159. <td>📞 <strong>Therapy Vignette Supervision</strong></td>
  160. <td>Generates treatment plan for a given therapy vignette.</td>
  161. <td>A good example of using multiple different expert agents working together to come up with a single plan.</td>
  162. </tr>
  163. </tbody>
  164. </table>
  165. <!-- pyml enable no-inline-html -->
  166. And many more: check out [docs/examples.md](docs/examples.md).
  167. ---
  168. ## High level Architecture
  169. <!-- pyml disable no-inline-html -->
  170. <p align="left">
  171. <img src="./docs/images/neuroai_arch_diagram.png" alt="neuro-san architecture" width="800"/>
  172. </p>
  173. <!-- pyml enable no-inline-html -->
  174. ---
  175. ## Install
  176. These instructions are for Linux and macOS systems. Please adjust the commands accordingly for Windows.
  177. ### Install `uv`
  178. [`uv`](https://docs.astral.sh/uv/) is a fast Python package and project manager built by Astral.
  179. Official installation docs:
  180. 👉 [https://docs.astral.sh/uv/getting-started/installation/](https://docs.astral.sh/uv/getting-started/installation/)
  181. ### Create a new Python project
  182. Create a folder for your project:
  183. ```bash
  184. mkdir my_project
  185. cd my_project
  186. ```
  187. Create a virtual environment, initialize a git repo and install `neuro-san-studio`
  188. ```bash
  189. uv init
  190. uv venv
  191. source .venv/bin/activate
  192. uv add neuro-san-studio
  193. ```
  194. ### Initialize neuro-san-studio
  195. Run `ns init` to initialize a Neuro SAN Studio project. `ns` stands for Neuro SAN. You can also use the long command
  196. `neuro-san-studio` instead. It will:
  197. * let you choose an LLM provider
  198. * create a `config` folder with your choice of LLM models and plugins configuration
  199. * create an `mcp` folder with a list of MCP tools
  200. * create a `registries` folder with a simple agent network and the
  201. [Agent Network Designer](#agent-network-designer), so you can start designing your own networks right away
  202. * create a `coded_tools` folder with the Python code those agent networks need
  203. * create an empty `middleware` folder for middleware you add later
  204. To learn more about the `ns` command run `ns --help`.
  205. ```bash
  206. ns init
  207. ```
  208. ```bash
  209. Which LLM providers do you want to enable?
  210. # Provider Default model
  211. 1 OpenAI gpt-5.2 (default)
  212. 2 Anthropic claude-sonnet
  213. 3 Google Gemini gemini-3-flash
  214. Enter numbers separated by commas (default: 1):
  215. ```
  216. **Note:** To access all Neuro SAN Studio capabilities, clone this repository and follow the setup instructions in the
  217. [docs/dev_guide.md](docs/dev_guide.md).
  218. ### Set your LLM API key(s)
  219. 1. Set your provider key, e.g. `OPENAI_API_KEY`, `ANTHROPIC_API_KEY` or `GOOGLE_API_KEY`
  220. (or create a `.env` file in the current directory).
  221. See [docs/api_key.md](docs/api_key.md) for details and other providers.
  222. ```bash
  223. export OPENAI_API_KEY="XXX"
  224. ```
  225. 2. Check your LLM API keys are correctly configured:
  226. ```bash
  227. ns check-llm-keys
  228. ```
  229. 3. Check your `config/llm_config.hocon` is working:
  230. ```bash
  231. ns check-config
  232. ```
  233. If the configuration is valid you will get a `hello` response from the configured LLMs.
  234. ### Import agent networks
  235. `ns init` already installs the Agent Network Designer, so you can start building right away.
  236. Use `ns import` to add any of the other agent network examples that ship with `neuro-san-studio`.
  237. Run it with no arguments to pick from an interactive list:
  238. ```bash
  239. ns import
  240. ```
  241. Or name a group or a single network directly:
  242. ```bash
  243. ns import basic # every network in the "basic" group
  244. ns import hello_world # a single network
  245. ```
  246. Each imported network brings its dependencies with it -- coded tools, middleware, sub-networks -- and is registered in
  247. `registries/manifest.hocon`. A running server picks it up within a few seconds.
