Welcome to the AI Alliance
You found the AI Alliance Github organization, where you can learn, use, and contribute to our open source AI projects.
The projects on this page are a prioritized set from across our community, including two types: Supported Projects are led and managed by a Member(s) of the AI Alliance (a company, a non-profit, etc.). Managed Projects are owned by the AI Alliance. Both types of projects commit to minimum requirements on transparency, contributor opportunity and IP, permissive use licensing, and community conduct. Learn more about our project governance here.
The Open Agent Lab
Collaborate, Experiment, and Build Production-ready Open Source Agents
The Open Agent Lab is a collaborative community of open source AI projects and domain-specific work groups that seek to make AI Agents successful in the real world through fast experimentation and distillation of learning into usable reference architectures and implementations, and build out of new tools to enable development and deployment.
Agent Reference Application Hub
(In progress - coming soon!) The agent reference application hub is a repository of continually updated domain-specific implementaitons and architectural components for developing and deploying agents based on the output of our work groups, which include AI researchers, engineers, and subject matter experts from industry leading organizations. Here is some of our initial work:
Industrial AI / Semiconductors: check out SemiKong a foundation model for semiconductor process agents.
Expert knowledge / Legal: try Bartlebot if you want to work with case law and other legal topics.
Finance: see Deep Research Agent for Finance, a new collaboration between finance and AI experts in the Alliance to explore the practical challenges of building and running trustworthy, production-quality AI-based finance applications.
Geospatial: check out projects like GeoBench and TerraTorch.
(Coming soon.) Materials, Health, and Time Series work groups.
Llama Stack and Llama Stack Agents
The Llama Stack project standardizes the core building blocks that simplify AI application development. It codifies best practices across the Llama ecosystem, integrates with other open-source tools and managed services, and provides APIs for inference, evaluation, agents, MCP, and deployment requirements like observability. It is designed to support both on-premise and cloud deployments. The ecosystem provides many example applications to help developers build and deploy AI applications quickly and effectively.
AI Alliance members are contributing directly to Llama Stack development, as well as building example applications that illustrate its use in various enterprise scenarios. The llama-stack-examples
project has two initial example applications, described in the table below. The first app is a simple getting-started chatbot that shows you the basics of creating an app with Llama Stack and how to run it. The second app (in development) is a deep research application, a popular class of AI applications, which will demonstrate Llama Stack support for technologies like agents and MCP. Other examples under consideration will be chosen to cover other common application patterns seen in several industries. Please join us!
Links | Description |
---|---|
AI Alliance Llama Stack Example Apps ![]() |
|
A growing suite of example applications for Llama Stack that demonstrate various stack features and common application patterns:
|
|
Llama Stack Demos for OpenShift and Kubernetes | |
A suite of examples for deploying and managing Llama Stack-based applications on OpenShift and Kubernetes. (Principal developer: Red Hat) | |
Llama Stack | |
The Llama Stack project itself. | |
Llama Stack Python Client | |
The Python library used by client applications to communicate with Llama Stack services. See the Llama Stack documentation for usage examples. There are also client libraries for other programming languages in the llamastack GitHub organization.
|
Model Context Protocol (MCP) Ecosystem and Related Projects
The Model Context Protocol (MCP) from Anthropic is quickly becoming an industry standard for communications between models, agents, data repositories, and other tools. The AI Alliance seeks to advance this protocol and foster a robust suite of tools around it to enable broad, trusted, and high-value use in production.
Links | Description |
---|---|
MCP Gateway | |
A Model Context Protocol (MCP) Gateway that serves as a central management point for tools, resources, and prompts. It can be accessed by MCP-compatible LLM applications. It converts REST API endpoints to MCP, composes virtual MCP servers with added security and observability, and converts between protocols (e.g., stdio, SSE, etc.). (Principal developer: IBM) | |
LastMile AI MCP Agent | |
Build effective agents using Model Context Protocol and simple workflow patterns. See the Deep Research Agent for Finance, discussed below, which is built with this toolkit. (Principal developer: LastMile AI) | |
Enkrypt AI Secure MCP Gateway | |
A secure MCP gateway built with authentication, automatic tool discovery, caching, and guardrail enforcement. It sits between your MCP client and MCP servers. So, by its nature, it also acts as an MCP server as well as an MCP client. When your MCP client connects to the gateway, it acts as an MCP server. When the gateway connects to the actual MCP server, it acts as an MCP client. (Principal developer: Enkrypt AI) |
The NLIP Project
The NLIP project is facilitating the development of an open-source protocol for intelligent agents to communicate with each other and with humans using natural language.
