OpenCode
Open-source AI coding agent that connects to 75+ AI providers and runs in your terminal, IDE, or desktop with LSP integration and multi-session support.
OpenAgent.bot
Open-source AI agents, models, skills, and memory systems directory.
Find, compare, and evaluate self-hostable AI tools. Browse open-source AI agents, open models, reusable skills, memory systems, plugins, bots, and developer tools with official sources, license info, and practical evaluations — all in one place.
Agents
Open-source agents for browser, coding, terminal, and workflow automation.
Gemini CLI
Open-source AI agent from Google that brings Gemini models into the terminal with file operations, shell commands, and Google Search grounding.
browser-use
Open-source browser automation agent framework that makes websites accessible to AI agents.
Codex CLI
Lightweight coding agent from OpenAI that runs locally in your terminal, built in Rust, works with ChatGPT plans or API keys.
OpenHands
Open-source AI software development agent for coding tasks, repositories, and developer workflows.
crawl4ai
Open-source LLM-friendly web crawler and scraper for extracting clean, structured content from any website.
Cline
Open-source autonomous coding agent for VS Code that creates and edits files, executes commands, and uses a browser — all with human approval at every step.
AutoGen
Multi-agent AI framework from Microsoft Research for building conversational agent systems with AgentChat, Core API, and Extensions.
Open Design
Local-first open-source design agent for prototypes, decks, dashboards, images, video, and agent-driven design systems.
ruflo
Open-source agent meta-harness for orchestrating multi-agent swarms with Claude, adaptive memory, and RAG integration.
CrewAI
Multi-agent orchestration framework where role-playing autonomous AI agents collaborate to execute complex workflows.
Aider
AI pair programming in your terminal that maps your codebase, auto-commits to git, and works with 100+ languages and any LLM provider.
Goose
Open-source AI agent from Block (now Linux Foundation) that automates engineering tasks via CLI and desktop app, with native MCP integration and any-LLM support.
Odysseus
Self-hosted AI workspace for chat, autonomous agents, deep research, email, documents, and more — local-first, privacy-first, no telemetry.
Tabby
Self-hosted AI coding assistant with code completion, chat, and agent capabilities that runs entirely on your infrastructure.
Continue
Open-source AI code agent for VS Code and JetBrains that combines chat, edit, agent, and autocomplete modes with source-controlled AI checks enforceable in CI.
OpenAI Agents SDK
Lightweight Python framework for building multi-agent workflows with handoffs, tools, tracing, and guardrails.
Kilo Code
Open-source AI coding agent for VS Code, JetBrains, and CLI with 500+ models, specialized modes, and cloud agent deployment.
SWE-agent
Autonomous coding agent that takes GitHub issues and fixes them using LLMs, achieving state-of-the-art results on SWE-bench.
PilotDeck
Open-source agent operating system with WorkSpace isolation, white-box memory, smart routing, and always-on execution.
Hermes Agent
MIT-licensed self-improving agent from Nous Research with persistent memory, skills, and always-on workflow channels.
LangGraph
Framework for building long-running, stateful agents with controllable workflows.
OpenClaw
Open-source agent platform for browser, tool, and workflow automation that actually takes actions.
smolagents
Lightweight Hugging Face library for agents that reason and act through code.
Claude Code
Agentic coding tool from Anthropic that lives in your terminal, understands codebases, and handles complex development tasks through natural language.
Codebuff
Terminal-native AI coding agent that understands your entire codebase and makes precise, style-consistent edits from natural language instructions.
Argent
Agentic toolkit that gives AI assistants direct access to iOS Simulators and Android Emulators.
Models
Open models that can power private, local, and self-hosted AI workflows.
DeepSeek-R1
Open reasoning model family for developers testing long-form reasoning, coding, and local AI workflows.
gpt4all
Run large language models locally on consumer hardware with a desktop application and Python library.
OLMo 2
Fully open language model family from AI2 for transparent research, training, and evaluation.
DeepSeek V4
Open DeepSeek V4 model family for million-token context, coding, reasoning, and agent workflows.
Gemma 4
Google DeepMind's open model family for local, multimodal, and agentic AI workflows.
Gemma 4 12B
Google DeepMind's 12B open multimodal model for local agentic workflows on laptops.
GLM-5
Open model line from Z.ai focused on agentic engineering and longer coding workflows.
GLM-OCR
Open OCR model and pipeline for turning complex document images into usable text.
Mistral Small 3.2
Apache-licensed small open model for practical instruction following, local inference, and agent experiments.
Qwen3-VL
Open vision-language model family for images, screens, documents, and multimodal workflows.
Qwen3.6
Qwen's open model line focused on stronger coding, agentic tasks, and real-world stability.
Kimi K2.5
Moonshot AI's open-weight multimodal model for agentic and tool-using workflows.
Skills
Reusable capability packs that make agents useful in real tasks.
