Coding & Development

把微信读书的划线与想法导出为独立 flomo memo 的 Agent Skill / Export WeRead highlights and thoughts to flomo via flomo MCP

AgentFlow-Go 是一个以场景 YAML 为配置中心的 Go Agent 框架，核心定位是组合 Agent、Tool、Skill、LLM Gateway、上下文治理、Memory、Run State 和 Human-in-the-loop 编排能力。它既可以作为 Go 库嵌入到项目中，也可以通过 CLI/HTTP 方式独立运行。

Static release-readiness gate for AI agent tool surfaces. CLI + GitHub Action. Scans MCP, OpenAPI, OpenAI Agents SDK, Anthropic, Google ADK, LangChain, CrewAI. Apache-2.0.

Template for AI development sub-agents: tester, PM reviewer, marketing strategist. Use with Claude Code Agent tool.

Delivering the Variable points affecting the price to the telegram bot using MCP , Agentic tools and codex

Claude 规划技能：把一句话目标转成可直接粘贴给 Codex 的有界任务单（Goal / Scope / Acceptance Criteria / Validation 九段式），让规划模型负责切片，让 Codex 专注执行。

MCP server giving Claude and other LLM clients structured access to the Internet Archive's Wayback Machine — 6 tools, 4 prompts, 1 resource, over stdio.

OpenClaw plugin: Bridge Codex, Gemini, and Claude Code CLIs as model providers

personal AI runtime, local-first. MCP bridge giving Claude Code 170+ tools (LSP, debugger, terminal, git) inside VS Code, Cursor, Windsurf, or JetBrains. Optional Patchwork layer adds YAML recipes, an approval queue, and an oversight dashboard. Your models, your machine, your policy. (Mac & Windows)

Safety-first sandbox verification for the Agent-Matrix ecosystem — clone, install, test, and debug untrusted repos (agents/tools/MCP servers) inside ephemeral containers.

MCP (Model Context Protocol) server for HawkAPI — auto-exports routes as agent tools

MCP server for Google NotebookLM: stdio + Streamable HTTP transports, NotebookLM tools/resources/prompts, OpenAPI/ChatGPT actions, Claude/Cursor/VS Code integration, token/OAuth auth, Docker/K8s deploys.

Voice I/O MCP for AI coding agents — local TTS + STT, 10 tools with ToolAnnotations

Tools and configurations for AI coding agents (Claude Code, etc.)

Private network memory for OpenClaw, Hermes, and MCP agents.

This repo contains skills for AI platforms to utilise.

A CLI to snapshot, encrypt, and sync AI agent configs — Claude, Cursor, Codex, Copilot, VS Code — across machines via a Git vault.

QA + product spec toolkit for Observo. 7 Claude Code skills + Playwright integration. Repo-agnostic, MIT.

My AI agent tools skills.

Detect and audit version drift between manifests and lockfiles for AI agent tools like Codex, Claude Code, and MCP servers

Marketing skills for AI agents: reusable instructions, scripts, and QA checks for growth work.

Scripts for use in ai harnesses, in hooks, skills and tools

From any API surface to verified AI agent tools: Go CLI + MCP + skills + SQLite + policy + proofs.

Open source agent tools — skills, scripts, and infrastructure for onchain AI agents