Code agents

Zero-dependency multi-agent build, automation and review system for Claude Code. 18 agents, 23 skills, a live per-project dashboard, and a /setup-forge onboarding wizard. One command: /forge.

A tiny testable, self hosted, provider neutral agent runtime for teams that want control, conformance, and no framework lock-ins.

Local-first control plane for governing AI agent runtime behavior, from preflight risk checks to live mediation and post-run audit.

Deterministic terminology layer for AI coding agents: canonical vocabulary, drift detection, CLI + MCP server.

AI-first vertical (9:16) video editor engine — the LLM plans a declarative Timeline IR; a deterministic FFmpeg renderer executes. Drivable from Claude Code via MCP.

Backup brain for Claude Code. When your Claude Max plan hits its limit or Claude is down, flip one command and your claude -p agents keep running on a local mlx-lm model. Default Claude. Local only when needed.

AI Chat + AI Agentic-Coding + Websearch with agentic search support

Agent-neutral handoff and governance protocol for long-running coding-agent work

Route Telegram topics to isolated Claude Code sessions with persistent memory.

Open-source AI agent security scanner — 114 payloads, 8 OWASP categories, SARIF export

Agentic RAG learning project — Pydantic AI agent + FastAPI + Next.js + pgvector.

AI-powered agent that autonomously discovers and enters free sweepstakes using browser-use

Native macOS companion app for Claude Code. Tabbed PTY sessions, a real MCPs/Skills/Marketplace UI, GitHub-style usage analytics, in-place session restart. Signed + notarized Sparkle auto-updates.

Fast-track your agentic engineering skills with Claude Code guides, resources, and tips

⚡ Fast, lightweight API client supporting REST, GraphQL, gRPC & MCP. Built for engineers who value speed and simplicity.

AI Subscription first - no API key. A lightweight, file-based, dependency-free workspace structure for AI agents.

An agentic development environment for Julia: AI agents drive a keyboard-driven TUI + REPL to read, run, and surface code — and coordinate across sessions and machines.

High-performance Agentic AI Anime Recommender built with RAG Architecture. Uses Groq LLM (LPU) for sub-second reasoning, HuggingFace Embedding,ChromaDB for semantic vector search,Vector Indexing & LangChain for orchestration.Features a premium Streamlit UI, CI/CD, Dockerized environment, and Kubernetes((K8s)-ready ,Minikube, deployment on GCP/GKE.

AgentLoop — harness-agnostic, self-verifying autonomy wrapper for coding agents. Drives OpenCode/Kilo/Claude/Aider/Codex in a verify-gated loop with a held-out oracle, so the agent actually finishes and proves it is correct.

Persistent codebase memory for AI coding agents via inline @agent notes, repo-local skills, and lightweight Codex hooks.

Command a fleet of AI agents — one-command installer + risk-tiered review gate. GitHub & GitLab.

Don't let your agent delete the database. Hybrid static + LLM permission classifier for Claude Code, OpenClaw and Cursor.

A Claude Code skill that builds hierarchical, domain-agnostic agent systems from a single objective, via a central Designator agent. Self-building, cost-aware, model-agnostic.

🛡️ AI Agent 远程审批系统 - 支持 Cursor/Trae/Claude Code/Codex 等 9 种 AI Agent，通过飞书推送审批卡片到手机/手表/PC，守护你的代码与文件安全

Loop engineering for AI coding agents — shaping the whole run, not one prompt: a Markdown-first overlay of task records, role boundaries, verification evidence, and review gates that holds across multi-hour work

Develop Your Local Assistant — a local-first AI workspace that turns project work into validated deliverables (briefs, estimates, data models, mockups, test plans, decks), running on a model on your own machine.

Self-grounding autonomous coding pipeline for Claude Code. Agents classify → plan → build (test-seam slices) → review (binary gates) → compound, grounded in a project knowledge base of gotchas & risk checks, held to a Proof Contract: ships only when evidence artifacts prove it. Includes a runnable eval harness that grades every run.

Agentic-first notes and knowledge base service. Plain text API, agent-driven, single Go binary with JSON file storage.

This repository is a starter template for integrating DataDoe MCP with Claude Code CLI in a secure, team-friendly way.

AI-powered diabetes assistant. Scan food with your camera to get nutrition insights, track blood sugar, and manage daily habits.

Build an AI chatbot with LangGraph, RAG, and Gemini for accurate answers, workflow automation, and easy Streamlit access

A self-hosted, single-tenant AI learning system that generates structured multi-lesson courses from user-defined topics using configurable LLM providers (Claude CLI, API, or local models). The system uses a bootstrap configuration flow and serves generated content as static HTML accessible from any device.

Spec, Plan, Review, Implement, Verify; a complete AI development workflow plugin for Claude Code

Jibay Ai , the king of Iranian ai ✨

GroupMe archiving + AI bot: Postgres archive, login-gated dashboard, points leaderboard, and an AI archivist in the dashboard and as an @SKChats bot. Supabase Edge Functions + Cloudflare Pages. Source-available (AGPL-3.0 + Commons Clause).