Links | Description |
---|---|
NLIP Project | |
The NLIP project is facilitating the development of an open-source protocol for intelligent agents to communicate with each other and with humans using natural language. NLIP is designed to perform the role of a meta-protocol that allows agents from other ecosystems to communicate with one another including interfaces with other protocols such as A2A, ACP, AGNTCY, MCP, NANDA, etc.
One outcome will be a new ECMA standard, TC-56 NLIP, Natural Language Interaction Protocol. The organization is also developing reference implementations of the protocol and end-points. See the GitHub organization for details on these implementations. |
AI-Powered Programming Language for Agents
Links | Description |
---|---|
Dana — The Agent-Native Evolution of AI Development | |
Dana is based on the question, “What if your agents could learn, adapt, and improve itself in production—without you?”
Dana bridges the gap between AI coding assistance and autonomous agents through agent-native programming: native agent primitives, context-aware reason() calls that adapt output types automatically, self-improving pipelines with compositional | (“pipe”) operators, and functions that evolve through POET feedback loops (an automated prompt improvement technique). (Principal developer: Aitomatic)
|
Agent Knowledge and Tool Foundations
Links | Description |
---|---|
Agent Lab UI ![]() |
|
AgentLabUI is a web-based interface designed to simplify the creation, management, and deployment of AI agents. It supports integration with Gofannon tools, enabling developers and researchers to rapidly prototype and experiment with sophisticated AI agent architectures. | |
Gofannon ![]() |
|
A repository of functions consumable by other agent frameworks. | |
Proscenium ![]() |
|
Collaborative, Asynchronous Human/Agent Interactions. | |
Lapidarist ![]() |
|
Document enrichment and knowledge structure (eg knowledge graph) extraction and resolution. | |
Deep Research Agent for Finance ![]() |
|
The Deep Research Agent for Finance project is a collaboration between finance and AI experts in the Alliance to explore the practical challenges of building and running trustworthy, production-quality AI-based finance applications. This project uses the LastMile AI MCP Agent, discussed above. | |
The Living Guide to Applying AI ![]() |
|
Tips from experts on using AI for various applications, including popular design patterns. | |
AllyCat ![]() |
|
(Beginner friendly!) Get started with a simple and fun end-to-end RAG application that scrapes your website so you can ask it questions. |
Governance, Evaluation and Safety
Safety, accuracy, red-teaming, security, compliance and more are required for successful AI applications. How do we know that AI applications are trustworthy, that they are safe, meaning free of harmful outputs, that they correctly implement the required behaviors? The following projects address these concerns.
