Agent frameworks

An agent operating system that keeps a hub of specialist AI agents and assembles a temporary team of them for a task, running locally alongside Claude Code, Codex, Cursor or Gemini.

• Agent frameworks

A third-party Android AI agent that can call system APIs, run a terminal, browse the web and act inside other apps, extended with Skills and MCP tools and using your own model API key.

• Agent frameworks
• Mobile

A library that lets AI agents call MCP and UTCP tools by writing and executing code instead of making individual tool calls, reducing the round trips needed for multi-step tasks.

• Agent frameworks
• MCP servers

An open-source showcase that uses CopilotKit and LangChain Deep Agents to let an AI agent generate interactive UI, such as algorithm visualizations, 3D animations, charts and diagrams, rendered live in a sandboxed iframe.

• Agent frameworks

An open standard, maintained by OpenAI and Stripe, that defines how buyers, their AI agents and businesses complete a purchase together using existing commerce infrastructure.

• Agent frameworks
• APIs

A CLI and set of standards for starting a new agent project, scaffolding scenario tests, versioned prompts and evaluation notebooks so agent behavior stays testable from day one.

• Agent frameworks
• AI evals

A self-hosted CLI agent framework that automates development chores such as PR reviews, bug fixing and security patching by combining reusable steps, prompt templates and an LLM.

• Agent frameworks
• Code quality

An open ecosystem where AI agents complete real-world tasks through workflow loops, get evaluated by mentor agents or humans, and turn the results into reusable training data.

• Agent frameworks
• AI evals

An advanced retrieval-augmented generation agent that uses a deterministic graph to answer complex questions over a user's own data that simple similarity search cannot solve.

• Agent frameworks
• RAG

A loop-engineering harness that turns existing coding agents into long-running, computer-use systems able to work across desktop apps and a terminal for dozens of hours.

• Agent frameworks

A Google DeepMind library for building generative social simulations, where language-model entities describe actions in natural language that a Game Master resolves into outcomes.

• Agent frameworks

A Python runtime framework for building GenAI application backends with structured outputs, observable actions, reusable skills and Model Context Protocol support.

• Agent frameworks

An unofficial, community desktop client for chatting with Claude and other LLM providers, built with Tauri, Rust and React, with local chat history, MCP tools and multi-agent orchestration.

• Agent frameworks
• Inference

An agent harness for interpreting financial markets that gives an agent a persistent research workspace per goal, so analysis and theses compound across sessions instead of resetting each time.

• Agent frameworks

An open-source Java toolkit for building, evaluating and deploying AI agents in code, with tight integration into Google Cloud services.

• Agent frameworks

A PHP framework for building generative AI applications and retrieval-augmented search, compatible with Symfony and Laravel and inspired by LangChain.

• Agent frameworks
• RAG

An open-source multi-agent simulation where several GPT-4 agents, each with its own memory, collaborate in a simulated world to work toward shared goals.

• Agent frameworks

Official code samples for the Agent2Agent protocol, demonstrating multi-agent interoperability with example agent servers and clients in Python, Go, .NET, Java and Node.js.

• Agent frameworks
• Tutorials

A local-first, self-hostable AI chat workspace that brings multi-model chat, an agent mode for multi-step tool workflows, and deep research with reviewable plans into one app, keeping conversation history in the browser by default.

• Agent frameworks
• Inference

An Android GUI agent framework that lets an AI agent see, plan and operate real Android app interfaces on a physical device, returning structured results for each action.

• Agent frameworks
• Mobile

A multi-agent AI platform for data analysis and research that automates hypothesis generation, data cleaning, visualization and report writing using LangChain, OpenAI models and LangGraph.

• Agent frameworks
• Data engineering

A DeepSeek Harness plugin that turns the current session into a captain able to assemble durable sub-agents, split a goal into dependency-aware tasks, and coordinate them through direct messages and a live web UI.

• Agent frameworks

A Go framework for building production agent systems, providing LLM agents, graph-based workflows, tool calling, session and memory state, knowledge retrieval, evaluation and OpenTelemetry observability in one Go-native stack.

• Agent frameworks

A single-binary management console with an embedded web UI for installing, configuring, monitoring and updating components of the NullClaw AI-agent ecosystem, including process supervision and health checks.

• Agent frameworks
• Monitoring