Code agents

A coding assistant built on persistent multi-agent teams: durable members that discuss, chat, and re-sync continuously — Discuss -> Code in parallel -> Sync -> Verify together.

No API keys required. Transform the native ChatGPT, Claude, and Gemini web interfaces into fully autonomous local coding agents.

Use OpenAI Codex models in GitHub Copilot Chat with ChatGPT OAuth

本地优先的 AI 求职 MCP Server：一句话搜索 BOSS直聘、猎聘、智联、前程无忧，按简历排序并追踪新增与已投岗位。

Lightweight observability for multi-agent AI pipelines. Self-hosted, no cloud dependency — add two lines of Python and see real-time agent events, DAG graphs, token usage, and session history on a local dashboard.

Image generation CLI that reuses your Codex (ChatGPT) login.

中国+海外双市场 Flutter+NestJS 多平台 App 开发 Agent Skills：三 flavor 发布/第三方登录/测试/CI-CD/可观测性，适配 Claude Code、Codex 等

Turn your team's unwritten code-review conventions into rules your AI coding assistant follows.

Curated repositories for building and running development workflows with OpenAI Codex.

Track LLM token usage, enforce rate limit & budget policies, and trigger alerts across OpenAI, Groq, OpenRouter, and AWS Bedrock.

Think first, then code. Where Claude Code and Codex jump straight to writing, this stays review-first: a code reviewer, security scanner, root-cause debugger, and code generator, all in one shell-native loop.

🔍 AI-powered code auditor using Rust & Ollama. Features agentic tool-calling architecture where LLM autonomously explores, reads, and analyzes codebases. Detects security vulnerabilities, bugs, and performance issues. Generates detailed Markdown reports with actionable insights.

Markdown-first, human-gated multi-agent editorial workflow with explicit research, planning, writing, and review artifacts.

Two-way communication bridge between Claude Code sessions using the Channels API

Orkestrai is a visual orchestration tool for teams of AI agents that can work ranging from ideation, planing, architecture, design, devops, content creation and marketing..

A terminal AI coding agent. Autonomous by choice, gated by trust.

Multi-Agents VSCode Extension that Focuses on the Full Control of Context, Observability and Auditability. Works like Wakaba Mutsumi's Personalilties 🥒. 吓我一跳我释放忍术😰若叶睦那么多首啊🥷

🧭 Let your coding agent off the leash — not off the rails. Guardrails, a hard budget cap & a self-fixing PR loop for Claude Code / Codex / Gemini. Eval-gated 100/100, you always merge.

Jump to any agent session across Cursor, Claude Code, OpenCode and more. See all your chaos in one place and feed your need to context switch.

Agent Skills for small-molecule and protein therapeutics: cheminformatics, molecular ML, docking and dynamics, protein design platforms, and target-discovery knowledge graphs.

Preserved-layout English-Chinese PDF translation for Zotero using Codex or OpenAI-compatible APIs

The open-source CMO: growth playbooks from 16 operators (Cursor, Notion, Linear, Deel, Gamma, Granola...) as an installable AI skill

Open-source, self-hostable server and runtime core for Run402 — backend infrastructure for AI agents. Postgres/PostgREST with RLS, storage, routing, functions and portable project archives. Apache-2.0.

MCP Server for Development Tooling - Project Detection, Process Management, and Reverse Proxy with Frontend Instrumentation

Universal SAP skills and agents for Claude Code — FI, CO, TR, MM, SD, PP, HCM, SFSF, ABAP, S/4 Migration, BTP, BASIS

Claude Code | Codex plugin for React Native — explores codebases, designs architecture, implements features and QA the code in provable way

Native Windows GUI for Oh My Pi: sessions, models, providers, MCP, plugins, context, and browser tools.

Constitutional governance runtime for autonomous AI agents

Reliable research infrastructure for AI agents. Evidence-backed web search with citations, confidence scores, and Clarity anti-hallucination. MCP server, REST API, Python SDK.

Complete 21-phase local business SEO audit plugin for Claude Code — 24 skills, 36 commands, 6 sub-agents, AI visibility, competitor analysis, and actionable roadmaps

A Retrieval-Augmented Generation (RAG) application for querying legal documents. It uses PostgreSQL, Elasticsearch, and LLM to provide summaries and suggestions based on user queries. Features data ingestion with Airflow, real-time monitoring with Grafana, and a Streamlit interface.