Links | Description |
---|---|
Achieving Confidence in Enterprise AI Applications ![]() |
|
Are you an enterprise developer? How should you test AI applications? You know how to write deterministic tests for your "pre-AI" applications. What should you do when you add generative AI models, which aren't deterministic? This project adapts existing evaluation techniques for the "last mile" of AI evaluation; verifying that an AI application correctly implements its requirements and use cases, going beyond the general concerns of evaluation for safety, security, etc. We are building nontrivial, reusable examples and instructional materials, so you can use these techniques effectively in combination with the traditional tools you already know. See also the companion Evaluation Reference Stack and Evaluation Is for Everyone projects. This project is part of the Trust and Safety Evaluation Initiative (TSEI). | |
Evaluation Is for Everyone ![]() |
|
Evaluation Is for Everyone addresses two problems: 1) many AI application builders don't know what they should do to ensure trust and safety, and 2) it should be as easy as possible to add trust and safety capabilities to AI applications. Many trust and safety evaluation suites are available that can be executed on the Evaluation Reference Stack. We are making it as easy as possible for AI application developers to find and deploy the evaluations they need. See also the companion Achieving Confidence in Enterprise AI Applications project. This project is part of the Trust and Safety Evaluation Initiative (TSEI). | |
Evaluation Reference Stack ![]() |
|
The companion projects Achieving Confidence in Enterprise AI Applications and Evaluation Is for Everyone require a runtime stack that is flexible and easy to deploy and manage. This project is collating popular tools for writing and running evaluations into easy-to-consume packages. This project is part of the Trust and Safety Evaluation Initiative (TSEI). | |
Ranking AI Safety Priorities by Domain ![]() |
|
What are the most important safety concerns for your specific domain and use cases? This project explores these questions in several industries, healthcare, finance, education, and legal, with more to come. | |
The AI Trust and Safety User Guide ![]() |
|
Introduction to T&S with guidance from diverse experts. | |
unitxt | |
Unitxt is a Python library for enterprise-grade evaluation of AI performance, offering the world's largest catalog of tools and data for end-to-end AI benchmarking. (Principal developer: IBM Research) |
Open Trusted Data and Tooling
Good datasets are essential for building good models and applications. The AI Alliance is cataloging datasets, and in some cases building them, that have clear licenses for open use, backed by unambiguous provenance and governance constraints.
Links | Description |
---|---|
The Open, Trusted Data Initiative ![]() |
|
Open data has clear license for use, across a wide range of topic areas, with clear provenance and governance. OTDI seeks to clarify the criteria for openness and catalog the world’s datasets that meet the criteria. Our projects:
|
|
Docling | |
Docling simplifies document processing, parsing diverse formats — including advanced PDF understanding — and providing seamless integrations with the gen AI ecosystem. Docling is a key tool for the project Parsing PDFs to Build AI Datasets for Science, discussed above. (Principal developer: IBM Research) |
Open Models and Tooling for New Domains and Modalities
The AI Alliance is building new models for many domains and modalities at the intersection of research and engineering. Our projects include models for industrial AI, molecular discovery, geospatial, and time series applications.
Links | Description |
---|---|
Open Models | |
Several AI Alliance work groups are collaborating on the development of domain-specific models:
|
|
TerraTorch | |
TerraTorch is a library based on PyTorch Lightning and the TorchGeo domain library for geospatial data. (Principal developer: IBM Research) | |
GEO-bench | |
GEO-Bench is a General Earth Observation benchmark for evaluating the performance of large pre-trained models on geospatial data. (Principal developer: ServiceNow) |
Deployment and Scaling
Deploying and scaling AI systems, especially to the growing diversity of hardware accelerators for AI, and efficiently scaling from PoCs and single node deployments to large numbers of users and distributed deployments are a key set of challenges.
Links | Description |
---|---|
The AI Accelerator Software Ecosystem Guide ![]() |
|
A guide to the most common AI accelerators and the software stacks they use to integrate with tools you know, like PyTorch. |
AI Alliance Regional Chapters
The AI Alliance is a global organization. However, localization matters and is key to representation. To ensure effectiveness, relevance, and impact across diverse markets and communities, regional chapters of the AI Alliance exist and more are planned:
- Japan
- India - coming soon!
- Paris - coming soon!
Events
Come meet us and learn about AI! See our full list of Alliance-sponsored and third-party AI events.
Additional Links
- Contributing: We welcome your contributions! Here’s how you can contribute.
- About Us: More about the AI Alliance and this project.
For More Information
- The full list of Alliance-sponsored and third-party AI events.
- The AI Alliance GitHub Organization
- This documentation’s GitHub repo
- The microsite template: The template used for Alliance projects, including all the websites listed above. See the README-template.md for instructions.
- The AI Alliance website: About the AI Alliance, our goals and initiatives.
- Learn more about getting involved.
Authors | AI Alliance Team |
Last Update | V0.2.2, 2025-07-18 |