Code agents

🛰️ Orbit — turn any repo into a self-prompting agentic loop (memory + sub-agent team + skills + loop + hard stop conditions). A Claude Code plugin.

Give your AI assistant a face — a WebGL particle talking-head (~800k dots) that speaks with your own local Claude. Unofficial community project · CC0.

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

Read-only Steam MCP server for AI agents: 37 tools + prompts + resources across library, friends, achievements, store, reviews, sales, discovery, recommendations, and co-op planning. Official Steam Web API, bring-your-own-key, open source. On PyPI + the MCP Registry.

Puts a Pi agent on Telegram: your terminal session on your phone, and a secretary that replies to other people for you — built for a small local model, with strict context isolation and long-term memory per contact (I don't know TypeScript at all; this is mostly a local-model experiment, with occasional help from Claude Code)

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

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.

MCP server for RedM / RDR3: native lookups (hash ↔ name), semantic search, VORP, RSGCore, oxmysql, rdr3_discoveries community data. Hosted HTTP endpoint, no auth.

One agent proves a capability is safe. Every other agent — Codex, Cursor, Claude Code — reuses it instantly, without rebuilding or re-verifying.

mlx safetensors gemma4 4-bit quantized apple-silicon

safetensors qwen2 abliterated uncensored code qwen2.5

AI-Powered B2B Outreach Plugin 2026: Persistent Briefing & 40 Skills for Claude Code

Click any planet, moon, star, or galaxy to dive into a scientifically accurate profile — physical data, internal structure, exploration missions, and citations back to NASA, ESA, JPL, the IAU, Hubble, JWST, and peer-reviewed publications.

Decepticon 2026: AI Red Team Toolkit 🔓 | Autonomous Security Agent

Evidence-tested design, implementation, and review skills for AI coding agents. File-based handoffs across Claude Code, OpenAI Codex, sessions, and vendors—no shared chat required.

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

SAP ATC Checker - Run ABAP Test Cockpit checks with any check variant via SAP ADT API

Agent-friendly flight search and booking CLI and Skill for Atlas

Runtime security and policy enforcement for tool-using autonomous AI agents

30 production-focused examples: covering RAG patterns, hybrid search, routing, agentic RAG, knowledge graphs, multimodal RAG, and debugging.

Undetected browser automation MCP server - a stealth, anti-bot-resistant alternative to chrome-devtools-mcp for Claude, Cursor and AI agents. Powered by nodriver (bypasses Cloudflare/WebDriver detection). 65 tools, plus several isolated browsers at once so parallel agents never share a session.

This Agent Beats AGI? Prime Agent GitHub Tested Locally - Autonomous Recursive Multi-Agent Logic & Puzzle Solver harness inspired by Prime Intellect RLM architecture.

Focusing on building both MCP servers and clients using the Python SDK to make sure these three core primitives—tools, resources, and prompts—and understand how they integrate with Claude AI, Gemini AI, Copilot and Grok to create powerful applications without writing extensive integration code.

VulnFlow（渗透工坊） - AI 原生多代理渗透测试平台。由协作型大语言模型驱动的自主安全评估，具备基于 LangGraph 的代理编排、RAG 知识库，以及完整的安全工具链集成。

Multi-agent AI factory: one-line idea → researched, quality-scored project specification. LangGraph + FastAPI + Next.js, Claude web_search grounding, HITL gates.

Opt-in dual-agent workflow: Claude Code plans and reviews, Codex implements, deterministic gates verify, and you decide what merges.

Cut API bills 40–70% and stop rogue agent behaviour with a single static binary that sits between any agent and its MCP server — enforcing tool-level security, deduplicating and semantically caching calls, and exposing Datadog‑style observability.

Book recommendation system built from scratch and deployed with FastAPI. Includes subject and behavioral similarity as well and cold and warm users recommendations.

agent-Shield sits silently between your AI IDE (Cursor, Claude Desktop) and your computer. It continuously watches the Model Context Protocol (MCP) tool requests, blocking dangerous commands and API key leaks in real-time.

agman — agent manager: AWS_PROFILE-style config profiles for AI coding agents (Claude Code today; Codex, Gemini CLI on the roadmap)

Self-hosted clinical AI agent platform: deterministic drug-interaction & critical-value safety rules, FHIR R4 / CDS Hooks 2.0, PHI de-identification, RAG document vault, HIPAA-aware audit. FastAPI + LangGraph + Python.

Build one shared, permission-aware, auditable AI memory for an entire organization. A vendor-neutral blueprint you hand to a coding agent: 13 pillars, 70 decision forks, an M0-M15 build order. The org-scale sibling of RAG-OS and an alternative to Glean, Dust, M365 Copilot, Letta, and Zep.

High-autonomy config for opencode: ship features end-to-end with one command. 5 models, 5 families, zero interruptions.

