Code agents

Substack MCP server for AI clients (Claude, Cursor, Codex, Windsurf) — draft, publish, schedule, analyze, and research Substack publications via the Model Context Protocol.

Run a fleet of agent coding agents from Neovim

医学科研 AI 智能体团队：面向中文临床研究者的 OpenCode 工作流插件

10-stage SEO content pipeline built using Claude Code skills. Research-deploy, with human approval gates after each step.

🛡️ Local privacy firewall for AI coding agents — masks API keys & personal data before they reach the cloud, then restores them transparently.

Project-aware multi-model harness for Claude Code with account routing, isolated sessions, LeanCTX, and MCP integrations.

Agent Skills by mr-kelly

Black-box LiveKit voice agent testing: real WebRTC/SIP calls with an AI caller. Catch barge-in, noise, quiet-mic, and latency failures that text pytest misses. Forensic reports + MCP + lks CLI — no agent code changes.

Docker image to run a self-hosted MCP (Model Context Protocol) gateway with Bearer token auth. Multi-server hub powered by MCPHub + Caddy. Streamable HTTP + SSE transport. Access filesystem, fetch, GitHub, Brave Search, Git, PostgreSQL, memory, and more from a single endpoint. Multi-arch: amd64, arm64.

Message notification router: Haiku safety gate + Opus router with code-enforced guardrails. #94 of 1,983, HackerRank Orchestrate 2026.

Self-hostable RAG chatbot for networks with no internet access, such as Japan's LGWAN. LDAP authentication, chat history, and admin tools over in-house documents.

SERPsmith helps AI agents research, create, and publish evidence-led, SEO-ready content.

Codex app-server powered auth broker for Pi, Factory Droid, and OpenAI Responses API clients

Using the API use Nemotron without even needing any account in python

A modern Laravel-based recruitment platform for job seekers, featuring AI-powered resume parsing and a seamless application experience.

Lightweight Bun + Elysia proxy for OpenAI-compatible APIs with Langfuse telemetry

Press 1 to allow - global hotkeys for Claude Code permission prompts on Windows. Popup + hotkeys or Logitech MX Console, no focus switch, no auto-approve.

The bone cracks. The model reads. Audited divination for AI agents — tarot, I Ching, Xiao Liu Ren, Bazi. MCP server + CLI + agent skills.

Catch false-positive Claude Code safety/policy blocks, scrub PII, and auto-file clean GitHub issues. FOSS.

CodeNexus - Semantic Code Search Engine — Ask natural language questions about any codebase and get relevant code snippets with AI-powered explanations. Built with FastAPI, Next.js, FAISS, tree-sitter, and sentence-transformers.

Personal RAG engine — simple, fast, Rust. One binary (15 MB), one DB, native collections. MCP-native.

Local-first literature RAG workbench for PDF, Zotero, Chatbox, and OpenAI-compatible APIs

Motion graphics as code. An agent skill for building frame-exact animated logos, kinetic typography and brand videos as a single HTML file, then exporting them to MP4 in 1:1, 4:5 and 9:16.

MCP channel server for the Zalo Bot API. Talk to your Claude Code session from Zalo, with pairing, allowlists, and group gating.

Multiple Entry Iron Condor (MEIC) strategy agent for 0DTE options via tastytrade and Claude Code

AI code review for GitLab, GitHub, and Gitea with OpenCode Agent Review backend. 基于 sunmh207/AI-Codereview-Gitlab 演进的 OpenCode Agent Review 版本，保留原有多平台 AI Code Review 能力，并新增 OpenCode Serve backend 集成。

An embeddable AI dev agent for your running app — chat, page control, and live tests, injected into the page via a Vite plugin.

CLI, MCP and TS library that turns source code into a map of files, symbols, references, and dependencies using tree-sitter.

AgentInterdict — runtime enforcement for autonomous AI agents. Trust context. Verify authority. Interdict unsafe action.

Portable, validation-first workspace and localhost gateway foundation for governed multi-agent development.

Native AI terminal for working with a fleet of coding agents. Run any agent (Claude Code, Codex, opencode…) with your own subscription — plan, sandbox, ship. macOS & Windows.

Open protocol for AI agents to use Obsidian vaults as persistent memory with SHA256-based incremental indexing.

Local-first, event-driven AI software factory for building, modernizing, debugging, securing, porting, validating, and optimizing applications through task-activated specialist agents, multi-provider model routing, isolated workspaces, runtime QC, and audit-ready evidence.

A model-native quality control plane for agentic software work. Preserved at 6.7.0; development paused.

Your personal coding assistant for macOS

Qofeno agent skills — real, production-only workflows for Claude Code, Cursor, Antigravity, and other AI agents

Apply V4A context-anchored diffs from any LLM model and get structured line-by-line diff output with built-in instant rollback capability.

Local-first shared memory and task coordination for AI coding agents. One Go binary, MCP server, markdown files you own. Hooks for Claude Code and Codex CLI (and their desktop apps).