Moodle.tj — образовательная платформа: курсы, тесты, встроенный компилятор, автопроверяемые задачи, ИИ-помощник, онлайн-библиотека и аналитика удержания. Работает на https://moodle.tj/

Browser-integrated LinkedIn companion offering intelligent job filtering alongside tailored application refinement.

Hyper Terminal 2026: Next-Gen Web Tech CLI ⚡ | Free & Open Source

Self-hosted GitHub review bot for your public and private repos — its own App identity, ~$0/mo on free-tier LLMs + Cloud Run.

Production QuickBooks MCP Server: AI-powered assistant, Azure/Docker deployment, OAuth automation, unified API. Fork of Intuit's official implementation with enhanced features: customer search, transaction analytics, multi-provider AI (GPT/Claude), and enterprise-ready deployment.

An India-specific personal finance assistant built with FastAPI, LangGraph, Groq (Llama 3.3), Supabase (Auth/Database), and Tavily. Supports real-time rate comparisons, precision financial calculators (EMI/SIP/Tax), and personalized query history.

Assistant pédagogique IA souverain et open source pour les enseignants, branché sur Albert API — la passerelle d'IA générative de l'État français (DINUM). Auto-hébergeable, RGPD, accessible. 🇫🇷

Intelligent vehicle management app with AI mechanic chat, maintenance tracking, VIN decoding, and diagnostics. Built with React Native, Expo, Firebase & Supabase.

An assistant-companion Neovim plugin over coder/claudecode.nvim: send a selection or motion to Claude as a review/explain prompt without leaving nvim.

Best Free AI Job Application Bot 2026 - Auto Fill LinkedIn, Greenhouse & Workday

Интерактивный фреймворк для написания текстов в Claude Code на основе методологии Julian Shapiro

HRMS Lite is an enterprise-grade, AI powered Human Resource Management System built with React 18, FastAPI, PostgreSQL, and LangChain. It enables intelligent workforce analytics, real-time attendance tracking, and secure people operations through a modern, scalable full-stack architecture.

Nept is a lightweight, AI-powered reconnaissance framework for modern penetration testing. It enables fast, modular, and automated intelligence gathering across domains, networks, and web applications with mobile-first design and intelligent analysis.

Local-first financial scenario analysis engine combining deterministic TypeScript calculations with optional LLM-assisted intent parsing and narrative output.

Claude Code for JetBrains IDEs — a native GUI client for Anthropic's AI coding agent. Streaming chat, editable IDE diffs, MCP and a deterministic security layer. IntelliJ IDEA, PyCharm, WebStorm, GoLand, Rider. No Node.js at runtime.

Browse a curated list of top AI tools, models, and frameworks to accelerate your development work.

Voice-driven extended reality. GPT Realtime hears you, GPT-5.6 Sol plans agentic, and Reframe segments the object and rebuilds the background from monocular depth and TSDF fusion without LiDAR.

Tecnia Bot — asistente educativo de IA para enseñar Arduino y ESP32 en escuelas técnicas argentinas (programa INET). Capa educativa sobre OpenCode, offline y de un doble clic.

Personal AI Infrastructure for Claude Code - 70 skills, 59 hooks, 20 agents, Algorithm v3.14.0

AI-powered side panel for DHIS2 (Chrome MV3). 32 tools — analytics, tracker writes, atomic metadata authoring (programs, datasets, category combos, sharing), rule/indicator audit + repair, backups. Any OpenAI-compatible provider; defaults to local Ollama, no API key. Authenticates via active DHIS2 tab session.

Convert Unreal Engine Blueprint clipboard text into compact, readable pseudocode — copy nodes in the editor, paste, and get the logic as text. Great for sharing Blueprints with LLMs, forums, and code reviews. Zero-dependency CLI + Streamlit GUI.

MCP server that turns Claude into an Ashby ATS copilot — re-engagement campaigns, deep pipeline reports, historical narratives, and personalized outreach.

Building for Doctors - AI Agent that converts doctor-patient conversation into structured notes, recommends ICD10 codes and saves to EHR after physician review.

A collection of 100,000+ APIs designed to power your agents 🤖

CLI and Python library for querying, navigating, and authoring Google Open Knowledge Format (OKF) bundles. Adds semantic search, link graph traversal, and agent-friendly progressive disclosure to plain markdown knowledge bases.

Manage your ongoing harness sessions and worktrees from a single place

Slack for agents: threads, flat replies, cross-thread links, pull notifications

metahub is building the missing infrastructure for AI tools, in the open — a registry that installs skills, MCP servers, agents and plugins into any harness, free publisher observability, and an eval framework going open source.

A Ruby gem with a C extension for scanning and redacting sensitive patterns (AWS keys, Italian fiscal codes, passport numbers, etc.)

Complete, verified command reference and comparison guide for Claude Code (Anthropic) and Codex CLI (OpenAI): every slash command, flag, and shortcut. FR + EN PDFs.

