Minimal AI coding agent (~950 Lines Python) inspired by Claude Code. Works with any LLM. Think nanoGPT for coding agents.

Switch between multiple Claude Code accounts

AI Session Memory with Think-Execute-Reflect Quality Loops — give your agent a brain that survives every session. Built on the Intelligent Distance principle.

One API for 20+ LLM providers, your databases, and your files — self-hosted, open-source AI gateway with RAG, voice, and guardrails.

Claude API Proxy platform - Seamlessly forward Claude Code requests to any OpenAI-compatible API service with smart model mapping, streaming support, deployed on Cloudflare Worker.

Run Hermes Agent and OpenClaw on the same WeChat account

AI Session Memory with Think-Execute-Reflect Quality Loops — give your agent a brain that survives every session. Built on the Intelligent Distance principle.

The Express.js for MCP Servers. Type-safe tools · Presenters that control what the LLM sees · Built-in PII redaction · Deploy once — every AI assistant connects.

A structured prompt pipeline that turns vague ideas into implementable RFCs — works with any AI assistant.

Knowledge Management for Humans and Agents

Turn your AI agent into a money-making machine. 50+ HYRVE API endpoints, job polling daemon, auto-accept mode. v1.6.2

Install Claude Code skills from GitHub with one command: uvx add-skill 🚀 Also works for slash commands and subagents 🤙