Agent Frameworks

Framework for building agent swarms using the OpenAI Assistants API. Enables creating agencies where agents communicate ...

Multi-agent framework for building, orchestrating, and evaluating LLM-powered agent systems with built-in memory managem...

Lightweight Python framework for building multi-modal agents. Memory, knowledge, and tool use built-in.

Lightweight, composable framework for building AI agents and pipelines. Uses Pydantic for schema validation and focuses ...

AutoGen is a Microsoft-backed framework for building multi-agent AI systems where multiple LLM-powered agents collaborat...

IBM's open-source framework for building, deploying, and serving powerful agentic workflows at scale. Features ReAct-bas...

Communicative Agents for Mind Exploration of Large Scale Language Models. Role-playing framework enabling autonomous coo...

Virtual software company powered by LLM agents. Multiple specialized agents (CEO, CTO, programmer, reviewer) communicate...

Multi-agent orchestration framework that enables developers to define crews of AI agents with roles, goals, and tasks to...

Multi-agent simulation framework in TypeScript by ai16z. Powers autonomous AI agents for social media, Web3, and convers...

Platform and SDK for building stateful, long-running AI agents. Agents persist state across sessions, execute multi-step...

LangChain's framework for building stateful multi-agent applications with cycles, branching, and persistence.

A generalist multi-agent system for solving complex web and file-based tasks, built on Microsoft AutoGen. Uses an Orches...

Multi-agent framework that assigns different roles (engineer, PM, architect) to LLMs to collaboratively solve complex so...

Official OpenAI framework for building multi-agent systems. Handoffs, guardrails, and tracing built-in.

An experimental, educational framework for lightweight multi-agent orchestration using OpenAI's Chat Completions API. Di...

Agent framework by the Pydantic team. Type-safe agent definition with dependency injection and structured responses.

Rust library for building LLM-powered applications and agents. Provides type-safe abstractions for model providers, vect...

Hugging Face's lightweight agent library. Code-based agents that write and execute Python to solve tasks.

Open-source autonomous AI agent framework with a developer-first interface. Supports concurrent agents, custom tools, ve...

Production-grade multi-agent orchestration framework by Kyegon Labs. Supports sequential, concurrent, and hierarchical a...

Microsoft's code-first agent framework for data analytics tasks. Converts user requests into executable Python code snip...