LLM agents as your hyperparameter optimizer.
Claude Code-style background agents for OpenCode – async delegation with context persistence

Open-source Agent Operating System
Turn your local files into a Wiki for your agents. Open-source and local-first.
The theory of LLM wikis, running as one. A framework for agent-operated knowledge: typed, linked, review-gated markdown your agents execute.

Agent Ops for your second brain - a 3D IDE for Obsidian built on Three.js. Visualize your vault as a code city, dispatch AI coding agents (Claude Code, Codex, Antigravity), post research quests, and watch your agent fleet work in real time.
Reusable Skills for LLMQuant Agent, Claude Code, Claude.ai, Cursor, Hermes Agent, OpenClaw and Codex, grounded in LLMQuant Data
Self-hosted agent OS with skills, workflows, MCP, and second brain storage.
Built from the ground-up for agents, Vessel Browser is an open source AI browser for Linux/Mac/Windows that provides a durable state, MCP control, and BYOK with full autonomous browsing. Use with Hermes Agent, OpenClaw, or connect to your favorite API provider.
OpenClaw Hermes AI Agent Social Network🦞💬🦞Built on Google 3D Maps and A2A protocol, connects OpenClaw and Hermes agents worldwide in a 3D environment.
Memory service, SDK, CLI, and plugins for agent recall and writeback.
AI Agent Skills built for Founders who hate Marketing
Build autonomous AI agents in Python.
Outworked - Cozy Office for Claude Code
A repository for skills that are essential to my daily work
Where AI agents hire AI agents — hiring and coordination infrastructure for the agent economy
🐬DeepChat - A smart assistant that connects powerful AI to your personal world
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.)
Autonomous AI backend for deep research AI applications.
A collection of AI agent skills for Hermes Agent — research, creative, productivity, devops, and more. Each skill is self-contained and tested.
A selective learning and memory substrate for agentic systems — typed, revisable, decayable memory with competence learning and trust-aware retrieval.
On-screen aware AI assistant for your desktop. Uses current app context, multiple LLMs, and MCP tools to help you act across apps.
GoClaw - GoClaw is OpenClaw rebuilt in Go — with multi-tenant isolation, 5-layer security, and native concurrency. Deploy AI agent teams at scale without compromising on safety.
YC (S26) | Open Computer History | Record your screen continuously locally and provide context to your agents (Claude, Codex, Openclaw, Hermes, Runner...)