Awesome AI Agent Stack

Agent Frameworks & Orchestration

Build your own agents and multi-agent systems.

Core frameworks

• langchain-ai/langgraph - Graph-based stateful agent orchestration; the default for production Python agents.
• langchain-ai/langchain - The original LLM application framework and integration ecosystem.
• pydantic/pydantic-ai - Type-safe agent framework from the Pydantic team; great for structured outputs.
• openai/openai-agents-python - OpenAI's lightweight multi-agent SDK with handoffs and guardrails.
• google/adk-python - Google's Agent Development Kit for Gemini and beyond.
• anthropics/anthropic-sdk-python - Official Claude SDK; tool use, streaming and the Agent SDK.
• crewAIInc/crewAI - Role-playing multi-agent crews with tasks and processes.
• microsoft/autogen - Conversational multi-agent framework from Microsoft Research.
• huggingface/smolagents - Minimal agents that write code as actions.
• run-llama/llama_index - Data framework for connecting LLMs to your data; strong agentic RAG.
• deepset-ai/haystack - Production-oriented pipelines for RAG and agents.
• stanfordnlp/dspy - Program, don't prompt: optimize prompts and weights declaratively.
• agno-agi/agno - Build, run, and manage agent platforms.
• langchain-ai/deepagents - The batteries-included agent harness.
• microsoft/agent-framework - Microsoft's framework for building, orchestrating and deploying agents.
• agentscope-ai/agentscope - Build agents you can see, understand and trust.
• microsoft/semantic-kernel - Microsoft's SDK for building LLM agents into .NET, Python, and Java apps.
• strands-agents/harness-sdk - AWS's official open-source agent SDK for Python and TypeScript, any model or cloud.
• ag2ai/ag2 - AG2 (formerly AutoGen): the open-source AgentOS for multi-agent applications.
• anthropics/claude-agent-sdk-python - Official Python SDK for building Claude-powered agents.
• i-am-bee/beeai-framework - Build production-ready AI agents in Python and TypeScript.
• Upsonic/Upsonic - Build autonomous AI agents in Python.
• Eigenwise/atomic-agents - Build AI agents atomically with modular, composable components.
• Forethought-Technologies/AutoChain - Build lightweight, extensible, and testable LLM agents.
• jackmpcollins/magentic - Seamlessly integrate LLMs as plain Python functions.
• Mirascope/mirascope - The LLM anti-framework: minimal abstractions over provider APIs.
• langroid/langroid - Harness LLMs with multi-agent programming in Python.
• SylphAI-Inc/AdalFlow - Library to build and auto-optimize LLM applications.
• The-Pocket/PocketFlow - 100-line LLM framework where agents can build agents.
• TencentCloudADP/youtu-agent - Simple agent framework built to work well with open-source models.
• evalstate/fast-agent - Build and evaluate agents with MCP, skills, ACP and A2A support.
• QwenLM/Qwen-Agent - Agent framework on Qwen with function calling, MCP, and code execution.
• microsoft/Agents-for-python - Microsoft 365 Agents SDK for Python.
• andrewyng/openworker - Andrew Ng's open agentic-worker framework.
• lastmile-ai/mcp-agent - Build effective agents with Model Context Protocol and simple workflows.
• emcie-co/parlant - Interaction control harness for building reliable customer-facing agents.
• RasaHQ/rasa - Open-source machine learning framework for text and voice assistants.
• aurelio-labs/semantic-router - Superfast semantic decision-making for routing between agents and tools.
• humanlayer/humanlayer - Human-in-the-loop layer so coding agents solve hard problems safely.
• griptape-ai/griptape - Modular Python framework for AI agents and workflows with chain-of-thought reasoning, tools, and memory.
• PrefectHQ/marvin - Ambient intelligence library for agentic data workflows.
• modelscope/ms-agent - MS-Agent: a lightweight framework to empower agentic execution of complex tasks.