PickleShell ChatGPT Plugin - Interactive sessions with your local AI agent from ChatGPT

Your own private AI workstation — frontier-class local models, a 15-tool agent, and secure remote access, all self-hosted on your GPU. No cloud, no API keys.

System design for AI, taught like a story — free, from zero to production.

A simple language aware Ruby chatbot for Telegram messenger using SimSimi API.

[Python] "Bring-Your-Own-Key" terminal based application allowing interaction with the OpenAI's GPT-3 artificial intelligence. It provides a chat mode, code generation in Python, C++, C#, Java, Javascript, TypeScript, PHP, Assembly, SQL, Bash, Ruby, Go, Perl, R, Matlab, Q# and more.

An Android chatbot application using Dialogflow

An open-source package that allows developers to easily integrate the power of OpenAI's state-of-the-art AI models into their Dart/Flutter applications.

Use Raspberry Pi + OpenAI to control home appliances from conversational interfaces e.g., Slack.

Python script utilizing OpenAI's DALL-E 3 API to generate images with AI from text prompts. It includes user input handling and returns generated image URLs.

💬 A minimal example template repository for utilizing your own APIs with ChatGPT actions. Inspired by Fireship's video and hosted for free on Vercel.

A sample speech transcription app implementing OpenAI Text to Speech API based on Whisper, an automatic speech recognition (ASR) system, built using Next 13, the React framework

A framework and module library that lets teams maintain coding standards, design systems, and domain rules once and automatically deploy them to all major AI coding assistants.

DevDuck is a sentiment-aware rubber duck agent.

K-LLM orchestrated code review for OpenCode. Dispatches 6 parallel review passes across different AI models, synthesizes findings with majority voting, and validates to eliminate false positives.

TechLearn is a revolutionary 🔥 learning management system specifically designed to empower African youth 👨‍💻👩‍💻 with cutting-edge technology skills.

Automate your computer with RuneFlow: record clicks and typing, replay workflows, and use anchor-based vision for reliable desktop control

Full-stack urban microclimate simulation — React frontend + FastAPI backends for LLM-orchestrated CFD, solar, and thermal comfort analysis via natural language

Physical hardware controls for Claude Code on the Logitech MX Creative Keypad — live status, one-press prompts, git, and offline voice.

Relocate Claude Code projects without losing sessions, memory, or worktrees.

Native Windows tray monitor for Claude Code usage — shows your rate-limit %, projects when you'll run out, and turns the icon red before you hit the limit. Plus a local 24h usage breakdown.

Local MCP server for Gmail, Google Calendar and Contacts — runs on your own OAuth credentials, keeps secrets in the OS credential manager

Vibe-code MicroPython apps for the EMF Camp Tildagon badge. Browser UI, Ollama or Anthropic, deploys over Web Serial.

Token governance for Claude Code: the top model directs, execution goes to the cheapest adequate means. Routing kernel, hook-enforced pre-budget, telemetry, statusline with plan quotas.

Podcast transcript API and MCP server — any published podcast as clean Markdown with real speaker names. For Claude, Cursor and other AI agents.

A local, agent-queryable mail intelligence layer — progressive mailbox index + MCP server that gives AI agents recall over your email without handing them the keys.

Ash — offline survival assistant for iOS. Gemma 4 E2B/E4B fully on-device (text · image · voice) with RAG-grounded answers over 56 emergency-response packs. Built for the Kaggle Gemma 4 Good Hackathon.

Multi-agent AI podcast production platform with anthropomorphic AI hosts for automated deep-dive content generation. 多智能体AI播客创作工具，人格化AI嘉宾自动生成深度播客节目。

숭실대 공개·개인 데이터를 MCP 도구와 REST API로 제공하고 인증·동의·장애 격리를 관리하는 비공식 백엔드

Companion source code for AI APIs in Practice, a visual engineering book on multimodal AI, agents, RAG, evaluation, governance, and production-ready products. Book DOI: 10.5281/zenodo.21431944 · Software DOI: 10.5281/zenodo.21419466

An Agent Skill that learns your web design taste from reference sites, remembers approved decisions, and applies them to new interfaces.

从零基础教程到生产级验证的本地 AI Agent / AgentOps 项目：RAG、审批、最小授权、幂等、崩溃恢复与密封评测

Open-source MCP-OAuth conformance scanner + IETF reference implementation of draft-ietf-oauth-identity-chaining-14 and draft-ietf-oauth-transaction-tokens-08. CLI + GitHub Action + hosted scanner + public registry. Apache 2.0.

A.I.M. – Actual Intelligent Memory: zero-token exoskeleton for long-running Claude/Gemini/Codex CLI agents. External SQLite memory, GitOps guardrails, DataJack cartridges. Alpha, trenches-first.

