Code agents

Real-time tracking of every new GitHub 'skills' repo to capture the AI agent skill ecosystem trend

Find AI/LLM security vulnerabilities in your code before attackers do — covers prompt injection, MCP tool poisoning, RAG data poisoning, and more

Universal AI Agent skill for downloading videos from YouTube/Bilibili/Douyin/Xiaohongshu/Kuaishou/Weibo/Twitter/Vimeo/TikTok. Works with Codex, Claude Code, Cursor, Cline.

Offline fault diagnosis assistant for the AgiBot X2 Ultra humanoid: drop in a log package, get a three-round reviewed diagnosis. Rules + causal inference + LLM agent.

Forge your own agent harness — a config-to-code generator that renders a thin, standalone Python agent harness you fully own. No LangChain/LangGraph/ADK lock-in, no dependency on the generator after generation.

Windows computer-use MCP server: drive any desktop app via semantic discover-then-act targeting (entities + leases, not pixel coordinates), with per-action perception guards, a native Rust UIA engine, Chrome CDP, and Key Locker credential autofill for ssh/sudo password prompts. Works with Claude, Cursor, and any MCP client.

对话式 PRD 生成技能，中文优化，通用 Agent Skill（Claude Code / Codex / Hermes / OpenClaw 等） · A conversational PRD-writing Agent Skill

transformers pytorch llama text-generation code math

CLI that distills the silent decisions your AI coding agents make into a reviewable ledger. Approve once, becomes precedent.

Your product idea. One command. Shipped. The Hyper-Scale Solo Infrastructure(TS 7.0, Bun1.4, oRPC v2, Nix devenv)

Local dashboard to run parallel Claude Code & Cursor agents — kanban fleet view, one permission inbox, in-app diff review. macOS, MIT.

Self-hosted multi-tenant agent platform for teams: skills, knowledge, API contracts and MCP servers live in the database and grow at runtime; big API responses are queried with SQL, not stuffed into context. Typed Python core (Protocol ports) you can embed in your own stack.

Drive Claude Code through an SDLC pipeline on your GitHub Project board — Specify → Research → Plan → Implement → Review → Validate. Human in the loop, or on it. A Go CLI for automated, issue-driven development. Docs → fabrik.handarbeit.io

Run one command, follow the instructions, and get your first AI agents up and running — Claude Code or Codex. Built for the Elnora AI agent hackathon.

My daily AI agent skills for Claude Code, Codex, frontend QA, reviews, and workflow automation.

The robustness engine for AI coding agents. A local Rust code graph gives an agent repo-wide understanding, a validation gate that runs before an edit lands, and safe symbol-aware edits. Deep on TypeScript, useful on Rust, local and deterministic.

🦅Strix 落地与调教完全指北 —— 这是一个专注于下一代自主 AI 渗透测试代理Strix 的实战部署与性能榨干指南。🎮以及如何通过 --instruction 指令化身“赛博御兽师”操纵 AI 黑客注意力的进阶玩法的核心沉淀。⚡内含国内网络环境下 Docker 0/33 沙箱卡死究极加速方案，💰全网超全的多模型（DeepSeek-V4、Claude、火山引擎、OpenRouter）高性价比接入配置。A comprehensive hands-on guide to maximizing Strix, the autonomous AI agent that thinks and acts like a real hacker.

Local knowledge base for AI agents (hermes plugin): hybrid search over your PDFs, DOCX, sites, YouTube and Obsidian; answers grounded strictly in sources with verified citations. One-command install, cloud or fully local.

Cognitive Loop Runtime for Kubernetes

100 days, 100 sources: a daily public learning log of modern AI - LLMs, agents, RAG, fine-tuning, MLOps and more. Daily on Threads, X, and Bluesky @reksas13 & LinkedIn under #100DaysWithAI.

Agent-powered iterative optimization: put an AI agent in a verified improvement loop.

Repository-scoped memory for coding agent's decisions, pitfalls, and handoffs stored in one inspectable SQLite file, so agents continue instead of starting over.

muxel is a GPUI-native multiplexer for coding agents

Agentic coding scheduler, a Rust agent harness that runs background coding agents autonomously

A local-first desktop dashboard for macOS and Windows that turns Codex CLI and app logs into clear insights on token usage, estimated costs, models, and projects.

The Codebase Intelligence layer for AI coding agents. Semantic indexing, graph navigation, and repository intelligence

코딩 에이전트가 만들어 주는 데모 영상 — 바이브코딩 결과물을 제대로 뽐내세요.

Structured market intelligence for Indian financial events, macro context, and sector impact.

transformers gguf causal-lm code text-generation en

Read-only macOS storage audit skill with an interactive report and safe Finder Reveal bridge.