TypeScript & JavaScript frameworks

• mastra-ai/mastra - Mastra is the modern TypeScript framework for AI-powered applications and agents.
• genkit-ai/genkit - Google's open-source framework for agentic apps in JS, Go, Python, and Dart.
• elizaOS/eliza - TypeScript framework for autonomous agents across chat, social, and on-chain integrations.
• anthropics/anthropic-sdk-typescript - Official TypeScript SDK for Anthropic APIs and agent tooling.
• anthropics/claude-agent-sdk-typescript - Official TypeScript SDK for building Claude-powered agents.
• google/adk-js - Google's open-source, code-first TypeScript toolkit for building agents.
• inngest/agent-kit - Build multi-agent networks in TypeScript with deterministic routing.
• kaiban-ai/KaibanJS - JavaScript-native framework for building multi-agent teams.
• langchain-ai/langchainjs - The agent engineering platform for JavaScript and TypeScript.
• openai/openai-agents-js - Lightweight framework for multi-agent workflows and voice agents.
• VoltAgent/voltagent - AI agent engineering platform on open-source TypeScript.
• vercel/eve - The open framework for building agents.
• withastro/flue - The sandbox agent framework.
• open-multi-agent/open-multi-agent - Self-hosted TypeScript agent runtime with durable approvals and run records.
• cloudflare/agents - Build and deploy AI agents on Cloudflare's edge network.
• daydreamsai/daydreams - TypeScript toolkit for building commerce-focused AI agents.
• bradygaster/squad - AI agent teams for any project, in TypeScript.

Go, Java, Rust, Ruby & other languages

• 0xPlaygrounds/rig - Modular Rust library for building scalable LLM-powered applications.
• agenticenv/agent-sdk-go - Durable execution framework for AI agents in Go.
• agentscope-ai/agentscope-java - Build distributed, production-grade, long-running agents in Java.
• aixgo-dev/aixgo - AI-native agent framework for Go.
• BoxcarsAI/boxcars - Composable Ruby framework for building applications with LLMs.
• cloudwego/eino - ByteDance's Go framework for LLM/AI application development.
• embabel/embabel-agent - JVM agent framework for predictable, enterprise-grade agents.
• geminik23/ai-agents - Declarative Rust agent framework: one YAML defines any agent.
• google/adk-go - Google's open-source, code-first Go toolkit for building agents.
• google/adk-java - Google's open-source, code-first Java toolkit for building agents.
• JetBrains/koog - JVM framework for predictable, fault-tolerant, enterprise agents.
• langchain4j/langchain4j - Idiomatic Java library for building LLM applications.
• LLPhant/LLPhant - Comprehensive PHP generative AI framework with agent support.
• patterns-ai-core/langchainrb - Build LLM-powered applications in Ruby.
• prism-php/prism - Unified interface for working with LLMs in Laravel.
• rhgs/crewai-go - Idiomatic Go port of CrewAI for collaborative autonomous agents.
• Shopify/roast - Structured AI workflows made easy in Ruby.
• spring-projects/spring-ai - Application framework for AI engineering on Spring.
• tmc/langchaingo - LangChain for Go: the easiest way to write LLM programs in Go.
• crmne/ruby_llm - Ruby-native AI framework for chat, agents, tools and media through one API.
• agentjido/jido - Autonomous, distributed agent framework for Elixir.
• trpc-group/trpc-agent-go - Go framework for production agents with graph workflows, tools and memory.
• alibaba/spring-ai-alibaba - Agentic AI framework for Java developers.
• 11fsociety/encom - Open-source AI agent framework; single-binary Rust daemon with TypeScript skills.
• thClaws/thClaws - Open-source AI agent harness in native Rust: GUI, CLI, and headless.

Multi-agent systems

• bytedance/deer-flow - An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the.
• OpenBMB/ChatDev - ChatDev 2.0: Dev All through LLM-powered Multi-Agent Collaboration.
• FoundationAgents/MetaGPT - The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming.
• 2FastLabs/agent-squad - Flexible framework for managing multiple AI agents and complex conversations.
• camel-ai/camel - Pioneering multi-agent framework for role-playing autonomous agents.
• camel-ai/owl - Optimized workforce learning for general multi-agent assistance.
• FoundationAgents/OpenManus - Open-source generalist multi-agent framework.
• HKUDS/ClawTeam - Agent swarm intelligence with one-command full automation.
• kyegomez/swarms - Enterprise-grade multi-agent orchestration framework.
• openai/swarm - Educational framework for ergonomic, lightweight multi-agent orchestration.
• VRSEN/agency-swarm - Reliable multi-agent orchestration framework.
• OpenBMB/IoA - Open framework for collaborative AI agents across organizations.
• openagents-org/openagents - The collaboration OS for AI agents.
• multica-ai/multica - Make humans and AI agents work as one team; open-source and self-hostable.
• MervinPraison/PraisonAI - Multi-agent framework for building always-on AI workforces.
• yyyy231209/ai-company-framework - Open-source multi-agent orchestration for running an AI company.
• Zerone-Laboratories/RIGEL - Multi-agentic AI assistant and builder.
• NeuroLift-Technologies/nlt-otoi - Multi-agent orchestration with user-defined terms of interaction.
• sipyourdrink-ltd/bernstein - Declarative governance and orchestration framework for AI agents.
• GammaLabTechnologies/harmonist - Portable agent orchestration with mechanical protocol enforcement.
• block/buzz - Hive-mind communication platform for coordinating agent swarms.
• aden-hive/hive - Multi-agent harness for production AI workloads.
• ruvnet/ruflo - Agent harness for deploying multi-player swarms and autonomous workflows.
• cft0808/edict - OpenClaw multi-agent orchestration with nine specialized agents and dashboard.
• CelestoAI/agentor - Open-source Claude managed-agents platform for building agent teams.
• compozy/compozy - Operating system for AI agents that plugs into your existing agent CLIs.
• GoogleCloudPlatform/scion - Open orchestration platform for teams of AI agents and their people.
• Runfusion/Fusion - Software factory: multi-node agents building software around the clock.
• phodal/routa - Workspace-first multi-agent coordination with shared specs and Kanban.
• hfadhlullah/kaizen - Agents show the plan first, then a second agent reviews the work.
• paperclipai/paperclip - The open-source app everyone uses to manage agents at work.
• zhayujie/CowAgent - Open-source super AI assistant and self-evolving agent harness.
• openakita/openakita - Open-source AI assistant framework with skills and agent architecture.
• TokenRhythm/opensquilla - Token-efficient AI agent with higher intelligence density per budget.