Repo-scoped Codex skill for launching and collecting independent Luna subagents.

LLM Knowledge Management • Wiki-grounded verification • RFC-based documentation • Best practices automation • AI-native engineering

Where agents co-create, humans are welcome too.

MIMO Claude Code Traces is a collection of coding-agent trajectories in a Claude Code-style environment.

Visual Tales Generator is an AI pipeline transforming text into visuals. It uses OpenAI API, Flux Dev diffusion models, and LoRA fine-tuning. An agent processes JSON, NLP ensures character consistency, and a model-agnostic architecture uses system prompts. It generates Pixar-style 3D storyboards via Replicate API, automating visual storytelling.

Unofficial, experimental Codex skill for safely auditing and cleaning closed subagent histories without touching main conversations.

Terminal coding agent that executes tools (real think>tool>result loop with confirm + undo, MCP tools in-loop) and rewrites its own system prompt from feedback with metrics + auto-rollback. Free by default via the FCM model router.

Mook - a full-stack RAG proof of concept. FastAPI backend with document ingestion (PDF, Excel, URL) and vector search, a React/Vite front end, and pluggable LLM providers: Claude CLI, Azure OpenAI, OpenAI, or an offline mock for testing.

litert-lm litertlm qwen Qwen2.5 text-generation en

Terminal coding agent for local LLMs (llama.cpp, Ollama, vLLM) and any OpenAI-compatible API. OS-sandboxed autonomy, MCP, sessions. Go.

A generative engine that treats the human voice as a physical force. It uses the resonance of spoken intent to organize digital chaos into structured form, allowing creators to literally sound their ideas into reality.

Tenki Weather 🌤️ — Archived Indonesian weather chatbot built with Unity 6 WebGL, OpenAI, WeatherAPI, and ElevenLabs. No longer maintained.

让第三方中转 API 也能用 Codex 手机 App 等官方原生全部功能：保留 ChatGPT 官方登录态，请求走中转省钱。单文件 exe，双击出界面。

Local-first live dashboard, CLI, and Windows widget for your subscription quotas plus local token spend. Silent updates, zero telemetry.

Legal Cite PL — MCP server weryfikujący aktualne brzmienie przepisu PL/UE prosto ze źródła (Sejm ELI, EUR-Lex). Anti-halucynacja dla Claude. Apache 2.0.

Vellum: an auditable agentic ICD-10-CM/PCS autocoder that proves every code and catches the model fabricating its own evidence. Glass-box web cockpit. Built with Claude.

Claude Code usage monitor on an e-ink desk gadget — rate-limit meters, live WORKING/NEEDS-YOU/QUESTION/DONE status, and a bell that rings when it's your turn. Waveshare ESP32-S3-ePaper-1.54, BLE.

Axiom is a curated marketplace of shared plugins for Claude Code and Codex.

A Claude Agent Skill that humanizes AI-written marketing and long-form copy: landing pages, sales pages, e-books, case studies, founder notes. Removes AI tells and process bleed, de-slops prose, strips em dashes, never invents facts, keeps your brand voice.

Stack-agnostic monorepo template where agents are the workflow: PM → implementer → fresh-context reviewer loops via Claude Code subagents, skills, and GitHub Actions

SQLGraph is an ontology-based GraphRAG system that enables natural language querying of SQL databases by constructing a knowledge graph from database schemas and data.

OpenRag - OpenRAG turns private documents into a secure AI knowledge system

A model-facing field manual for turning venture ideas into inspectable enterprise systems.

Vidify is an ASR-first video understanding agent that turns YouTube, local files, and live streams into timelines, searchable Q&A, reports, and highlight clips

A knowledge graph in the Postgres you already run — multi-hop traversal, mutation, and vector search via recursive CTEs on two plain tables. No graph database, no extension.

Kinetic Trust Protocol (KTP): environment-derived authorization for autonomous agents — authority recomputed from current conditions, never issued in advance, under A ≤ E. 27 RFC specifications. v2.0.0 "Gödel".

Turn any PDF, EPUB, DOCX, or slide deck into an agent skill. A CLI + skill that reads whole books and docs, then writes SKILL.md for Claude Code, Codex, Gemini CLI, Cursor, and opencode.

Lightweight browser automation CLI + MCP server driving your everyday Chrome via the extension chrome.debugger API — keeps your login state, no --remote-debugging-port

🔍 Rebrief - Compress your repository into a clean, AI-ready Markdown summary. Reduce token waste and give LLM agents a sharp roadmap of your codebase.

Local-first MCP server for video: download any video from almost any URL, or get a transcript plus scene-aware deduplicated keyframes. YouTube, TikTok, Instagram, X, WeChat Channels, MP4/HLS. No cloud, no API keys.

Battle-tested multi-agent collaboration playbook for DeepSeek Harness: model-tier routing, spec discipline, git single-writer rule — as an installable skill. 多 agent 管线里运行 DSH 的实战协作规范

DataBrain is a powerful, modular, and local-first knowledge management and learning platform designed to help you organize, learn, and create interactive content effortlessly. Built with a block-based architecture, it combines the flexibility of a notebook with the interactivity of a modern webapp.