A hand-drawn illustration and animation language for LLMs

从零手搓的 Coding Agent（ReAct + 工具 + 记忆 + 权限 + 上下文压缩 + 子agent + MCP），纯 Python/asyncio

A cooperative gate for the shell commands AI agents run. Previews, backups, policy, audit. Claude Code + Cursor. A windshield, not a sandbox.

跨项目知识库整理 Skill：信息分层归位、权限白名单优化、历史对话提炼。Claude Code 全局整理工具。

Pulsar2 Agent, Build a 10‑stage automated pipeline powered by AI Agent. Convert floating‑point models into out‑of‑the‑box full AX‑chip delivery packages with a single natural‑language instruction to empower algorithm engineers.

Multi-agent AI video interview platform — auto-generates interview plans from JD + resume, runs staged multi-round interviews with calibrated belief-driven follow-ups, and produces structured, compliance-partitioned evaluation reports with HR human review.

Jetson Nano edge AI vision Agent Harness: real-time video analytics, MCP tools, event evidence, DeepSeek online/offline, secure recovery

Your night crew, on Telegram. Run Claude Code, Codex or any terminal agent from a Telegram topic — one topic per tmux session. Watches the context window and the 5-hour limit, compacts before the wall, and holds prompts through a lockout instead of losing them. Python stdlib only, no relay server.

Deterministic, local-only audit reports for Claude Code AI agent sessions. Rust + SQLite. Zero network calls. MCP server for agents.

Track your daily prompt contributions across CLI coding agents

Task-aware reasoning-mode routing for opencode: spec/react/weak three-band agent routing, ported from yjh051108/dsh-routing-suite

Turn scattered marketing notes into a searchable intelligence layer your AI can read — one command in Claude Code.

Tool schemas get re-prefilled on every LLM request. ContextCache compiles them into a KV cache once, stores it on disk and reuses it across users and sessions — TTFT stays near 200ms with 50 tools instead of 5.6s (Qwen3-8B, RTX 3090 Ti).

Local zero-LLM PR QA designer: turns commits and diffs into behavior lifecycles, QA scenarios, and deterministic automation drafts.

Rule-driven AI job search and application workflows for Codex. Your apply Buddy!

Local-first IELTS speaking practice desktop app with voice sessions, review reports, study plans, and targeted retraining.

Opinionated Go skill for Claude Code, Codex, Cursor, Copilot & OpenCode — architecture, modern Go, testing, code review, MCP & agent patterns.

Free Claude Code plugin: learn Anthropic products hands-on from the official Claude Academy curriculum, and get your Claude Code setup and habits reviewed against Anthropic's best practices

Local-first runtime for observable, debuggable AI-agent workflows with slidable autonomy and multi-agent/tool orchestration.

The Zero-Trust Runtime Security & Governance Layer for Autonomous AI Agents.

Tends your codebase while you're away. An always-on AI engineer that reviews your logs, implements your tickets and keeps your pull requests moving, each in a disposable sandbox.

Unofficial local and LAN WebUI for the real Codex app-server, with approvals, streaming tools, review diffs, and mobile support.

Answers you can judge and act on without reading code — Claude Code plugins that keep implementation detail below a marked line. Off by default, armed one session at a time.

Agent Skill that turns your coding agent into a keyboard firmware expert. Audits ZMK/QMK keymaps, tunes home row mods, makes trackballs layer-aware, generates keymap diagrams with CI, adds alt layouts (Graphite, Colemak-DH), and debugs the failures the docs don't cover. Works with Claude Code, Codex, Cursor, Gemini CLI and more.

A curated collection of skills for AI agents to properly work with datavault4dbt.

Decide-then-code. A Claude Code plugin that teaches every load-bearing decision, records your choice, and blocks code from moving past a decision you have not made yet.

Install source for Forge Mentor — a decide-then-code Claude Code plugin.

Self-evolving skills for your coding agent — auto-create and auto-improve skills as you work, no trigger needed.

Python + Terraform. Cloud-ready GraphRAG solution that uncovers distant connections across data and grows incrementally as new documents arrive.

⚖️ VerdictAI — Multi-agent courtroom debate & verdict system. 7 AI experts cross-examine real case PDFs, cite real statutes & precedents, and deliver structured verdicts with executable next steps. FastAPI + LangGraph + WebSocket.

ShellX — desktop AI workspace for Grok Build, Claude Code, Codex, and Antigravity across Windows, macOS, WSL, and SSH. Includes a private agent browser and secure local Vault for credentials.

亚马逊评论分析 Agent Skill：卖家精灵 Review 表 → 一/二/三级分类树（格子里是买家原话）→ HTML 看板 + 交付 Excel

OpenGptLoop AI Agent is a fast, lightweight, and autonomous general-purpose AI agent.

Local, live code review for the AI age - read what the agent wrote and send feedback straight back

MCP server for Apple Mail: sub-ms search over 300k+ messages via Mail's own SQLite index, verified sends, Exchange body backfill, triage plan/review/apply. 849 tests, MIT.

