Cognizant Open-Sources Neuro AI Multi-Agent Accelerator, Advancing Enterprise AI Adoption

Cognizant Open-Sources Its Neuro AI Multi-Agent Accelerator

'[We] want to establish this as the de facto standard by which people create these types of scaled multi-agentic systems. There are other platforms out there for creating multi-agent systems. We found none of them to be at the same scale with the same level of interoperability, the simplicity to build these systems, and the safety features that we have. So we decided to put this out there in the service of the AI and developer community and encourage everyone to use it,' says Babak Hodjat, Cognizant's chief technology officer of AI. Global solution provider Cognizant Thursday said it has open-sourced its Neuro AI Multi-Agent Accelerator technology for prototyping and building agent networks across any industry vertical. The Neuro AI Multi-Agent Accelerator is the platform and framework that Cognizant uses to build multi-agentic systems safely and at scale, said Babak Hodjat, chief technology officer of AI at Teaneck, N.J.-based Cognizant, which is No. 8 on CRN's Solution Provider 500. Cognizant uses its Neuro AI Multi-Agent Accelerator to create multi-agent systems for internal use and for its clients, but is now bringing it to open source to promote the creation of multi-agentic systems, Hodjat told CRN. [Related: Cognizant Ties AI Agents From Multiple Apps For Scale, Autonomous Operations] "This is going to be an academic research license, obviously," he said. "But we also want to establish this as the de facto standard by which people create these types of scaled multi-agentic systems. There are other platforms out there for creating multi-agent systems. We found none of them to be at the same scale with the same level of interoperability, the simplicity to build these systems, and the safety features that we have. So we decided to put this out there in the service of the AI and developer community and encourage everyone to use it, because I think people will benefit from being able to create agent networks that then they can connect to other agents." The repository for Cognizant's multi-agent accelerator will be located on GitHub and known as neuro-san, where "san" is short for system of agent networks, Hodjat said. There will also be a studio available, neuro-san-studio, with a number of pre-built templates, he said. "Those pre-built templates include, and maybe this will amaze you, an agent network that can create agent networks," he said. "It's a network of agents. You describe your process or your company, or the task at hand, and it will automatically design and create an agent network for that particular task. Obviously, there's work to be done to ground these systems, but it's a great starting point to explore." The academic research license gives developers and researchers the opportunity to experiment with the Neuro AI Multi-Agent Accelerator, as well as contribute back to the technology, Hodjat said. However, that license does not allow commercial use, he said. "I think we need the libraries to be in the hand of professionals who can actually build them out and ground them for the enterprises," he said. "And we think we're the best people to do so for that. People have to come see us, but if you want to kick the tires, if you want to contribute as part of the community to the code base and help extend it and expand it and make your own agents interoperable with it, this can end up being the fabric that allows this interoperability with other agents." Hodjat said the system is already interoperable with Google's Agentspace and Salesforce's Agentforce, and supports Anthropic's MCP (model context protocol). "Many companies, including Google and OpenAI and so forth have signed up to it," he said. "It also supports A2A, or Agent2Agent, announced by Google recently. It's been designed to be fully interoperable. As a developer, as someone that's working in academia or research, you have full access, and you can play around with it. It's just the commercialization aspect that is restricted." The Neuro AI Multi-Agent Accelerator allows users to run agent networks and serve them, Hodjat said. Users can have multiple servers, with each server running its own agent network, and agents from one server can talk with agents to another server. "It allows that kind of complexity in a very straightforward, simple way, actually," he said. Hodjat said there are other open source multi-agent accelerators available, including an open source library called LangChain on which the Cognizant system was built. "LangChain is almost a de facto standard now for agentic systems, and it allows you to build agentic systems that are LLM-agnostic," he said. "So if you want to use Google Gemini or Open AI GPT-4 or Anthropic or what have you, or open source networks like Llama, you can do that very easily. We didn't reinvent the wheel on that. " Other open source multi-agent accelerators include Microsoft AutoGen and LangGraph, he said. Cognizant is "client zero" for its Neuro AI Multi-Agent Accelerator, Hodjat said. "We've used it and it's in deployment now for our own intranet," he said. "And what's amazing is that the intranet has many agents in it. This would be the biggest modern multi-agentic system you've seen. It includes HR, finance, legal, and sales. Just imagine the scale and the security aspects and the safety aspects that have to go into identifying your intranet, as well as the fact that you need to set it up in a way that is incrementally extensible. And that's one of the things that this system does very, very well." Cognizant already has a number of commercial clients for its Neuro AI Multi-Agent Accelerator, including Telstra, the Australian telecommunications company.

