Agentic AI & Multi-Agent Systems

Foundational library for agents, chains, and memory.

The original autonomous AI agent framework that sparked the agent revolution. Vision of accessible AI for everyone with modular agent architecture, benchmark testing, and forge-based agent building. 183k+ stars.

Stateful, controllable agent orchestration.

Role-based agent framework.

Flexible multi-agent conversation framework.

Framework for programming language model pipelines with modules, optimizers, and evaluation loops.

SDK for building and orchestrating AI agents and workflows across multiple programming languages.

TypeScript API/SDK for AI agent decision workflows: typed choices, scores, and probabilities via one evaluate() call. MIT licensed.

Lightweight agent framework centered on tool use and code-executing workflows.

PHP Agentic Framework for building production-ready AI driven applications. Connect components (LLMs, vector DBs, memory) to agents that can interact with your data. MIT licensed.

New open-source framework to build and deploy intelligent agents with support for Claude, Gemini, and OpenAI models. Apache 2.0 licensed.

The agent that grows with you. Autonomous server-side agent with persistent memory that learns and improves over time.

Model-driven approach to building AI agents in just a few lines of code. Multi-agent systems, autonomous agents, and streaming support with built-in MCP. Apache 2.0 licensed.

Build, run, and manage agentic software at scale. High-performance framework for multi-agent systems with memory, knowledge, and tools.

Agent framework for fintech and banking with built-in MCP support, guardrails, and tool server architecture.

TypeScript-first AI agent engineering platform with memory, RAG, workflows, MCP integration, and voice support.

100-line minimalist LLM framework for building agent workflows. Lightweight, extensible architecture for tool use and autonomous task execution.

Code-first Python toolkit for building sophisticated AI agents with multi-agent orchestration, built-in evaluation, and flexible deployment. Model-agnostic with tight Google ecosystem integration. Apache 2.0 licensed.

Type-safe AI agent framework from the creators of Pydantic. Model-agnostic with 20+ providers, built-in observability via Logfire, MCP/A2A protocol support, and YAML/JSON agent definitions. MIT licensed.

Modular Python framework for AI agents and workflows with chain-of-thought reasoning, tools, and memory. Enforces structures like sequential pipelines and DAG-based workflows for predictable AI systems. Apache 2.0 licensed.

Harness LLMs with multi-agent programming. Mature tool calling system based on Pydantic, supports hundreds of LLM providers including OpenAI and local servers. Built for robust agent behavior in real-world use cases. MIT licensed.

Model-agnostic AI agent runtime written in Rust with specialist agents, MCP support, multiple provider integrations, and zero-config setup. Apache 2.0 licensed.

Python framework for structured outputs and agentic AI workflows. Simplifies LLM interactions with type-safe interfaces, automatic schema generation, and built-in observability. From the creators of Prefect. Apache 2.0 licensed.

Apache incubating framework for building stateful AI applications (chatbots, agents, simulations). Monitor, trace, persist, and execute on your own infrastructure with built-in UI and pluggable memory. Apache 2.0 licensed.