Hermes Agent Production Knowledge Repository — 406+ repos, AI Agent Marketplace, MCP servers, autonomous AI agent patterns. Production-tested from 1,200+ hours of ops. Updated daily.

A systems language designed so an AI agent can safely write and run backend code: proven no GC/races/overflow, GBNF-constrained generation, structured diagnostics, OS-process sandboxing.

AI-driven automated threat analysis pipeline that routes files, URLs, IPs, domains, or images through specialized security analyzers and generates professional PWNDoc reports with integrated YARA and Sigma rule.

Free, open-source ERD designer for browser, VS Code & Google Drive — with AI agent integration (MCP / Claude Code plugin). DDL export for 7 databases.

Run claude with rootless podman

Structured Word, PowerPoint, and Excel automation for .NET and coding agents, with validated plans, MCP, tracked changes, and SharePoint

A TypeScript framework for building WhatsApp agents. Pluggable transports (Baileys, Cloud API, Twilio), a tool-calling agent core, and multi-provider LLM support.

Let an LLM write its own tools at runtime: parsed with acorn, versioned in SQLite, run in a supervised worker process

Free, open-source AI video editor for macOS, Windows and Linux — drive the whole timeline from any MCP client.

Open-source full-stack AI agent with an embeddable React UI and FastAPI runtime. Self-host with streaming, pause/resume, durable state, and parallel multi-agent subtasks.

SparkWork — a local-first desktop AI agent workbench for coding, research, documents, multimedia, workflows, and automation.

Fa - Factory Agent. Cross-platform AI agent harness for Dart and Flutter — streaming providers, agent loop with tools, session persistence, compaction; backend agent mode: fa behind product Go backends

📡 全网最全 · The world's most comprehensive tracker of the Jev (TypeSafe AI System One) ecosystem — 220+ documented cases · 108 confidence-graded entries · verified & rescanned every 3 hours · API access guide included

Six skills tell coding agents how to work. Two guards enforce the parts that should not depend on judgment.

The coding agent you don't babysit. Automatic software factory.

Real-world Elastic Email examples for transactional email, SMTP, webhooks, inbound email, contacts, serverless platforms and AI coding agents across 20+ languages and frameworks.

OpenClaw Virtual Office — real-time pixel-art agent office

Compile an API, an MCP server, a database or a web page into a CLI your agent can run. Ten engines, one output contract, 4.1x less context than raw MCP.

Dure — every coding agent, one workspace across desktop and mobile.

Open-source broker connectivity for code, apps, and AI agents. One normalized API for brokers & exchanges: accounts, positions, trade history, performance stats, with your own keys, running wherever your code runs. No hosted service, no per-connection fees.

Multi-account and usage manager for Claude Code and OpenAI Codex - switch logins, track quota, auto-rotate before rate limits

Turn WorkBuddy / CodeBuddy (Tencent) quota into a local OpenAI + Anthropic compatible API. Zero-dependency Node.js, multi-account pool with auto-rotation, context compression. 把 WorkBuddy/CodeBuddy 额度转成本机 OpenAI/Anthropic 兼容接口，零依赖、多账号轮换。

Claude Code and Codex in your Mac menu bar: see which AI coding agent is working, waiting for you or running background tasks, get alerts before weekly and 5-hour usage limits run out, and add desktop widgets. Free, open source, native macOS.

Curated GPT-Image-2 prompts for the OpenAI API — portraits, posters, UI mockups, game screenshots, character sheets, and more. Ready-to-use prompts for gpt-image-2.

Deterministic CI scanner and surface-risk scoring for MCP (Model Context Protocol) servers.

Scalable API gateway that aggregates calls to multiple LLMs (OpenAI, Hugging Face, Groq, Anthropic, Gemini, etc.), includes caching, rate limiting, logging, monitoring and production-ready deployment.

ContextQA - The open-source tool for data-driven conversations

Universal infinite memory layer for Developer AI assistants. One shared brain across Claude, Cursor, Windsurf & more. 100% local, built on MCP standard. Stop re-explaining context

Minimalist Context Management for message-based GPTs

A FastAPI application that relays client WebSocket connections to OpenAI's Realtime API, enabling seamless integration for real-time speech-to-speech interactions

Python command-line tool for interacting with AI models through the OpenRouter API/Cloudflare AI Gateway, or local self-hosted Ollama. Optionally support Microsoft LLMLingua prompt token compression

Krishna GPT: This iOS AI app, influenced by the teachings of the Bhagavad Gita, provides answers with a spiritual perspective to help you uncover hidden truths.

Semantic code search and RAG system written in Rust with tree-sitter chunking, MCP server for IDE integration, prompt injection detection, and secret redaction

⚠️ DEPRECATED - Use https://github.com/SylphxAI/coderag instead

The World of Akemon—Agent’s Second World. By day, Agent works for you. By night, let it live for itself.