  248. See [`docs/cli/import.md`](docs/cli/import.md) for the full set of options.
  249. ### Start the developer UI
  250. You can start a `neuro-san` server and the `nsflow` UI with the `ns run` command:
  251. ```bash
  252. ns run
  253. ```
  254. The Neuro SAN server listens on `localhost:8080`.
  255. The nsflow UI is served at
  256. [http://localhost:4173/](http://localhost:4173/).
  257. Logs land under `logs/` (`server.log`, `nsflow.log`, `thinking_dir/`).
  258. Screenshot:
  259. ![NSFlow UI Snapshot](https://raw.githubusercontent.com/cognizant-ai-lab/nsflow/main/docs/snapshot01.png)
  260. ### Agent Network Designer
  261. Use the Agent Network Designer to create your own agent network.
  262. 1. From the `nsflow` UI, click the `NEW` button at the top, center of the screen.
  263. ![AND Button](docs/images/agent_network_designer_new_button.png)
  264. 2. In the new window that opens, type your prompts in the text box in the bottom right
  265. corner of the screen. Then Agent Network Designer:
  266. * Creates the agents
  267. * Links them together
  268. * Writes instructions for each agent
  269. * Generates a few sample queries you can ask this agent network
  270. * Saves the agent network in the `registries/generated` folder
  271. 3. Once the Agent Network Designer is done and comes back with an answer in the chat window,
  272. you can continue the design by asking it to make changes
  273. 4. Once you're happy with the design, test it! Click the blue `Launch` button at the top
  274. center of the screen. It opens a new window from which you can chat with the agent network.
  275. 5. If you want to make modifications, go back to the editor window and ask for changes.
  276. 6. You can also edit any agent network by clicking the pen icon next to its name in the main window.
  277. ### Import a project from a file / Export to a file
  278. You can import a project from a .hocon file or from a zip file using the `ns import <PATH>`.
  279. ```bash
  280. ns import ~/Downloads/my_project.hocon
  281. ```
  282. Similarly, you can export an agent network and all its dependencies using the `ns export` command:
  283. ```bash
  284. ns export my_project.hocon
  285. ```
  286. See [`docs/cli/export.md`](docs/cli/export.md) for details.
  287. ### Command reference
  288. <!-- pyml disable line-length -->
  289. | Command | Purpose | Key flags |
  290. |---------------------|------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
  291. | `ns init` | Scaffold a starter project in the current dir. | `--providers openai,anthropic,google` |
  292. | `ns run` | Start the Neuro SAN server and nsflow UI. | `--server-host`, `--server-http-port`, `--nsflow-port`, `--log-level`, `--client-only`, `--server-only` |
  293. | `ns chat` | Chat with an agent network directly (no server needed). | Positional: agent name, `--connection`, `--host`, `--port`, `--one-shot`, `--list`. |
  294. | `ns import` | Import agent networks into the current project. | Positional: space-separated group names, network names, or `all`; or local `.hocon` / `.zip` paths (don't mix the two). `--force` to overwrite. Omit args for interactive mode. |
  295. | `ns export` | Bundle a network from the current project into a shareable file. | Positional: network name (e.g. `music_nerd` or `basic/music_nerd`). `-o` / `--output` to set the output path. Omit args for interactive picker. |
  296. | `ns check-llm-keys` | Validate LLM API keys / env vars. | `--tier 1` (placeholder), `--tier 2` (format), `--tier 3` (live API call, default) |
  297. | `ns check-config` | Validate the LLM configurations in a HOCON file. | `--hocon-path` (defaults to `config/llm_config.hocon`) |
  298. | `ns validate` | Validate a network file and load its coded tools and middleware. | Positional: HOCON path. `--verbose`, `--manifest`, `--external-agents`, `--registry-dir`. References to other networks (`/name`) are checked against the networks served by the manifest. |
  299. <!-- pyml enable line-length -->
  300. Use `ns <command> --help` for the full flag list of any subcommand.
  301. ---
  302. ## User guide
  303. Ready to dive in? Check out the [user guide](docs/user_guide.md) for a detailed overview of the neuro-san library
  304. and its features.
