Claude Desktop インストールガイド
ローカル MCP 設定に対応するデスクトップクライアント。
MCP Servers
Опубликовано на Infostart: https://infostart.ru/1c/tools/2720241/
A progressive AI Agent Harness tutorial written in Rust.
Installing MCPs is a huge pain, so I made a CLI tool to make it easier.
Knowledge graph + MCP tool server for LLM agents with hybrid retrieval, live DB sync, Korean FTS, and memory feedback.
A starting point for Claude Code to Codex collaboration
IDE-style navigation for structured data — code, JSON, YAML. Jump to definitions, find callers, follow references. Available as an MCP server or a mounted folder.
- — MCP Protocol v2 (spec revision 2026-07-28, streamable HTTP) and experimental StrongDM API support are here — see the release notes.
Local-first memory layer for CLI agents. Indexes Claude Code, Codex CLI, and Cursor session histories into SQLite + FTS5 — searchable from a CLI, TUI, or MCP server so your next agent session can...
Agent-managed GitHub merge queue for Codex, Claude Code, Cursor, and MCP clients
Self-hosted audit trail for AI agents — one command or one dashboard click from any step back to root cause.
Every local AI coding session in one tab: Claude Code, Codex and OpenCode in a single list, with a queue you can schedule and isolated Claude Desktop instances kept apart. Local, private, MCP-native.
Testing and evaluation platform to chat, inspect, and debug MCP servers, MCP apps, and ChatGPT apps.
Agent Skills
This repository contains hands-on tutorials for learning LangChain, LangGraph, and Deep Agents, organized into two learning tracks:
A growing collection of design skills for AI coding tools — Claude Code, Cursor, Codex, Windsurf, and anything else that reads a markdown rules file.
Honey (I Shrunk the AI) by GreenPT is a cross-tool coding skill that cuts AI coding-agent token usage and LLM API costs — making agents emit less code and less prose without losing correctness.
A reusable skeleton for an built on Hermes: a fleet of agents that items from sources, them, them against a rubric, them in parallel, each to a fulfillment path, pauses at , then — all coordinated on...
A Claude Code skill for maintaining and optimizing OpenClaw workspace files — the markdown files that form an AI agent's soul, memory, and operating procedures.
A framework for AI-First development with Claude Code and Codex. One methodology, two compatible runtimes.
Fourth girlfriend voting in progress - please vote on Issues.
终端里起多个会话并行干活、互相通信；长任务跑着的时候人走开了，也能从微信/企微把它喊回来。
基于 Hermes 改造的轻量级 AI 助手框架，可以快速打造商用 SaaS 平台，支持多租户隔离部署、多平台渠道接入、工具调用、定时任务和 Web 实时通信。
A design skill for building never-cheap, high-craft web interfaces — both brand surfaces and product UI.
A file-backed, spec-driven AI coding workflow framework for building real software while staying in control.
: Claude Opus 5 (claude-opus-5) / Claude Opus 4.6 (earlier chapters) : Claude Code + OpenClaw + OpenCode : 2026-08-02 : v2026.3.9 (v2026.3.8-170-g665f67726) : https://github.