Visual & low-code builders

• langgenius/dify - Visual builder for agentic workflows and RAG pipelines with a rich tool ecosystem.
• langflow-ai/langflow - Drag-and-drop builder for LangChain flows and agents.
• inkeep/agents - Build agents in a visual builder or TypeScript SDK with two-way sync.
• botpress/botpress - Open-source hub to build and deploy GPT/LLM agents.
• dust-tt/dust - Custom AI agent platform to speed up knowledge work.
• i-am-bee/agentstack - Deploy and share agents on open infrastructure, free from vendor lock-in.
• paradigmxyz/centaur - Frontier agentic infrastructure you own; open-source agent cloud.

Agent protocols & interoperability

• a2aproject/a2a-js - Official JavaScript SDK for the Agent2Agent (A2A) protocol.
• a2aproject/a2a-python - Official Python SDK for the Agent2Agent (A2A) protocol.
• a2aproject/a2a-go - Official Go SDK for the Agent2Agent (A2A) interoperability protocol.
• agent-network-protocol/AgentNetworkProtocol - Open protocol for agent communication, discovery, and identity.
• agntcy/dir - Distributed announce and discovery service for multi-agent systems.
• agntcy/oasf - Open Agentic Schema Framework for interoperable agent definitions.
• Coral-Protocol/coral-server - CoralOS: registry, runtime, and payments between your agents and production.
• fetchai/uAgents - Fast, lightweight framework for decentralized autonomous agents.
• google-agentic-commerce/AP2 - Google's open protocol for secure, interoperable agent payments.
• projnanda/adapter - SDK for building agents on MIT's NANDA Internet-of-Agents network.
• valory-xyz/open-autonomy - Framework for creating autonomous agent services.
• a2aproject/A2A - Agent2Agent (A2A) is an open protocol enabling communication and interoperability between opaque agentic applications.

Durable execution & background agents

• temporalio/temporal - Durable workflow engine; the right way to run long-lived agents that must survive crashes.
• inngest/inngest - Event-driven durable functions with first-class AI step support.
• conductor-oss/conductor - Conductor is an event driven agentic workflow engine providing durable and highly resilient execution engine for applications and AI Agents.
• julep-ai/julep - Durable, composable AI agents with crash-and-resume flows.
• loopx-project/loopx - Control plane with durable state kernel for long-horizon agents.
• restatedev/restate - Resilient applications with durable workflows that tolerate any failure.
• ThousandBirdsInc/chidori - Agent framework where every run is durable, replayable and resumable.

Azure AI Foundry

• Azure-Samples/get-started-with-ai-agents - Deploy an agent web app with Azure AI Foundry.
• jonathanscholtes/azure-ai-foundry-agentic-workshop - Hands-on Foundry agent workshop.
• Azure-Samples/app-service-agentic-langgraph-foundry-python - LangGraph + Foundry agents on App Service.
• MSFT-Innovation-Hub-India/LangGraph-Foundry-HostedAgent-TravelAgent - Multi-agent customer support as a hosted Foundry agent.
• scholarly360/From-Zero-to-Microsoft-Foundry-Creating-Agents-Via-AI-Projects-Library - Agents via the Azure AI Projects SDK.