The pit crew for agentic coding.

🦴 paleo — token-saving skills for LLM agents: compress output, trim context, cap budget (Claude Code / Codex / Gemini / Hermes)

一个 Skill，只装一次。本地优先、无需账号的 Agent Skill 管理工具。

Spec Kit + Roo Code integration starter: one-command setup, 7/10/17-mode AI teams. Roo Code sunset May 2026 - Zoo Code (community successor) compatibility untested.

A service-agnostic proof-of-intelligence gate. Issues escalating challenges and mints offline-verifiable proofs to tell intelligent agents from dumb scripts

API-free Douyin/Taobao/Tmall/Qianniu customer-service connector: signed webhooks, normalization, idempotency, human review, BossAI intake.

AI Terminal Manager — unified session history for Claude Code, Codex, Gemini CLI, opencode and Pi, plus a persistent tmux sidebar

A local-first job-search assistant: watches your email, chats and calendar, finds roles worth your time, and surfaces the few things that need you today. Never applies or sends without approval.

Build and verify browser-native HTML presentations for laptops and projectors.

Meta-prompt system that writes prompts: raw idea in — a polished, model-specific prompt out. Cross-model (Claude, Gemini, GPT, DeepSeek, Grok, Qwen, Kimi, GLM), 8-agent QUORUM council, SCOPE.HELM, live model specs. v8.4.8, four editions, Claude Code / Cowork plugin.

RoboClaw live robot lab — community, experience, and API. Star to unlock the Host Concierge.

A general-purpose, multi-provider AI agent engine. Tools, orchestration, persistent memory, and application integration through terminal, headless, and ACP interfaces.

中文 GBrain 实操手册 for Amazon sellers: build an AI-native second brain with real commands, examples, governance, and Agent workflows.

Research Software Engineering skills for AI coding agents

Autonomous Penetration Testing Agent Framework with External State Memory & Anti-False-Falsification Guardrails.

😼 AI-участница Telegram-чата с памятью, локальными мемами, реакциями и собственным характером

Multiple ChatGPT subscriptions in one Codex desktop app — switch accounts, per-account usage, original app untouched. macOS.

Efficient, Evidence-based, Opinionated vibe-coding pipeline for CC / Codex / OpenCode / Antigravity / Pi

Awesome list for Claude Sonnet 5: announcement, pricing, API docs, migration from Sonnet 4.6 and reviews.

Interactive UI for AI agents — turn structured questions into browser forms.

DSH (DeepSeek Harness) web GUI plugin collection — task notifications, provider usage, LAN proxy, MCP manager, file-preview redirect, isolated browser verification. Targets dsh 0.1.5-rc.1 (rc only, no alpha). Install: dsh plugin --profile web add @wingsky-1/dsh-plugins-all

Evidence-backed audits, evaluations, and measured improvements for any AI agent.

The same HTTP API in 10 languages at 3 sizes, 30 implementations. Token cost for LLM agents, plus cold start, latency, throughput, CPU and memory. All measured, all verified over live HTTP.

Turn a written trading strategy into a MetaTrader 5 Expert Advisor with an AI coding agent. Headless MQL5 compile, headless Strategy Tester, and the nine silent failures of the MT5 command line.

Zero config documentation framework - Let AI write the Markdown. Let seemore show it better.

Agent skill that turns scripts or fact lists into Vox-style paper-collage explainer videos — narration-first pipeline with AI-generated cutout imagery, limited-frame animation, music, and ffmpeg assembly.

Local repo-intelligence index + MCP server: semantic search, symbol/graph navigation, impact-surface preflight, git + GitHub papertrail, and a source-anchored memory graph.

Live code graph that fuses static analysis (tree-sitter) with OpenTelemetry runtime traces, queried over MCP so AI coding agents get real full-stack context.

Let AI Agents control your real firefox browser: fill forms, authenticate, automate actions, web development; all via token-efficient, easy to use CLI. Claude plugin / Codex skill included. agent-browser, but for Firefox chads.

Voice agents in YAML, compiled to Pipecat or LiveKit. Production code you own, deployed anywhere.

Zero-trust security gateway between AI agents and MCP servers: scoped capabilities, redaction, rate and cost limits, and verifiable session logs.

Test mode for your integrations, built for the way agents build

A curated guide to agentic engineering: building and shipping software by directing AI coding agents. Harnesses, context and loop engineering, spec-driven dev, evals, and real production case studies.