  305. ---
  306. ## Tutorial
  307. For a detailed tutorial, refer to [docs/tutorial.md](docs/tutorial.md).
  308. ---
  309. ## Examples
  310. For examples of agent networks, check out [docs/examples.md](docs/examples.md).
  311. ---
  312. ## Developer Guide
  313. For local development setup and contribution instructions, see the [docs/dev_guide.md](docs/dev_guide.md).
  314. ---
  315. ## Community Projects
  316. ### Applications
  317. * [Climate Change](https://github.com/cognizant-ai-lab/neuro-san-cc):
  318. a tool to answer questions about COP, the Paris Agreement or the Kyoto Protocol using UNFCCC documents.
  319. * [Enterprise Access Portal](https://github.com/M-Elsaied/enterprise-access-portal):
  320. an AI-powered multi-agent system for managing enterprise application access requests and IT operations.
  321. * [F1 fans eval](https://github.com/deepsaia/f1-fan-eval):
  322. an app that evaluates F1 fan submissions about why they are the biggest F1 fans.
  323. * [PDF Knowledge Assistant](https://github.com/M-Elsaied/neuro-san-studio/tree/pdf-knowledge-base/apps/pdf_knowledge_assistant):
  324. a Flask web app that queries PDFs using RAG with topic-based long-term memory synthesis across documents.
  325. * [Loopy Agents](https://github.com/babakatwork/loopy_agent):
  326. run Neuro SAN agents continuously or on triggers through a separate service, with asynchronous messaging.
  327. * [Annual Report Reader](https://github.com/shrushtiimehta/neuro-san-annual-report-reader):
  328. analyzes a LinkedIn profile and delivers a personalized summary of Cognizant's 2024 Annual Report,
  329. surfacing content most relevant to the user's industry and seniority level.
  330. * [Tochiro File Organizer](https://github.com/ofrancon/tochiro):
  331. a macOS file organization assistant with a dedicated UI to analyze a folder,
  332. create a plan for moving the files, ask for approval and execute the moves.
  333. * [Legacy Business-Rule Extractor](https://github.com/Sivakumarraj/neuro-san-legacy-analyzer):
  334. a 6-agent network that extracts business rules from legacy COBOL, Java, and PL/SQL code,
  335. pairing deterministic CodedTool parsers with LLM agents to produce a modernization-ready
  336. specification document.
  337. ### Utilities
  338. * [Neuro SAN Web Client](https://github.com/cognizant-ai-lab/neuro-san-web-client):
  339. a basic Flask web client interface for Neuro SAN.
  340. * [Neuro SAN Slack app](./apps/slack/README.md)
  341. a Slack integration that lets you interact with Neuro SAN directly from your workspace.
  342. ---
  343. ## Links
  344. * Website: [Cognizant AI Lab](https://www.cognizant.com/us/en/ai-lab)
  345. * YouTube: [Decision AI](https://www.youtube.com/@decision-ai)
  346. * X: [@cognizantailab](https://x.com/cognizantailab)
  347. * LinkedIn: [Cognizant AI Lab](https://www.linkedin.com/showcase/cognizant-ai-lab)
  348. * Amazon Marketplace: [Cognizant Neuro SAN](https://aws.amazon.com/marketplace/pp/prodview-z246c4x7j3xb6)
  349. * Azure Marketplace: [Cognizant Neuro SAN](https://marketplace.microsoft.com/en-us/product/virtual-machine/cognizant.cognizant_neurosanai-application)
  350. ---
  351. ## More details
  352. For more information, check out the [Cognizant AI Lab Neuro SAN landing page](https://www.cognizant.com/us/en/ai-lab/neuro-san).

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.