⚡ Competitive multi-wallet NFT auto-minting agent for OpenSea/SeaDrop & direct contracts — low-latency fast-mint (raw EIP-1559, multi-RPC fan-out, RBF), scheduled drops, browser fallback & listing. Runs as an MCP server, an AI-agent skill (Hermes/Claude), or a CLI. Security-hardened, multi-chain EVM.

Executive-ready slides, one API call away. API-first AI presentation engine with 32 slide types, 24 chart types, 15 themes, finance vertical. PPTX + Google Slides. MCP server for AI agents. TypeScript SDK.

SOIA 技能生态门户：规范真源、技能目录与跨仓路由清单

Self-hosted AI analysis harness that turns GitHub repositories into validated SysML v2 and interactive architecture graphs.

Mines corrections from your AI agent's chat logs to catch recurring drift and overclaiming before the next response ships. A cheap-to-expensive pre-flight gate — regex, then structured scoring, then a pressure probe — plus memory that carries past corrections into similar tasks. MIT, zero dependencies.

A minimal Coding Agent Harness inspired by Pi, built to study and validate Agent Runtime/Harness abstractions through executable demos and real LLM experiments.

Portable doc bridge for AI agents — OKF + Self-Describe + AgentHandoff. CLI, MCP, Fumadocs/Docusaurus adapters.

Agent skill for the Supadata API — transcripts, metadata, web scraping, and AI extraction

DSH 插件：OpenCode Go 额度圆环 —— 输入框模型选择器左侧的进度圆环，点击切换 5小时/每周/每月用量（OpenCode Go quota ring for DeepSeek Harness Web）

Making AI coding harness improvements observable and measurable.

Open your AI agents' black box. The waste is between your agents, not inside them. Four deterministic detectors over one trace file, priced from real usage fields. Hosted at boxdawn.com.

Token-efficient code knowledge graph for AI coding agents — type-checker-accurate call graphs for Go & TypeScript/JS, served over MCP.

Memory for your coding agent — markdown project graph template: product, plans, features, bugs, specs, architecture, releases

Loop engineering: two skills in the open Agent Skills format (idea-to-spec with a required grill step, spec-to-done with an evidence ledger and integrated done gate) for turning ideas into reviewed specs and driving them to an evidence-backed done. Works with Claude Code, Codex, Cursor, Gemini CLI, and any Agent Skills-compatible tool.

A governance layer for AI agents. Decides what the agent may do and may claim; it can't overrule either. Wired to a live broker. Risk gate I broke 4 times myself.

Spawn silent-boot codex/omx coder teams — a maw plugin + charter. Each coder on its own account & worktree, zero trust prompts.

📐 Bidirectional spec-to-code drift detection. Rust CLI and MCP server that catches undocumented exports and vanished symbols in CI.

This repository presents an Agent2Agent (A2A) architecture using Google Apps Script to resolve Tool Space Interference. It supports scalable, distributed task execution via multiple parallel, category-specific A2A servers.

Local fine-tuning for your own work. A provider-neutral kit that turns project experience into reusable criteria for AI agents — distilled at a threshold you control, pruned when it grows, and portable between models.

Run an always-on SEO/AEO growth loop on your own site with Claude: pulls GA4 and Search Console signals, proposes fixes with the reasoning attached, applies approved changes to WordPress, verifies they landed, and learns from outcomes. Every write is human-approved. MIT, no telemetry, no scraping.

A local-first, governed agent harness: high autonomy inside structurally-enforced boundaries (Autopilot, not YOLO).

DeepSeek Harness 插件：确认改动的代码行真的被测试覆盖到，结论绑定代码指纹，代码一变自动过期

面向扫地机器人售前、售后与使用报告的多工具智能客服 Agent：基于 LangChain/LangGraph、通义千问、Chroma RAG、SQLite 与 Streamlit，集成知识库安全入库、浏览器定位、实时天气、会话用户及设备使用记录查询，并提供可审阅工具追踪、动态 Prompt 与 Recall@K/MRR 检索评测。

Compiler-style pre-execution safety analysis for Harness shell actions.

An AI agent that drives a real browser, audits any web app against UX/functional/conversion rubrics, and shows evidence-backed findings. Works with any OpenAI-compatible LLM.

Native multi-provider AI coding agent in Rust — Avalonia desktop app for Linux/macOS with a native Android companion, WhatsApp bridge, Tor/Arti multi-device mesh, on-device skills, persistent memory and Web Search.

Jeomwon (점원) — agent kit that turns one domain interview into a working reservation SaaS: AI storefront clerk chat, admin dashboard, and lifecycle emails on Convex + Next.js

Agentic exporter and runner for internal network pentesting, autonomous host discovery, patch/vulnerability state collection, and server/application inventory, surfaced as structured findings for the Lorikeet Security platform.

Native Claude Agent SDK with Harness specialized become as team member.