Open-source observability & evaluation platform for AI agents and coding agents. Trace LLMs, tools, prompts, costs & agent workflows with OpenTelemetry.

Open-World Self-Evolution for LLM Agents — agents that build both their skills and their own verification signals from scratch, with no target-task supervision. (Code coming soon.)

Local first, desktop companion platform with animated pets, plugin SDK and coding-agent integrations.

Complete AI Agent System for OpenClaw — memory, self-healing, self-improvement, voice, automation

👾 Open Computer Use – Open-Source Alternative to Codex Computer Use

OpenJudge: A Unified Framework for Holistic Evaluation and Quality Rewards

Agent-SDK without CLI dependencies, as an alternative to claude-agent-sdk, completely open source

OpenSpec Plus — Agentic skills that enhance OpenSpec's Spec-Driven Development through better discovery, requirements, design decisions, execution planning and execution. Works with Claude Code, OpenCode, Github Copilot and any other AI coding agents

MCP server for OpenCode AI — 70 tools, 10 resources, 5 prompts. Use npx opencode-mcp with Claude Desktop, Claude Code, Cursor, Windsurf, or any MCP client.

A free, open-source coding agent inside VS Code.

TypeScript multi-agent framework that runs in your own environment: consequential actions wait for approval and every run leaves a verifiable record. Describe the goal, not the graph. 13 built-in providers (Claude, OpenAI, Gemini, DeepSeek and more) plus any OpenAI-compatible endpoint, local models included.

Nightly Claude Code CLI Decompile — Reverse Engineered & Rebuilt

Agentic game development taken to the next level: plan, build and test across major engines with any coding agent🤖

OpenSwarm — Autonomous AI dev team orchestrator powered by Claude Code CLI. Discord control, Linear integration, cognitive memory.

MCP server that gives any LLM its own computer — managed Docker workspaces with live browser, terminal, code execution, document skills, and autonomous sub-agents. Self-hosted, open-source, pluggable into any model.

Multi-Agent works on native GUI desktop. Supports skills and IM channel, build-in a IDE for light development. Built on the shared piscis-engine kernel.

Control 1 or more machines using computer use tools that integrates with your agents

Multi-agent harness that runs Claude Code and Codex together as one system

Mention any ACP coding agent from Slack, GitHub, GitLab, Linear, or Lark. OpenTag runs Claude Code, Codex, Cursor and more on your own machine, then replies in-thread with verified, evidence-backed results.

OpenGUI is an Android GUI agent framework for phone-use AI that can see, plan, and operate real mobile apps through the GUI.

OpenBrowser is a framework for intelligent browser automation. It combines direct CDP communication with a CodeAgent architecture, where the LLM writes Python code executed in a persistent namespace, to navigate, interact with, and extract information from web pages autonomously.

Deterministic, local-first memory and guardrails for AI coding agents with no LLM in the hot path.

Crabbox: warm a box, sync the diff, run the suite.

Open-source, desktop client/UI build to harness Claude Code, Codex and any other Agent accepting Agent Client Protocol. Run multiple AI coding agents side by side with rich tool visualization, MCP integrations, built-in terminal, git, browser and just about anything else you may need.