Cognizant Makes Scalable Agent Networks Accessible to Every Enterprise By Investing.com

TEANECK, N.J., May 22, 2025 /PRNewswire/ -- Cognizant (Nasdaq: CTSH) today announced that it has open-sourced its Neuro ® AI Multi-Agent Accelerator for research and academic use. This open-source software enables domain experts, researchers, and developers to immediately start prototyping and building agent networks across virtually any use case. The open-source software will help accelerate AI adoption by promoting collaboration in building and customizing multi-agent systems for adaptive operations and real-time decision-making. Enterprises can leverage Cognizant's Multi-Agent Services Suite to deploy networks of agents in a commercial setting at scale and to efficiently manage them in production, under a commercial license. The AI Agents Market is anticipated to rapidly grow over the next five years, from a value of USD 5.1 billion in 2024 to a projected worth of USD 47.1 billion by the year 2030. Today's news speeds how enterprises can leverage interconnected agents to explore new revenue streams and drive scalable business value. Developed by Cognizant's AI Lab, the open-sourced software for Neuro ® AI Multi-Agent Accelerator demonstrates Cognizant's leadership in AI innovation and its commitment to advancing the application of AI Agents. Clients like Telstra, Australia's leading telecommunications and technology company, are working with Cognizant to test and deploy multi-agent systems. "The open sourcing of the Neuro AI Multi-Agent Accelerator will further empower our teams to rapidly prototype and integrate existing AI agents, and help accelerate our software development lifecycle," said Telstra's Group Executive for Product and Technology, Kim Krogh Andersen. "We're already starting to see the potential for gains in quality, velocity and efficiency as a result." Cognizant has also helped a healthcare company create a Contract Negotiator agent network that speeds up medical appeal processing times, as well as a consumer packaged goods firm for analyzing supply chain management. Cognizant is in the process of more than 65 conversations with clients around agentic AI. Building a successful multi-agent network requires the ability to orchestrate diverse agents, tools, and knowledge sources " including general-purpose large language models (LLMs) and organization-specific systems like service level management (SLMs) or retrieval-augmented generation (RAG) frameworks. Cognizant's Neuro AI Multi-Agent Accelerator aims to enable virtually seamless integration with APIs, RAG, and third-party agents like Salesforce's Agentforce, Google's Agentspace, or Crew AI"via its native Model Context Protocol (MCP) or standard API calls. An optional inter-agent coordination protocol allows these agents to autonomously organize, delegate tasks, and route processes"boosting efficiency and minimizing errors. Agent2Agent (A2A) protocol is also supported, which expands agent collaboration across clouds, platforms, and organizational boundaries. "To stay competitive in the era of agentic AI, enterprises must be free to experiment"to explore how agents can transform business processes and drive operational efficiencies," said Babak Hodjat, Chief Technology Officer of AI at Cognizant. "By open-sourcing Neuro AI Multi-Agent Accelerator, we're expanding access to our cutting-edge multi-agent technology"empowering developers to innovate faster, and enabling decision-makers, regardless of technical background, to rapidly prototype systems and directly observe their impact on key performance indicators. "Agentforce is built on Salesforce's deeply unified platform that is open and extensible, empowering our ecosystem of partners and builders to innovate with AI that's grounded in trust. Cognizant's decision to open source its Neuro AI Multi-Agent Accelerator exemplifies the kind of partnership that helps our customers move faster and innovate with confidence," said Gary Lerhaupt, Vice President of Product Architecture, Salesforce. "Together, we're enabling enterprises to deploy agents that think, collaborate, and deliver value"across every corner of their business." Neuro ® AI Multi-Agent Accelerator - Key Features: Cognizant Scales Agents to 330,000 people via its Intranet, 1Cognizant Thousands of employees now use 1Cognizant, an intranet assistant powered by its Neuro AI Multi-Agent Accelerator. This tool consolidates and organizes multiple agents to efficiently help employees with various tasks, from reserving meeting rooms and calling cabs to handling inquiries like moving countries or getting married. 1Cognizant can now provide immediate actionable advice and assistance to employees, increasing efficiency and breaking down internal silos. For more information visit our landing page or our blog. About Cognizant Cognizant (Nasdaq-100: CTSH) engineers modern businesses. We help our clients modernize technology, reimagine processes and transform experiences so they can stay ahead in our fast-changing world. Together, we're improving everyday life. See how at www.cognizant.com or @cognizant.

