Code agents

Own Your Intelligence. Open-source framework for building AI-automated businesses.

Self-hosted web relay to use your local GitHub Copilot CLI session from any browser — phone, tablet, or second computer. Streams tool activity, supports ask_user question cards, file uploads, image attachments, model/mode selection, conversation history, and optional SSH tunnel for remote access.

MOVED: now the bug-shepherd plugin in github.com/mshadmanrahman/pm-pilot. Install: claude plugin install bug-shepherd@pm-pilot

GH-300 live demo kit. A real Python app left intentionally immature (bugs, security gaps, low coverage) across 5 structured Copilot modules. Prompt library, Skills, AGENT.md, and a reset script included.

Your personal executive assistant that lives in your terminal. Built on Claude Code. Manages your day, tracks tasks, preps meetings, and keeps you accountable.

Convert an X (Twitter) URL into clean markdown — tweets, photos, videos, long-form X Articles, and top replies. No auth, no API key.

Convert any code repository into a single markdown file for NotebookLM and other LLM tools.

On-prem, MCP-native memory for AI agents in regulated settings: every write lands in a SHA-256 hash-chained log an auditor can verify offline, without trusting the store or the vendor. Rust, embedded, Apache-2.0.

A powerful native SillyTavern extension for high-performance local web search and scraping. Built using Playwright for superior page extraction with full MCP tool-calling parity. No external API keys required—fast, private, and fully integrated with the SillyTavern UI.

Local LLM server that provides drop-in API compatibility with both Ollama and OpenAI, using your locally installed [llama.cpp](https://github.com/ggerganov/llama.cpp) 's `llama-server` as the inference backend.

MCP server for multiple PostgreSQL databases. One process, unlimited databases. Hot-reload JSON config, --label per-project isolation. Read-only safe queries. Works with Claude Code, Cursor, Windsurf, Cline, and any MCP-compatible AI client.

Turn SpringDoc OpenAPI into production-ready MCP tools for Spring Boot: discovery, validation, workflows, and guardrails.

Universal AI memory starter for Claude Code, Codex CLI, Aider, Cursor. File-based + git, no MCP plugins, no external DB. Battle-tested replacement for Pensyve/Mem0/Letta.

Shared context substrate for AI agents. Retrieval that learns what's useful. Runs local or cloud.

Your screen history, searchable and automated - Windows OCR + REST API + AI + RAG

Turn a short prompt into one clean, hand-drawn concept illustration starring a deadpan peanut — an agent skill for Claude Code and OpenAI Codex.

Production harness between LLMs and the real world. Kernel sandbox that cannot escape. Verification pipeline before delivery. On-chain attestation via ENSO/ICP. Fault-tolerant execution with rollback. Self-healing memory. 36 providers. 20 platforms. Live trading. Rust.

⚔ AI agent skills installer — 17,000+ skills for Claude Code, Cursor, Cline, Aider, Codex & Antigravity. pip install lotr-skills. cursor rules, claude code skills, SKILL.md, AGENTS.md.

Free Claude / Free Claude Code — use Claude Code & Claude Desktop with any AI provider (OpenAI, Gemini, Grok, DeepSeek, OpenRouter, Groq, NVIDIA NIM, GLM, Kimi…). Cross-platform desktop app.

Should you care about this CVE? An agent skill that triages whether a CVE applies to your environment, with sourced, verifiable reasoning.

Giáo trình xây hệ thống wiki AI-first Obsidian + Claude Code đa vault giống Phạm Thành Long. 41 file, 7 phần, từ triết lý đến template copy-paste.

BYOK coding and research agent. Obsidian-compatible markdown wiki as a baked-in memory system. Isolate work from life using frames.

月老鳌烨的相亲决策操作系统 · 蒸馏自公开直播视频的 AI skill · CC BY-NC-SA 4.0

an opensourse AI coding agent

AI 軟體工廠：用一句白話需求，產出可審查的靜態網頁／小工具草稿（zip 或草稿 PR），全程人類把關。

Self-hostable AI agent runtime — single Rust binary, Tailscale cluster, runs across Mac/Linux/Windows/Android/iOS without a cloud account. Apache 2.0.

AI-Native Trading Engine - AI 에이전트 기반 자동 주식 매매 트레이딩 시스템

Clone your voice, license it, sell it, earn 💸. Only devnet for now. Since it is not yet available for general use, only texts up to 300 characters are voiced for the testing of 0-data voice clones to reduce costs.

Give AI coding agents control of your real Chrome browser — with login sessions, cookies, and extensions.

Local-first AI security gateway for AI Agents. Intercept, audit and govern Claude Code · Codex · Cursor · OpenClaw traffic — 3 monitoring tiers × 8 defense layers, zero cloud.

AI-Native Post-Authentication Runtime Control Plane. LLM-driven Zero Trust security platform for Spring Boot applications. Continuously evaluates authenticated runtime behavior with 5-action dynamic control (ALLOW · CHALLENGE · BLOCK · ESCALATE · PENDING).

