LLM agents as your hyperparameter optimizer.

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.

🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.

MCPify is an AI enablement compiler that transforms existing applications into AI-native, agent-operable systems.

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.

Measure token savings per AI coding agent, optimize context, and share a live local knowledge graph across 16 CLI clients.

Self-hosted agent OS with skills, workflows, MCP, and second brain storage.

🪈 Intelligent orchestration system that coordinates multiple AI coding assistants (Claude, Codex, Gemini CLI, Copilot CLI) to collaborate on complex software development tasks via REPL or a Vue/Nuxt UI dashboard. Also includes an Agentic Team runtime with role-based multi-agent open communication & lead-gated final responses.

The Rust SDK for building coding agents. Tools, streaming, graph, sub-agent orchestration, MCP — as composable functions

Open-source local workbench for multi-agent software development.

A repository for skills that are essential to my daily work

✨ AI Coding, Vim Style

Evaluate agent skill quality. Find the weakest link. Fix it. Prove it worked.

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.)

A collection of AI agent skills for Hermes Agent — research, creative, productivity, devops, and more. Each skill is self-contained and tested.

Monitor all your coding agents from one terminal - Claude Code, Cursor, OpenCode, pi and more

BootAgent is a local management tool of AI agents. It turns a fresh machine into a usable, repeatable setup without asking you to edit several tool-specific config files by hand.

AI-powered multi-agent code review. Simulates a customizable team of Engineers performing code review with built-in discourse.

Migrate coding agent sessions across 18 harnesses (Claude Code, Codex, Pi, OpenCode, Copilot, Antigravity, Vibe, Muse, Qwen, Kimi, Cursor, etc.)

Self-hosted control plane for AI agents: dispatch tasks, review runs, track spend, and operate OpenClaw, Claude Code, Codex, and other runtimes.

Multi-harness agentic plugin marketplace for Claude Code, Codex, Cursor, OpenCode, GitHub Copilot, and Google Antigravity

YC (S26) | Open Computer History | Record your screen continuously locally and provide context to your agents (Claude, Codex, Openclaw, Hermes, Runner...)