Own your AI. The native macOS harness for AI agents -- any model, persistent memory, autonomous execution, cryptographic identity. Built in Swift. Fully offline. Open source.
Multi-agent AI orchestration platform for automation, workflows, and developer tools. Golutra transforms Codex, Claude Code, and OpenClaw into a unified agent system with parallel execution, task orchestration, long-running workflows, and AI productivity workspace.
All in one plugin for Hermes Agent β the coding intelligence, a long-term memory system and model optimized workflow packages
AI Agent Engineering Platform built on an Open Source TypeScript AI Agent Framework
Open-source, local-first desktop AI research workbench for scientific computing with Python/R, MCP bioinformatics tools, SSH/WSL/GPU runtimes, and OpenAI/Anthropic models.
The living ecosystem where AI agents complete tasks through workflow loops, improve through iterative execution, are evaluated by mentor agents or humans in the loop, and turn completed work into reusable work experience and data to improve future agents.
π°οΈ Track token usage across AI coding agents from your terminal. π Global leaderboard with trillions of tokens tracked.
Give coding agents a disposable Linux VM, not your laptop
The missing DevTools for Claude Code β inspect session logs, tool calls, token usage, subagents, and context window in a visual UI. Free, open source.
162 production-ready AI agent templates for OpenClaw. SOUL.md configs across 19 categories. Submit yours!
An agent skill for evidence-based mouse sensitivity tuning, cross-game conversion, and gameplay review. Works with Codex, Claude Code, and Agent Skills hosts.
GoClaw - GoClaw is OpenClaw rebuilt in Go β with multi-tenant isolation, 5-layer security, and native concurrency. Deploy AI agent teams at scale without compromising on safety.
secure multiplexed execution paths for agents - zero trust, zero setup, zero latency.
The agent IDE that builds itself
Observability and enforcement for AI agent harnesses. Capture every run and runtime reliability with policy enforcement. 40 built-in policies, a local dashboard, no account required with a generous free cloud plan
Open Source version of Claude Cowork with 500+ SaaS app integrations

The fullstack MCP framework to develop MCP Apps for ChatGPT / Claude & MCP Servers for AI Agents.
Agent Skills that turn novels into source-grounded, fully playable games for Claude Code, Codex, and Kimi Code(K3).

Real-time Claude Code usage monitor with predictions and warnings
Agent-SDK without CLI dependencies, as an alternative to claude-agent-sdk, completely open source
LLM agents as your hyperparameter optimizer.
See what Claude Code and Codex actually send to the API β and what each part costs.
π¨ Open-source AI slide studio inside Codex: image-native decks, every slide a full visual canvas. β‘ 10+ high-quality slides in ~4β5 minutes β Fast mode renders every page in parallel. π Watch the whole chain live: research β outline β style β render β edit β present β export PDF/PPTX. π₯οΈ Browser-first Β· zero API keys Β· durable projects.
Portable AI agent orchestration with mechanical protocol enforcement. 186 agents, zero runtime dependencies.