A Claude Code skill for working in large remote Linux repositories over SSH when your local machine does not have enough memory to run the project comfortably.

Safety first. Hardware-verified DeFi for AI agents — designed for when the AI can be compromised.

🛠️ Build a collaborative framework for pricing strategies using AI, enhancing decision-making through real-time data analysis and human insight.

Spec Driven Build 系统提示词 - 让 Claude Code / Gemini CLI 先设计再编码，通过需求→设计→任务三阶段驱动 AI 开发

LangGraph multi-agent research pipeline with RAG, hybrid BM25+semantic search, FastAPI streaming, and LLM-powered synthesis.

macOS desktop companion for solo developers — an AI coding partner that watches your screen, hears your voice, remembers context, and proactively helps. Built for Gemini Live Agent Challenge 2026.

Local AI code review agent. Self hosted with Ollama, no data leaves your machine.

WWA Transform — Turn any website into an AI-powered agentfront. Claude Code plugin + Codex agent + CLI.

A managed AI marketing agent that plugs into all your AI tools. MCP server configs, setup guides, and integrations for Claude, ChatGPT, Cursor, VS Code, and more.

Universal MCP skill dispatcher for AI coding agents. Load Claude Code, OpenCode, Cursor, Gemini, command, and GitHub-hosted skills on demand.

AI agent skills for onboarding merchants to UCP (Universal Commerce Protocol). Audit → Profile → Catalog → Checkout → Validate.

Durable, review-gated background research for OpenClaw agents

MCP server for spawning and controlling Codex CLI and Claude Code sessions

ShuyuanCore (数元体) — 智能进化、风格一致、深度记忆、自主行动的开源AI Agent。（ShuyuanCore—An open‑source AI agent with intelligent evolution, consistent style, deep memory, and autonomous action.）

一款企业级多语言(Polyglot)智能出行 Agent 架构实战。采用 Monorepo 单仓管理，底层基于 Java Spring Cloud 构建高并发票务微服务底座；AI 大脑层提供 Java (Spring AI) 与 Python (FastAPI+LangChain) 双引擎实现。核心特性包含：端到端 JWT 上下文鉴权透传、基于 Tool Calling 的异常自纠错 (Self-Correction) 循环，以及微服务级的数据流压缩，完整打通自然语言到真实复杂业务下单的全链路闭环。

A recursive dashboard. Built on the Cursor SDK and FastAPI. The agent reads its own source code, queries its own data, and edits itself when you ask it to. Two lines of Python and a script tag.

Skills that guide AI coding agents to integrate with the Adaline platform — send traces, manage prompts, run evaluations, fetch deployments, and more. Compatible with Cursor, Claude Code, Codex, Windsurf, and 40+ other agents.

MeetingMind — agent-native meeting notes: local recording + whisper.cpp (or your own ASR) transcription, summarized by your terminal agent. macOS, no UI, no cloud.

Documentation compiler built end-to-end by autonomous Claude Code agents

Autonomous AI Security Agent leveraging LLMs, RAG, and Knowledge Graphs for automated CVE analysis and auto-patching.

Governance-first agent command center for workflow automation, validation, policy, documentation sync, and execution discipline.

Claude Code production runtime - Python implementation and prose chapters

if you love claude code you will make it your ex if you use this

Lightweight coding agent.

AI-powered customer support agent built with Python smolagents and InterSystems IRIS — SQL, RAG, and live interoperability

AI-powered multi-agent system for Web3 marketing automation — content generation, on-chain analytics, narrative tracking, campaign management. Built with MiMo LLM + FastAPI.

MCP server giving AI agents instant access to 1,500+ free public APIs — search, probe, and generate code snippets

Append-only event kernel with Ed25519-signed Merkle checkpoints. Every AI action gets a verifiable receipt.

Production-ready scaffolding for Next.js, Vite+React, FastAPI, and NestJS — one prompt to a fully configured project with auth, database, testing, and Docker.

VS Code & Cursor extension to manage AI coding agent sessions across git repositories and worktrees. Fork sessions, track changes, run quick actions. Supports Claude Code — extensible for other agents.

Your team's second brain — turn every product discussion into a structured, versioned, team-shared knowledge base. From discussion to PRD, prototype, dev handoff, GTM content, email, and product videos, end-to-end. Works with Claude Code & Codex.

Codex skill for Ghost Buyer: careful Taobao/Tmall shopping research with user-controlled browser sessions and Markdown/HTML buying reports.

一站式游戏数据采集与自动化分析工作流，内置可视化 WebUI 与 AI Agent 助手。

A professional Telegram bot for YouTube creators that uses the Google Gemini API to generate content ideas, optimize headlines, and adapt content for short formats.

A universal, highly intelligent LLM API proxy gateway. Seamlessly translates heterogeneous AI protocols (OpenAI, Anthropic, Gemini) with built-in multi-account rotation, circuit breaking, and zero-config deployment.

