AutoGen ★ 60.5k

Pioneered multi-agent orchestration patterns at Microsoft Research with a layered extensible architecture (Core -> AgentChat -> Extensions), cross-language...

microsoft· dormant
CrewAI ★ 57.3k

Combines two complementary paradigms -- autonomous role-based Crews and event-driven deterministic Flows -- letting developers balance agent autonomy with...

crewAIInc· active
AgentScope ★ 29.1k

A model-centric (not framework-centric) agent service designed for increasingly agentic LLMs, shipping a full FastAPI backend + Web UI with multi-tenancy,...

agentscope-ai· active
Mastra ★ 27.3k

It is a TypeScript-native agent framework from the Gatsby creators: graph-based workflows with durable human-in-the-loop suspend/resume, Observational Memory, a...

mastra-ai· active
LangChain JS Tools ★ 18.1k

Framework for building LLM-powered applications that helps developers chain together interoperable components and third-party integrations, simplifying AI...

langchain-ai· active
Qwen-Agent ★ 17.0k

Framework for building LLM applications leveraging Qwen's instruction following, tool usage, planning, and memory capabilities, featuring MCP support, code...

QwenLM· active
PraisonAI ★ 8.9k

AI agent framework for autonomous, self-improving multi-agent systems. Unique five-layer agent stack (Prompt -> Context -> Harness -> Loop -> Graph) plus a...

MervinPraison· active
Flue ★ 8.0k

Programmable TypeScript harness framework for building autonomous agents where the agent IS a function composed of hooks (useModel, useSandbox, useSkill,...

withastro· active
Claude Agent SDK (Python) ★ 7.9k

Official Anthropic Python SDK for building agentic applications powered by Claude Code. In-process SDK MCP servers let custom tools run in the same Python...

anthropics· active
Swarms ★ 7.1k

Enterprise-grade multi-agent orchestration framework with 60+ prebuilt multi-agent architectures (sequential, concurrent, hierarchical). AutoSwarmBuilder...

kyegomez· active
Strands Agents SDK ★ 7.0k

Model-driven SDK taking a minimal-code approach to building agents. Model-agnostic (any model, any cloud; swap backends without code changes). Agent loop traces...

strands-agents· active
open-multi-agent ★ 6.8k

'Describe the goal, not the graph' — the coordinator agent builds the task DAG at runtime from the goal rather than hand-wiring workflow graphs. Controlled...

open-multi-agent· active
Agents ★ 6.0k

A data-centric, self-evolving autonomous language agent framework (Agents 2.0) that applies the connectionist learning procedure to agent training. Makes an...

aiwaves-cn· active
TrueForge ★ 4.8k

The runtime layer that turns an LLM into a working agent — model calls, MCP tools, skills, sandboxing, approvals, context management, and session state —...

truefoundry· active
Langroid ★ 4.1k

Intuitive, lightweight, extensible Python framework (from CMU/UW-Madison researchers) for building LLM-powered multi-agent applications. Agent-as-actor paradigm...

langroid· active
atmosphere ★ 3.8k

Real-time engine for AI agents on the JVM with deep-agent defaults (memory, plan, virtual filesystem, sub-agent delegation) and governance/compliance (OWASP...

Atmosphere· active
Claude Agent SDK (TypeScript) ★ 1.7k

Official Anthropic SDK that programmatically embeds Claude Code's agentic capabilities (codebase understanding, file editing, shell command execution, complex...

anthropics· active
sre ★ 1.3k

OS-level cloud-native runtime and SDK for production AI agents ('The Linux of AI Agents'). Unified Resource Abstraction — same API works across all providers...

SmythOS· active
IX ★ 1.0k

Platform for designing and deploying autonomous and semi-autonomous LLM-powered agents and workflows with a no-code visual agent editor for connecting nodes...

kreneskyp· active
Fantasy ★ 954

A unified Go library for building AI agents with a single API across many LLM providers and models, compiling to native machine code; built to power Charm's...

charmbracelet· active
OpenRath ★ 930

PyTorch-like runtime for dynamic multi-agent and multi-session workflows — Session as the central flowing value (like a Tensor); composable agents like...

Rath-Team· active
CodeFuse-muAgent ★ 774

Multi-agent framework driven by a Knowledge Graph (Eventic Knowledge Graph / EKG) engine rather than purely model-based or fixed-flow approaches. Successful...

codefuse-ai· active
WorkGPT ★ 731

Agent framework (AutoGPT/LangChain-style) that takes a directive and an array of APIs, then converses with AI until the directive is complete. Universal API...

team-openpm· dormant
LLama Cpp Agent ★ 656

Python framework for interacting with LLMs — chat, function calling, structured output, RAG, and agentic chains with tools. Key differentiator is guided...

