Agent Framework Open Source

Open-source library of 113 portable skills for coding agents, with an optional local Neo4j GraphRAG service ex…

A Claude Code harness that makes AI agents run discovery and weigh evidence before writing code. Forces agents…

Methodology and templates for building trustworthy, traceable AI data analyst agents with metrics-first approa…

AI-first Go CLI framework designed for AI agents to build production code correctly. Provides machine-checkabl…

Claude Code skill for generating and maintaining AGENTS.md files—a Markdown convention that guides AI coding a…

Claude Code plugin for spec-driven development. Manages requirement documents, tracks changes, and outputs spe…

Base template for Agent-Native Apps with pre-built dashboard UI, runtime bridge, and menu structure (secretary…

Generates customized AI Skills from proven methodologies for learning, design, and build projects. Includes fi…

.NET library for building Model Context Protocol (MCP) servers and clients. Enables AI assistants to discover …

Intuitive Python framework for multi-agent LLM apps from CMU and UW-Madison researchers. Set up agents with LL…

Framework providing guardrails, gates, and boundaries for autonomous AI coding agents. Integrates structural c…

Collection of reusable AI agent skills and CLI tools for Manus, Claude Code, Qodo, Cursor, and other AI coding…

Agent-native TypeScript framework for building MCP servers with declarative definitions, authentication, multi…

Go implementation of the Model Context Protocol (MCP) providing both client and server SDKs. Supports latest M…

Cloudflare Skills likely refers to a set of tools or capabilities provided by Cloudflare for building and depl…

An agent generative framework hosted on GitHub, facilitating the development and deployment of AI agents.

Composable, modular library for building AI agents. Bridges LLMs with tools via flexible reasoning loop; suppo…

Cross-platform agent ops framework adding state machines, decision logs, risk scoring, and tiered memory to AI…

Open-source Swift workspace for generative user interfaces. Agents produce declarative A2UI messages that clie…

Production-ready Next.js template for building AI agents with LangGraph.js. Includes MCP integration, human-in…

SAP toolkit for building, deploying, and connecting AI agents to SAP Joule via the A2A protocol on BTP Cloud F…

GitHub repository for experimenting with and developing AI agents. Community-driven project with active contri…

A GitHub repository likely associated with Jido, potentially related to agent development, AI research, or spe…

Claude Code skill that dissects AI skills into anatomy handbooks, documenting why they work, how they're built…

Python library for exposing Pydantic models as gRPC, ConnectRPC, and MCP services without protobuf files. Auto…

Battle-tested skill library for AI agents. Provides pre-written execution playbooks for crypto, PDFs, search, …

56 plug-and-play skills for OpenClaw AI agents: structured thinking, security guardrails, persistent memory, c…

Laravel package implementing the Model Context Protocol (MCP) for standardized AI model communication. Support…

Multi-agent framework family for AI-powered product development. Includes domain-specialized agents for produc…

GitHub template for AI-assisted development with structured SRS/PRD/task workflows. Integrates with AI agents …

A repository containing various autonomous agents, including examples for autonomous-agents. This project aims…

Framework for building effective AI agents using Model Context Protocol with composable patterns. Provides ful…

Git-native AI agent framework where agent identity, rules, memory, tools, and skills are version-controlled fi…

Framework for running parallel AI agent sessions in a single TUI panel with permission-aware tools, preflight …

Governance-driven AI development framework that enforces conventions, quality gates, and domain expertise for …

A filesystem-first framework for building durable AI agents. Organizes agent capabilities in conventional file…

Production-tested middleware that connects any LLM to OpenClaw framework. Enables integration of models like Q…

Rules and skills framework for Trae IDE agents. Provides 35 professional skills, 8 routing rules, dual-track m…

Lightweight AI agent framework for vertical domain applications. Provides out-of-box API service, domain knowl…

Sample custom industry AI agents built with SAP Joule Studio (no-code/low-code) and SAP Cloud SDK for AI. Incl…

Durable AI agent framework built on Inngest and pi-ai. Provides think/act/observe loops with automatic retries…

AI-native, intent-oriented programming language built on Python. Framework for intent-driven embedded AI progr…

Python framework implementing the Model Context Protocol (MCP) with client-server architecture. Integrates LLM…

Local-first desktop workspace for creating, versioning, comparing, and shipping AI Agent Skill assets. Cross-p…

Framework for managing software development lifecycle with AI agents. Combines structured SDLC phases with age…

Universal protocol and SDK suite enabling any application (C#, C++, Python, Node.js) to become AI-controllable…

Cross-platform AI agent harness for autonomous development cycles. Spec-driven, DAG-orchestrated orchestration…

Configuration framework for Claude Code that adds persistent memory, tool integrations, and autonomous workflo…

CLI + MCP server that unifies AI agent skills across multiple coding tools (Claude, Cursor, Gemini, Kimi, Code…

Open-source workflow framework for AI coding agents. Provides Markdown-based skills for architecture-first pla…

Records LLM agent behavior, identifies repeating patterns, and compiles them into verified WASM binaries that …

Go framework for building MCP servers with minimal boilerplate. Auto-generates JSON schemas from struct tags, …

Collection of reusable skills for Claude Code agents, including commit message generation, code review, prompt…

Collection of copy-paste prompts for deploying specialized autonomous AI agents that optimize, secure, and enh…

Terminal UI toolkit with 25+ React components and headless agent framework for building CLI apps and AI agents…

Multi-platform ACP client (VS Code, CLI, mobile) for connecting and switching between AI coding agents. Open-s…

MCP server implementing the Unified Cognitive Processing Framework for advanced reasoning, problem decompositi…

AutoGen is a flexible framework that enables developers to build applications with multiple AI agents that can…

Development framework for building production-ready AI agents with LangGraph. Grounds AI coding assistants in …

Governed skills for every AI agent your team runs. Curate one approved library of agent skills, distribute it …

C++ framework for building autonomous AI agents that run entirely on-device. Features multi-modal capabilities…

Open-source platform for building AI agents, data pipelines, and workflow automation. Unified no-code/pro-code…

Mastra is an open-source TypeScript and JavaScript framework for building, testing, and deploying AI agents an…

Open-source infrastructure for multi-agent AI systems. Provides shared memory, voice-to-text, and session logg…

[GitHub 186633⭐ topics=ai-agents, anthropic, claude, claude-code, developer-tools, llm, mcp, productivity] The…

Open source, self-hosted AI agent platform built on Elixir/OTP. Deploy with Docker, supports multiple LLM prov…

Open source framework for building stateful LLM applications with advanced reasoning and transparent long-term…

Full-stack TypeScript framework for building and deploying coding agents. Provides schema, policies, live quer…

LangChain provides the engineering platform and open source frameworks developers use to build, test, and depl…

Open-source React components and runtimes for building AI chat interfaces. Provides ChatGPT-style UIs, streami…

Open-source framework to extract a person into an AI agent through 8-week therapist-style interviews. Generate…

Local-first agent operating system running 19 LLMs, 145 tools, and 18 communication channels on your machine. …

[HN Show HN, 5 pts] Duralang – decorator makes every LangChain LLM/tool/MCP call a Temporal Activity

Build multimodal AI agents with memory, knowledge and tools. Simple, fast and model-agnostic agent framework.

AI Agent Platform with 100+ production-ready patterns, including agents, workflows, tools, chat UI, and market…

The TypeScript AI agent framework with assistants, RAG, and observability. Supports GPT-4, Claude, Gemini, Lla…

SDK and API platform enabling AI agents to take real-world actions (email, voice, commerce, research) with sig…

CP tools for builders shipping agentic services on Base.