Claude Code skills for the whole job hunt — turn messy experience into résumé language, decode JDs, find real openings online, and tailor résumés. Never fabricates. 中英双语

Keep your focus; offload the rest. dispatch.md is an Obsidian vault that becomes the memory and mind-map for your AI agent — so nothing slips and your mind stays clear.

VeyraSkills — A curated collection of Claude Code skills for founders, developers and AI builders

Skill discovery engine for AI coding agents. One install, 20+ developer workflow skills.

ai agent

AI命理运势分析Web应用｜Django + SQLite + 通义千问LLM｜生辰八字、五行四象、时运与正缘解读

A modular AI Agent framework designed for complex task orchestration and logic reasoning.

Build AI-native SaaS agents with the ROAM Loop: Render, Observe, Act, Memorize.

AI-SDLC framework of skills, rules, and agent definitions that AI coding agents use to generate consistent, production-quality Python code. Compatible with Claude Code, Codex, Cursor, Kiro, Windsurf, Gemini CLI, Antigravity, and GitHub Copilot.

Universal AI learning skill — transforms any content into a structured, adaptive learning system with knowledge base, spaced repetition, and achievement tracking. Works with Claude Code, Codex, Gemini, and any LLM.

"Jira for Claude Code": sprint/card/doc project management exposed over MCP, so AI agents plan, execute and track their own development.

A modern, AI-native, cross-platform terminal focused on speed, security, and developer flow.

Audit, optimize, and prepare your Laravel codebase for AI coding agents. Readiness scoring, auto-fixes, AGENTS.md generation, simulation mode, and plugin system.

MCP server + Claude Code plugin: multi-agent advisory squad with PRD-decomposed tasks, persistent learnings, weighted rubric scorecard, and PR posting.

统一的 AI 编程助手 Web 平台（Claude Code、Pi Agent、Codex）。实时流式输出、分屏并行、Agent 切换 Unified web platform for AI coding assistants (Claude Code, Pi Agent, Codex). Real-time streaming, split-screen parallel mode, agent switching, dark theme

Live demo of per-user/per-chat session isolation with Microsoft Foundry Hosted Agents. One agent, many sandboxes — visualised step by step.

Convert an Open API specification into an AI agent skill.

Every AI skill, independently scanned. Public, open-source trust scoring for skills, MCP servers, hooks, and plugins across every agent platform. Apache-2.0. saferskills.ai

A software development methodology for the agentic era — researched, debated, and authored by AI agents.

Nighttime ML experiment workflow with Claude Code multi-agent orchestration (Planner / Executor / Reviewer / Auditor)

Autonomous quality firewall for LLM agents - classifies failures, generates patches, writes evaluators, and runs shadow deployments. Built on LangSmith + LangGraph + Groq.

Fable 5 workflow Loop; A Claude Code skill: autonomous build / audit / verify loop that runs until a machine-checkable contract passes, with ▎ deterministic anti-spin stop conditions (no-progress, retry, oscillation, budget) and on-disk human escalation.

Research workrooms for AI agents: evidence retrieval, citation audit, adversarial review, peer review gates, and clean final reports.

Vectorless multi-agent research pipeline that transforms a raw topic into thematic structures, ranked gaps, competing methodologies, and a funding-ready proposal. Eliminates traditional RAG by using LLM-native synthesis with interpretable reasoning, quality gates, and quantitative novelty scoring.

Lightweight, thread-safe memory kernel for autonomous agents. Strengthens knowledge through reinforcement, prunes with gentle decay, and exports transparent Markdown — pure SQLite. Foundation for persistent, self-improving reasoning.

AI agents get stuck in infinite tool loops. Each loop cycle burns API credits. Microloop detects redundant tool calls locally in nanoseconds and blocks them before the call ever leaves the machine.

Simple MCP Server w/ Shell Exec. Connect to Local via Ngrok, or Host Ubuntu24 Container via Docker

DSAFlowBot is a smart assistant that streamlines DSA practice with topic-wise question flows.

Stateful AI agent memory layer for PostgreSQL with pgvector - TypeScript-first with intelligent context management

Quizzy is an AI interviewer that creates hyper-personalized interview simulation using a RAG-based system for dynamic conversations. It analyzes emotions, perception, posture, and responses, ensuring a natural flow. With job opening scraping and an embedding-based ATS score checker, Quizzy prepares you for the job market. Built with MLOps in Django

Deterministic $0 pytest assertions for AI agents — catch the agent that quietly stopped calling its tools, and cost blowups, offline in CI.

A high-performance AI knowledge base that uses DeepSeek-V3 and Hybrid Search to turn your PDFs and docs into an interactive, real-time chat expert. Built with a FastAPI backend and a premium Glassmorphism UI.

Rust-native universal retrieval layer for humans and AI agents — search, extract, rank, and synthesize the web. CLI + REST API + MCP server, with adaptive extraction (CEP), token-budgeted packing, multi-signal ranking, and cited research.