Pipeline-driven task management for AI coding agents — stages, dependencies, artifacts, and multi-agent collaboration

A curated list of Claude Code, Cursor, and Copilot skills and plugins built for students: IB, IGCSE, college-bound, and anyone studying with an AI coding agent at their side.

Free web search and page fetching for agents. Hosted MCP, no API key required.

Open-source AI security platform providing perimeter defense for LLMs and AI agents through swarm analysis, policy enforcement, adversarial testing, and real-time threat detection.

Trace how a silent tool failure taints a whole agent run: dependency graph, taint paths, and grounded or tainted verdicts.

Shared memory & coordination layer for AI coding tools. Local-first, no cloud, no MCP required.

Run Claude Code and Codex agents as a team: long-lived sessions, a durable mailbox, human approval gates and per-task token accounting, scheduled by code rather than a manager LLM.

A self-hosted web interface for the pi coding agent.

OpenAI Responses streaming + validated tool calls in FastAPI. Offline demo, bounded sessions, cancellation, and failure tests.

macOS menu bar app: Claude quota with pace

Serveur MCP pour l'API BoondManager (ERP/CRM des ESN) : 182 outils, 12 prompts et 22 ressources pour piloter candidats, consultants, opportunités, projets, CRA, notes de frais et facturation depuis Claude. TypeScript, transports stdio et HTTP (OAuth2). Un projet Silamir.

Repository of code examples for the book "Data Science First: Using Language Models in AI-Enabled Applications" -- Broken down into case studies using data from media, education, telecommunications and investment research.

Another WhatsApp bot with super clean code design. Written in TypeScript.

ForOpenAI - A Fortran library for OpenAI API.

Autonomous ChatGPT AI experiment written in Delphi

Translate subtitle using OpenAI-compatible APIs

Claude Max usage monitor for macOS menu bar

Systematic debugging methodology for AI agents and developers. Prevents common anti-patterns like patch-chaining and wrong-environment restarts.

Lightweight Python SDK for LLMs with unified API across 9 providers. Built-in ReAct & Plan-Execute agents, streaming, native tool calling, context injection, structured outputs, and observability.

Peer-to-peer communication for AI coding agents. 8 MCP tools, full CLI, Python client. Part of the Qualixar research initiative by Varun Pratap Bhardwaj.

Secure your AI Agents against prompt injection attacks

Agent-native marketing cli: 51 skills, 5 research agents, brand memory that compounds, plus a local Studio dashboard (beta). single agent-native cli, then /cmo in ur coding agent..

Open-source framework for stress-testing LLMs and conversational AI. Identify hallucinations, policy violations, and edge cases with scalable, realistic simulations. Join the discord: https://discord.gg/ssd4S37WNW

Liquefy is a local-first OpenClaw vault system for packing, verifying, searching, and auditing agent runs with domain-aware compression, policy/redaction, and proof artifacts.

Expose typed web-app actions to MCP-compatible AI agents over WebSocket. TypeScript SDK + matching MCP gateway.

Coding agent skills library for programming workflows | Claude Skills, Codex Skills | Forked from obra/superpower

LUMIN: Your data analysis companion that turns natural language questions into powerful insights through AI-driven visualizations and clear explanations.

This repository contains a simple but powerful chatbot built with Streamlit, OpenAI, and LangChain. The chatbot maintains conversational memory, meaning it can reference past exchanges in its responses.

AI agent converting natural language to Neo4j Cypher

Gemini Bot is a Flask based chatbot app, powered by Gemini-Pro-Vision model from Google's Generative AI service.

Developer MultiGroups canlı yayınında kodladığımız PDF yorumlayabilen bir sanal asistan.

A CLI interface that allows you to interact with ChatGPT from your terminal using an API key.

"Build Generative AI Apps with LangChain" is a repository that contains a comprehensive framework for building generative AI applications using LangChain, an innovative language modeling platform. This repository includes all the necessary code and documentation to help developers quickly build and deploy generative AI applications

This Repositry is an experiment with an agent that searches documents and asks questions repeatedly in response to the main question. It automatically determines the optimal answer from the current documents or recognizes when there is no answer.

AI-powered fundamental analysis platform. TimescaleDB, CrewAI agents, portfolio optimization, pair trading, and automated alpha extraction.