Sold by: Cognizant
Deployed on AWS
Open-source multi-agent AI platform by Cognizant AI Lab. Launch a ready-to-run server, add your own LLM key, and build, run, and debug agent networks in minutes with the NSFlow visual UI.
Overview
Image
neuro ai chatbot interface
Image
vibe code agent networks
Image
third party integrations
Image
agent to agent communication
Video
Product video
Cognizant Neuro® San (neuro-san-studio) is an open-source platform for building and running networks of cooperating AI agents, delivered as a ready-to-run image. The software is free and open source (Apache-2.0); you bring your own LLM API key.
Key capabilities:
- sly_data channel: keeps API keys, tokens, and PII out of LLM prompts.
- MCP-native: every server exposes a Model Context Protocol endpoint for agent-to-agent interoperability (e.g., with Amazon Bedrock).
- CodedTools: call deterministic Python functions from any agent.
- NSFlow: a real-time visual UI to design, run, and debug agent networks.
- Agent Network Designer: a meta-agent that generates HOCON networks from natural-language descriptions.
- Ships with 90+ ready-to-run example agent networks across banking, insurance, airline, retail, coding assistants, and more.
Getting started (after subscribing on AWS Marketplace):
- From the product page, choose Continue to Subscribe, then Continue to Configuration, then Continue to Launch. Select region US East (N. Virginia) and the recommended instance type (c7i.xlarge).
- Launch the instance with a key pair and a security group allowing inbound TCP 22 (SSH) and 4173 (NSFlow UI).
- SSH into the instance: ssh -i .pem ubuntu@
- Add one LLM API key: sudo nano /opt/neuro-san-studio/.env (uncomment a line, e.g. OPENAI_API_KEY=sk-...)
- Restart the service: sudo systemctl restart neuro-san-studio
- Open the NSFlow UI in your browser: http://:4173
Learn more: https://github.com/cognizant-ai-lab/neuro-san-studio
Highlights
- AAOSA protocol: decentralized, self-organizing inter-agent routing with no central orchestrator.
- HOCON configuration: describe complete agent networks declaratively, with no orchestration code.
- LLM-agnostic: per-agent model choice across OpenAI, Anthropic Claude, Google Gemini, Ollama, and Azure OpenAI.
Details
Sold by
Delivery method
Delivery option
64-bit (x86) Amazon Machine Image (AMI)
Latest version
Operating system
Ubuntu 22.04
Deployed on AWS
New
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Features and programs
Financing for AWS Marketplace purchases
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
Pricing
Pricing is based on actual usage, with charges varying according to how much you consume. Subscriptions have no end date and may be canceled any time.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
Dimension | Cost/hour |
|---|---|
c7i.xlarge Recommended | $0.013875 |
c5.2xlarge | $0.013875 |
c5.xlarge | $0.013875 |
t3.large | $0.013875 |
t3.xlarge | $0.013875 |
m7i.xlarge | $0.013875 |
c7i.2xlarge | $0.013875 |
Vendor refund policy
All sales are final and we do not offer refunds. You may cancel your monthly subscription at any time to stop future charges; access continues through the end of the current billing period. For billing questions, contact somesh.pattanaik@cognizant.com .
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA) .
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
Delivery details
64-bit (x86) Amazon Machine Image (AMI)
Amazon Machine Image (AMI)
An AMI is a virtual image that provides the information required to launch an instance. Amazon EC2 (Elastic Compute Cloud) instances are virtual servers on which you can run your applications and workloads, offering varying combinations of CPU, memory, storage, and networking resources. You can launch as many instances from as many different AMIs as you need.
Version release notes
Initial release: Cognizant Neuro San (neuro-san-studio 0.3.4) on Ubuntu 22.04 LTS with Python 3.12. Includes the neuro-san multi-agent server, the NSFlow visual UI, the Agent Network Designer, and 90+ ready-to-run example agent networks. Bring your own LLM API key.
Additional details
Usage instructions
After launching, the neuro-san-studio service starts automatically. To use it:
- SSH in: ssh -i <your-key>.pem ubuntu@<instance-public-ip>
- Add one LLM API key: sudo nano /opt/neuro-san-studio/.env (uncomment a line, e.g. OPENAI_API_KEY=...)
- Restart the service: sudo systemctl restart neuro-san-studio
- Open the NSFlow UI: http://<instance-public-ip>:4173 Docs: https://github.com/cognizant-ai-lab/neuro-san-studio
Resources
Support
Vendor support
For any support please contact somesh.pattanaik@cognizant.com
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Similar products
Cognizant's Lotus Notes modernization offering leverages Pega Notes to Blueprint, an AI powered analysis and transformation tool designed to accelerate Pega transformation. The tool combines AI-powered legacy estate analysis with, Cognizant’s deep industry solutions expertise, proven transformation methodology and cloud-native workflow automation on AWS — to help enterprises retire Lotus Notes, reduce operational risk, and unlock agentic AI capabilities.
Cognizant’s AI transformation service, powered by Cognizant Powered Blueprint™
A unique, AI-driven enterprise transformation solution that fuses Pega's revolutionary agentic workflow designer with Cognizant's proprietary IP, consulting methodologies, and decades of global implementation expertise.
Every engagement starts informed, not blank — grounding your AI transformation in real-world enterprise context from day one, closing the gap between AI pilots and AI in production, regardless of the source system or transformation tool.
Cognizant Ignition is a transformative platform designed to revolutionize data and business intelligence modernization. Experience accelerated time-to-market with up to 60% automation of modernization tasks and up to 40% reduction in implementation timelines.
Cognizant professional service to assess, implement, migrate for Singapore Public Sector applications to GCC AWS.
Customer reviews
No customer reviews yet
Be the first to review this product . We've partnered with PeerSpot to gather customer feedback. You can share your experience by writing or recording a review, or scheduling a call with a PeerSpot analyst.