Cognizant Makes Scalable Agent Networks Accessible to Every Enterprise

Cognizant announced that it has open-sourced its Neuro AI Multi-Agent Accelerator for research and academic use. This open-source software enables domain experts, researchers, and developers to immediately start prototyping and building agent networks across virtually any use case. The open-source software will help accelerate AI adoption by promoting collaboration in building and customizing multi-agent systems for adaptive operations and real-time decision-making. Enterprises can leverage Cognizant's Multi-Agent Services Suite to deploy networks of agents in a commercial setting at scale and to efficiently manage them in production, under a commercial license. The AI Agents Market is anticipated to rapidly grow over the next five years, from a value of USD 5.1 billion in 2024 to a projected worth of USD 47.1 billion by the year 2030. Today's news speeds how enterprises can leverage interconnected agents to explore new revenue streams and drive scalable business value. Developed by Cognizant's AI Lab, the open-sourced software for Neuro®? AI Multi-agent Accelerator demonstrates Cognizant's leadership in AI innovation and its commitment to advancing the application of AI Agents. Clients like Telstra, Australia's leading telecommunications and technology company, are working with Cognizant to test and deploy multi-agent systems. Neuro AI Multi- Agent Accelerator - Key Features: Intelligent Opportunity Discovery: Provide a company name or problem area, and the Agent Network Designer will automatically propose a tailored agentic network aligned to user use case--hel helping user move from idea to implementation faster. Rapid and Streamlined Customization: Quickly build and modify multi-agent systems using natural language or leverage prebuilt templates for domains like loan origination, customer service, retail optimization, and intret automation--dramatically reducing development cycles and risk. Scalable, Distributed Operation: Connectors support homegrown tools, APIs, and third-party agents like Salesforce's Agentforce and Google Agentspace via Model Context Protocol or standard API calls. A coordination layer enables agents to intelligently self-organize, distribute tasks, and route processes--boosting efficiency and reducing errors. Secure Private Data: Supports regulated industries such as finance and healthcare by isolating confidential information through private data channels to support compliance and data protection. LLM and Cloud Provider Agnostic: Easily switch between open-source and most commercial LLMs, as well as private/public cloud providers, without the need for system rebuilds. Extensible Coded Tools: Enhance agent networks with custom-coded tools--vital for grounding agent decisions in real-time data, or for defining logical boundaries that trigger human intervention where needed. Multi-server, Distributed Deployment: Run agent sub-networks across multiple servers, enabling scalable architectures that support parallel processing, geographic distribution, or segmented use cases. Data-Driven Network Definition: Define and update agentic systems entirely via data-only configuration files--supporting version control, auditability, and rapid reusability across projects. Agent Testing Capability: Use the Agent Network Tester to identify bottlenecks or breakdowns within network. Get actionable insights into coordination issues, agent logic gaps, or integration errors. Cognizant Scales Agents to 330,000 agents to 330,000,000,000 agents to support the next five years.