Maximilian-Winter· dormant
yAgents ★ 592

First Langchain Agent creator designed to build, prototype, and deploy AI-powered agents with on-the-fly agent/tool creation, interactive CLI, session...

genlayerlabs· dormant
Vendo ★ 590

An embedded agent SDK for B2B SaaS that lets your end customers build their own features and micro-apps on top of your product: agents execute through the host...

runvendo· active
giselle ★ 554

Open source AI agent studio with visual drag-and-drop builder, multi-model composition (GPT/Claude/Gemini), GitHub AI Operations automation, and knowledge store...

giselles-ai· active
FastAgency ★ 547

Unified programming interface for deploying AG2 (AutoGen) multi-agent workflows to production; seamless OpenAPI integration with few lines of code; Tester class...

ag2ai· active
cersei ★ 443

"Reverse-engineered Rust port of Claude Code architecture as an embeddable SDK; graph memory (Grafeo) with 98us recall vs Claude Code's 7.5s LM call; 6MB...

pacifio· active
Streamship ★ 321

Python SDK for the Steamship platform to build, scale, and monitor AI Agents, with a triad of deployable components (Agents, Packages, Plugins)....

steamship-core· active
intentlang ★ 93

AI-Native, Intent-Oriented Programming Language built on Python; first framework to formally represent human intent as structured elements (Intent IR: Goal,...

l3yx· active
Bazed ★ 78

Sagentic.ai Agent Framework, a unified platform for building, running, and scaling autonomous agents. Features a dev server with hot reloading and spawning...

sagentic-ai· dormant
par ★ 67

Modular, type-safe agent runtime for building LLM-powered applications ('LangChain + LangGraph for OCaml'). Written in OCaml 5.4 using Eio structured...

jcz2020· active
Dippin ★ 24

DSL and toolchain for authoring AI pipeline workflows with first-class syntax for prompts, shell scripts, model config, branching logic, and node types (agent,...

2389-research· active
2389 Agent Protocol (Rust) ★ 2

Production-ready Rust implementation of the 2389 Agent Protocol — a standard for interoperable AI agents communicating via MQTT in distributed systems. Provides...

2389-research· active
Agentic-Platform

Was described as an AI Agent Automation Platform for rapidly prototyping, testing, and deploying Multi-Agent Systems from the browser. GitHub repo...

dormant
Agenticai

Was described as a framework for building autonomous decision-making agents integrating reinforcement learning, NLP, and multi-agent systems. GitHub repo...

dormant
Agents by Hugging Face

Experimental agent API in Hugging Face Transformers offering CodeAgent (one-shot code generation and execution) and ReactAgent (step-by-step ReAct with JSON or...

active
Deep Agents Code

Batteries-included agent harness built on LangGraph. Provides planning, file system access, context management, sub-agents with isolated context windows, shell...

langchain-ai· active
LangGraph

Low-level orchestration framework and runtime for long-running, stateful agents; combines deterministic and agentic steps in one graph; durable execution,...

active
Microsoft Agent Framework

The direct successor to both Semantic Kernel and AutoGen (created by the same teams), merging AutoGen's simple agent abstractions with Semantic Kernel's...

active
Microsoft Magentic-One

A generalist multi-agent system with a modular, plug-and-play design where agents can be added/removed without reworking the system. An Orchestrator leads four...

active
Mux (Rust) ★ 0

Agent SDK / agentic infrastructure library for Rust providing tool execution with structured input/output, MCP client integration, permission-gated approval...

2389-research· active
NVIDIA NeMo Agent Toolkit

Open-source library for connecting and optimizing teams of AI agents across any framework. Supports MCP as both client and server (FastMCP), a public Plugin...

NVIDIA· active
Public-Agent-Framwork

Tailored for IBM Granite and Llama 3.x models; offers a sandboxed code interpreter, OpenAI-compatible Assistants API, serialization for pausing/resuming complex...

aurasgit· dormant
Python-Agents

Despite the repo name 'python-agents', this is a TypeScript agent framework (Clarisse Agent Framework) optimized for IBM Granite and Llama 3.x models; includes...

clarisseIO· dormant
Tiny-Agent

A lightweight, minimal ReAct (Reasoning & Acting) AI agent framework described as 'like Eliza, but tinier, cleaner, and with way less clutter.' Emphasizes...

bombap· active