任务分拣器 🧭 让 AI 助手知道任务轻重缓急：小事直接做，大事走流程。基于 mattpocock/skills 的前置判断层

AI-driven talent value intelligence platform. Conversational AI agent + full agent toolchain, talent analytics (9-box/key-person/Pareto/compensation/succession/burnout), multi-system-type (enterprise/academia/public/training/gig), chat console to run all operations. 中文/日本語 supported.

可安装的开源金融分析 skill：穿透价格隐含预期、产业瓶颈、政策约束、利润池与一致预期反转。支持 Codex、Claude Code、OpenClaw。

Backend security Agent Skill that helps AI audit code, detect vulnerabilities, and generate secure-by-default backend applications, with deep Django/DRF coverage and guidance for any backend stack.

An undo button for AI coding agents.

Auditable project memory for Codex and Claude Code — source-backed Markdown, lifecycle states, no server or repo writes.

RENAMED → remem-mcp. Long-term memory MCP server for AI coding agents. Go to github.com/tinhien11/remem-mcp

Comprehensive collection of +460 production-ready Agent Skills (46 domains) conforming to the Agent Skills Standard, featuring native auto-discovery for Antigravity, Gemini CLI, Claude Code, Cursor, and Codex.

Alpha-stage CLI Coding Agent prototype

Universal novel-writing skill for AI coding assistants: 5-stage pipeline (interview, setup, craft specs, writing loop, revision & release), 28 craft specs, 34-writer technique library, 8 genre styles, memory system for long-series continuity.

RAG-based AI learning mentor with hybrid retrieval, citations, reranking, Gemini integration, RAGAS evaluation, and A/B testing.

AI工程纪律框架——从6次真实事故中长出来的29条规则。不是提示词模板，是让AI少犯错、犯了错能被抓住、同样的错不犯第二次的纪律系统。

One workspace. Any model. No lost context.

A local-first personal agent workbench with durable runs, shared memory, Obsidian RAG, Ollama, Open WebUI, and optional Codex handoffs.

Disturpe AI Chatbot is a self-hosted Discord conversation bot with provider-neutral AI configuration, local SQLite memory, configurable daily quotas, optional Discord logging, and privacy-focused defaults.

x2fromx - Convert project structures between directories and text trees. InOneClick!

A design-taste skill that removes what an interface doesn't need, then perfects what's left.

Run parallel AI agent tasks from a single terminal dashboard — uses your CLI subscription, no API keys required

A Codex skill for creating and editing draw.io diagrams through a configured drawio MCP server. 通过已配置的 drawio MCP server 创建和编辑 draw.io 图表的 Codex Skill。

A self-evolving project builder. Given a vision and spec, it autonomously builds and improves a project session after session. Just drop it into your existing project and go.

One writes, one reviews — worker 与 reviewer 上下文隔离的 AI 编码工作流 Harness，以项目验证命令、风险门禁和运行证据判断任务能否完成。

Auperator 是一个基于 DeepAgents 架构的智能运维系统，能够自动监控 Web 应用、收集日志、智能分析并修复问题，最终通过提交 PR 完成闭环修复。

Checks for jobs continuously (24×7) on a schedule you control Parses job descriptions, extracts skills & keywords, and scores matches to your preferences Sends notifications (Email + Telegram bot supported in MVP) Generates tailored, job‑specific CVs (Markdown → optional PDF via Pandoc)

Ready-to-run CrewAI multi-agent automation recipes powered by NVIDIA NIM (Llama 3.1 8B by default, 70B optional). Clone, set one API key, run.

Parallel Multi-Agent SEO & GEO Engine powered by Google Gemini

LangGraph multi-agent pipeline (Parser → Writer → JD-Matcher → Critic ⇄ Writer → Formatter) that generates JD-tailored resume/LinkedIn content using Groq/Llama, FastAPI, and Streamlit.

racket-coding-agent — AI pair programmer in your terminal, written in Racket — a multi-turn agentic loop (read, grep, │ shell, edit) with human-approved colored diffs, ESC-to-interrupt, and Fireworks AI under the hood.

Zero-trust runtime security & governance layer for autonomous AI agents — prompt injection firewall, PII masking, real-time policy enforcement.

Autonomous lab-machine engagement loop for Claude Code — Kali in a container, a skill that drives it, and a methodology that rewrites itself after every run

🚀 Proteus OS: An Enterprise-grade Platform with Multi-Tenancy & Micro-Kernel Architecture. Empowered by Agentic AI, Next.js, and FastAPI for seamless business automation.

A behavioural instruction system for AI coding agents.

Open Agent Security Fabric — red-team agentic AI, MCP firewall SDK, action oracles & SARIF CI gates. Assure, Enforce & Govern. Python + TypeScript. OWASP LLM/Agentic/MCP Top 10.

A vendor-neutral workspace that turns coding agents into a repository-aware AI engineering team.