ECC
Agent harness for Claude Code, Codex, Opencode, Cursor, and other coding agents focused on performance, memory, and security.
Antigravity Awesome Skills
Large installable library of agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, and Antigravity.
Marketing Skills
Reusable marketing skill pack for Claude Code and other coding agents handling growth, positioning, and content workflows.
Scientific Agent Skills
Open-source ready-to-use agent skills for research, science, engineering, analysis, finance, and writing.
Anthropic Cybersecurity Skills
Cybersecurity skill collection for AI agents mapped to MITRE, NIST, and practical security workflows.
Skill Seekers
Tooling that converts docs, GitHub repositories, and PDFs into Claude AI skills.
Hugging Face Skills
Open-source skill collection that gives agents reusable access to Hugging Face ecosystem capabilities.
HTML Anything
Agentic HTML editor and skill system spanning many surfaces for UI generation and content transformation.
SkillOpt
Microsoft research project for optimizing reusable natural-language skills for frozen LLM agents.
Awesome Finance Skills
Finance-focused agent skills for research, analysis, and financial workflow automation.
GudaStudio Skills
Reusable Agent Skills collection from GudaStudio for agent workflows and task automation.
SEO GEO Claude Skills
SEO and generative-engine-optimization skill pack for Claude Code, Cursor, Codex, and related coding agents.
CC Skills Golang
Golang-focused agent skill pack for Claude Code and compatible coding-agent workflows.
Browser Act Skills
Browser automation CLI and skill set built for AI agents that need repeatable web actions.
Agent Rules Books
AGENTS.md rules and skills distilled from classic engineering books such as Clean Code, DDD, and DDIA.
Agent Skill Creator
Workflow for turning repeated procedures into reusable AI agent skills across multiple tools.
Awesome Design Skills
Curated collection of DESIGN.md and SKILL.md files for design-oriented AI agents.
MDA
Markdown superset that compiles agent-facing documents such as SKILL.md, AGENTS.md, MCP-SERVER.md, and CLAUDE.md.
OK Skills
Curated AI coding-agent skills and AGENTS.md playbooks for repeatable development workflows.
MagicSkills
Composable SKILL.md folders for reusable agent capabilities.
Agnix
Linter and language-server tooling for CLAUDE.md, AGENTS.md, SKILL.md, hooks, and MCP project files.
Robotics Agent Skills
Reusable robotics agent skills for ROS1, ROS2, and embodied AI development workflows.
HTML Video
Agent skill pack for generating HTML videos with liquid backgrounds, VFX overlays, and cinematic hero animations using local AI coding agents.
Letta Skills
Shared skills repository for Letta Code, Claude Code, Codex CLI, and other coding agents.
Security Skills for Claude Code
Security-focused skills, plugins, and automation pipelines for Claude Code review and hardening workflows.
Agentic Commerce Skills
Open skills and plugins for agentic commerce protocols, checkout, and ecommerce workflows.
AI Agents Skills
Curated open repository of specialized skills for coding agents and AI assistants.
GBrain
Open context and memory layer for giving agents a more durable project brain.
GStack
Open agent skill stack for planning, browsing, QA, shipping, and product workflows.
React Native Agent Skills
React Native-focused skills for helping coding agents work on mobile app projects.
Bots
Open-source AI bots for Discord, Telegram, Slack, WhatsApp, Matrix, WeChat, and self-hosted agent channels.
AstrBot
Multi-platform AI agent assistant framework for IM platforms, LLMs, plugins, and AI features.
Genesis
Universal physics engine and simulation platform for robotics and embodied AI at 430,000x real-time speed.
Kirara AI
DIY multimodal AI chatbot connecting WeChat, QQ, Telegram, and other chat platforms with DeepSeek, Claude, Ollama, Gemini, and OpenAI.
LangBot
Production-grade platform for building agentic IM bots across Discord, Slack, Telegram, LINE, WeChat, Feishu, DingTalk, and more.
NVIDIA Isaac GR00T
Open foundation model for generalist humanoid robots — VLA with real-time whole-body control.
RLinf
Production-grade reinforcement learning infrastructure for embodied and agentic AI.
Openaibot
Out-of-box ChatGPT-style bot framework for Discord, Slack, Kook, and Telegram with ToolCall and plugin support.
MuseBot
Multi-platform LLM bot supporting Telegram, Discord, Slack, Lark, DingTalk, WeChat, QQ, image generation, and video creation.
Python WhatsApp Bot
Pure Python reference project for building AI WhatsApp bots.
TeleChat
AI Telegram bot with web search, image generation, Groq, Gemini, Claude, and OpenAI model support.
llmcord
Discord frontend for LLMs that supports OpenAI-compatible APIs including Ollama, Gemini, xAI, and OpenRouter.