Reverse-engineered reference + MCP server for LinkedIn's internal web APIs (Voyager + SDUI). 130 endpoints, 26 MCP tools, browserless-first, honestly documented. Lets an AI assistant read & write LinkedIn.

PR and Code Understanding. Not just approval.

The largest index of MCP servers. 18,146+ Model Context Protocol servers searchable at protodex.io

MCP server: token cost math for LLM API calls, 69 models across 17 providers, prices verified by ComparEdge

A poweruser mail client for every plattform, free forever

Defensive /goal condition templates for Claude Code · 4-piece recipe · 6 patterns · 8 NEVER rules · 11-check linter · self-validating CI · MIT

Sugra MCP: connector between LLM agents and world data. 1,500+ endpoints aggregating 160+ primary sources across 36 data domains: markets, macroeconomics, company fundamentals, government, news, climate, maritime, and entity screening. Works with Anthropic Claude, OpenAI GPT, Google Gemini, xAI, and any MCP-enabled client.

Evidence-based design playbooks for Claude Code — rules synthesized from 407 real product sites: page-type playbooks with pattern frequencies, 9 style guides, per-site hex/type tokens, DESIGN.md generator. Free, local, MIT.

A schema-first GraphQL MCP server that avoids the 1MB introspection limit via typeNames/typeDepth scoping — built for federated topologies.

Bring Warp™ Oz™ to any IDE or agent via MCP — plus native @oz in VS Code Copilot Chat. OzBridge is an independent project and is not affiliated with, endorsed by, or sponsored by Warp.

Cross-platform PRD verifier for Codex, Gemini CLI, Claude Code, CI, and other MCP hosts. Deterministic Hard Output Rules, cross-section traceability, and a full 9-file PRD pipeline with calibrated multi-judge consensus where the host supports orchestration. 17 MCP tools · 1,503 tests.

A tested library of 25+ ready-made tools for LLM agents — web, files, data, math, text, datetime — with OpenAI schemas, Pydantic validation and pytest coverage

Pi extension that generates LLM tools from any OpenAPI/Swagger URL.

Model-assisted, rewind-safe compression and repair for Claude Code JSONL sessions.

MCP server for LLM-operable Midjourney image generation — compose, generate, inspect with vision, curate, log. 20 tools. Agent-first

Rust-native context compression for Claude Code, Codex & MCP agents: filters & compresses noisy tool output (tests, diffs, logs, JSON, provider traffic) before it reaches the LLM — fewer wasted tokens, full evidence recoverable. Local-first, Apache-2.0. Pairs with Code Explorer.

Local repository orientation layer for coding agents.

Read-only Model Context Protocol (MCP) server for WordPress + WooCommerce — give Claude and other AI agents access to products, orders, sales reports and posts over the REST API. By wppoland.com

Production-grade engineering skills and specialist agent personas for AI coding assistants. Orchestrates the full SDLC, from spec to ship, with structured verification gates, anti-rationalization checks, and senior-level engineering discipline.

Myco — the mycelial layer for your AI agents. A macOS menu-bar app that shares one skill across every agent (Claude Code, Codex, Cursor, Gemini CLI, Cline) and unifies their chat history.

Model Context Protocol server for Destiny 2 API integration. Provides player lookup, activity tracking, clan rosters, and item/perk resolution via local manifest cache. Built with TypeScript for Claude Desktop and other MCP clients.

HMAC-signed boundaries that keep untrusted LLM content as data, not authority

MCP servers exposing data and tools to Claude, Codex and other MCP clients.

AI-ready repository intelligence engine for Python & Node.js. Analyze codebases, detect frameworks, build project maps, and generate LLM-optimized repository context.

PGAutoPilot is a production-ready PostgreSQL MCP server that lets any AI assistant safely interact with PostgreSQL using natural language. It combines schema-aware query generation, enterprise safety controls, and a minimal-configuration setup into a single executable.

🏓 Bounce — Multi-layer AI provider failover gateway. UPS for your LLM tools. 多级 AI 提供商故障转移网关，让你的爱AI永不停机。

Token reduction & persistent memory for Pi coding agent.

Local, permissioned MCP server giving AI coding agents real Android dev tools — Gradle, adb, logcat, lint, crash triage — instead of raw shell access

MCP server over LS Securities OpenAPI — quotes, charts, screeners, ETF, program flow, and portfolio data for Korean and US markets, accessed in natural language.

Tool-agnostic agent workflow starter kit. One workflow core + team profile, generates adapters for Claude, Codex, Cursor, Copilot, CodeBuddy, Kiro, Trae.

A local-first, file-based memory CLI for AI tools. Own your context in plain Markdown — auditable, versionable, and provider-agnostic.

🛰️ Talk to any AI agent runtime through one TypeScript client. Provider-agnostic, ESM, zero-dependency.

Stops Claude Code from starting a task your usage quota can't finish. Local, zero-dependency CLI that warns or blocks prompts before you hit your 5-hour or weekly rate limit.