OpenEAI
Complete open-source hardware-software platform for real-world embodied AI from arm to VLA policy.
wandbot
Technical support bot for Weights & Biases developer tools that can run in Discord, Slack, ChatGPT, and Zendesk.
AIRA
3D-printable 7-DoF robotic arm with native LeRobot integration for ACT, Diffusion, PI0, and GR00T.
Discollama
AI-powered Discord bot designed to run from a local machine with local or hosted LLMs.
GPT-Shell
Open-source Discord AI companion with ChatGPT-style conversations and image generation, evolved into Erin.
Telegram LLM Bot
Telegram LLM bot backed by OpenAI, Whisper, Beam, LLaMA, Weaviate, MinIO, and MongoDB.
ccpoke
Bridge between AI coding agents and your phone with notifications, two-way chat, and permission handling.
Telegram AI Agent
Generic Claude and Codex Telegram bot runtime for controlling coding agents from chat.
Chibi
Self-hosted Telegram companion orchestrating multiple AI providers with autonomous agent capabilities, MCP integrations, and async tasks.
opensoul
Self-hosted AI companion agent across 30+ messaging channels for everyday conversation and complex tasks.
LeLab
A web UI for training and running real-world robotics policies from Hugging Face LeRobot.
Synapse OSS
Self-hosted AI assistant with hybrid memory, evolving personality, and multi-channel support across WhatsApp, Telegram, Discord, and Slack.
Zulip MCP
Run AI agents in Zulip as mentionable bots, or wire Zulip into MCP-compatible clients.
Comis
Self-hosted AI agent teams inside messaging apps.
FamClaw
Self-hosted family AI gateway with parental controls for Telegram, Discord, and web, designed for homelab and local/cloud LLM use.
Matrix Comms
Run an AI agent such as Claude or another LLM as a Matrix bot with streaming, sessions, room history, and error recovery.
Super Homunculus Bot
AI-powered multi-platform chat assistant using Claude Agent SDK across Telegram and Discord.
Memory Systems
Open memory systems for retrieval, long-term context, and user-owned knowledge.
ragflow
Open-source Retrieval-Augmented Generation engine that combines deep document understanding with agent capabilities.
CowAgent
Open-source AI assistant with multi-model support, task planning, tool execution, and persistent memory.
haystack
Open-source AI orchestration framework for building production-ready LLM applications with modular pipelines and RAG.
Cognee
Open-source memory and data infrastructure for AI applications that need reliable context.
Graphiti
Temporal knowledge graph memory system for agents that need facts, entities, and time-aware context.
Letta
Platform for stateful agents with advanced memory, personalization, and learning over time.
Mem0
Open-source memory layer for AI agents and assistants that need personalized recall.
Memori
Open-source memory engine for LLM apps and agents that need persistent context injection.
Evaluations
Evaluations
Decision guides for choosing tools by workflow, license, and operational risk.
Decision matrix Choose an open-source AI agent by workflow
Start with the work surface: browser, repository, local desktop, orchestration, or memory-heavy workflows.
Comparison OpenClaw vs browser-use vs OpenHandsCompare action-agent platforms, browser automation primitives, and coding agents by practical adoption risk.
Buyer guide Best open-source browser agentsA search-friendly shortlist for teams testing agents that operate real websites.
Guides
Guides
Practical comparisons and explainers around the open agent stack.
2026-06-03 Local LLM Tool Calling Benchmark: Why 27B Models Beat 397B at Real-World Agent Tasks
ToolCall-15 reveals the surprising truth about local LLM tool calling — Qwen3.5-27B scored a perfect 15/15 while 397B models failed. Learn why mid-size dense models dominate tool calling and how to benchmark your own models.
2026-06-03 Open Design Evaluation: Is This Open-Source Claude Design Alternative Ready?A practical evaluation of Open Design as an open-source Claude Design alternative and agent-era Figma alternative, with strengths, risks, community feedback, and adoption guidance.
2026-06-03 Open Design Guide: Design Systems, Skills, Plugins, and Better AI PrototypesLearn how Open Design uses design systems, skills, plugins, and artifact previews to make AI-generated prototypes more consistent, useful, and exportable.
2026-06-03 Open Design Quickstart: Run the AI Design Agent with Codex, Claude Code, Cursor, or OpenCodeA practical Open Design setup guide for developers who want to run the open-source AI design agent locally, connect coding agents, and generate the first prototype safely.
2026-06-03 OpenHands vs AutoGen vs CrewAI: Which Open-Source Agent Framework Fits Your Workflow?A practical comparison of OpenHands (code-first autonomous agent), AutoGen (multi-agent conversations), and CrewAI (role-based team orchestration).
2026-06-03 What Is Open Design? The Open-Source AI Design Agent ExplainedOpen Design is a local-first open-source design agent that turns coding agents, design systems, skills, and plugins into exportable prototypes, decks, dashboards, images, and videos.