Code agents

🔀 AI Coding Agent 模型切换器：为 Claude Code / Codex 一键切换 DeepSeek、Qwen、Kimi、OpenRouter 等模型，内置本地 LLM 代理、API Key 管理和 macOS 桌面版。

A pure-Python structured memory benchmark for multi-agent LLM systems — context graph vs vector RAG vs raw history dump, five scenarios, 18 graded queries, zero API calls.

Cascade orchestrates AI agents (Claude Code, Codex, opencode, LLMist) across your workflows in GitHub, Trello, Linear and Jira.

Filesystem-first LLM-Wiki + Obsidian + Hermes Agent memory system. Markdown source of truth, SQLite FTS5 search, secret scanning, tier-based memory. Built for local LLM setups.

Test harness for voice agents. Import from Retell, VAPI, Bland, LiveKit. Run autonomous simulations. Evaluate with LLM judges.

Deep Research skill for Claude Code — 3-cycle multi-agent adversarial ensemble methodology

A Claude Code Agent Skill for Vue.js development with TypeScript, emphasizing testing-first development, functional patterns, and maintainable architecture.

Tool to improve compiling proficiency for AI coding agents (i.e. Claude Code)

Mixture-of-Agents-X - utilizing the MoA framework in agentic coding tools.

A curated guide to convention files AI agents read, write, and act on: AGENTS.md, CLAUDE.md, SKILL.md, llms.txt, MCP configs, rules, and examples.

AI-native publishing system — build books like software. 6-phase pipeline from blank page to EPUB/PDF, with 16 skills, 7 agents, and 8 genre templates. Claude Code plugin.

Local-first markdown notes with a first-class MCP server. 16 tools + 2 resources for Claude Code, Claude Desktop, Cursor and any MCP agent. Per-folder permissions, semantic RAG via LanceDB, single Bun binary. AGPL.

Eco mode for Claude Code. /eco: -31% to -73% output tokens with critical findings intact; /eco-max: up to -75% with lowered effort. Measured hardest on Claude Fable 5 (fable5), deep-studied on Sonnet 5, works on Opus 4.8 too. We publish our negative results. 82 raw benchmark runs.

🦀 A Dynamic Island for your Mac's notch showing live Claude/Codex usage — 5-hour, 7-day, and credits with reset timers. Works with Claude Desktop, Codex, any browser signed into claude.ai, or the Claude Code CLI (terminal-only). Signed + notarized.

Cairn — an AI that walks your system and leaves a trail of tests: UI, API, unit, docs.

fak — the Fused Agent Kernel for Claude Code, Codex, Cursor, and MCP: use fewer tokens and do less repeated work with cache-stable model traffic, context compaction + crash resume, local repeat serving, nanosecond tool policy, and local GGUF inference.

transformers gguf code deepseek bf16 text-generation

transformers safetensors llama text-generation code granite

transformers safetensors phi4mm text-generation nlp code

transformers safetensors qwen3_next text-generation qwen qwen3

mlx safetensors qwen3_next text-generation conversational base_model:Qwen/Qwen3-Coder-Next

transformers safetensors qwen3_5_moe image-text-to-text text-generation-inference unsloth

Claude Code plugin & Agent Skills for AI-native development: codebase readiness scoring (/assess), Six Thinking Hats deliberation (/huddle), AI-slop removal (/deslop), skill hardening (/skill-forge), and more.

AI-native software delivery workflow for Claude Code and Codex: design, change, implement, test, review, and archive.

Use ChatGPT/Codex OAuth in Claude Code without an API key

Apache Camel-style integration framework for .NET. 30+ EIP patterns, 27 transports (Kafka, RabbitMQ, MQTT, S3, gRPC, SFTP, SQL...), fluent C# DSL.

Mindlas catches your coding agent drifting before the bad code lands. Real-time tracking and correction for context rot, unverified done claims, patch sprawl, and tool loops in your Claude Code session.

The memory layer for investment agents.

AKM — universal Agent Knowledge Management. A tool-agnostic Markdown knowledge OS for AI agents: memory / brain / vault over seven layers, with a Learn Back loop. Works with Claude Code, Codex, OpenClaw, and any agent.

Context Diet is a Claude Code agent skill for measuring system-prompt overhead, reviewing tool payload size, and reducing unused definitions through controlled settings.json configuration.

Local semantic code index and MCP server for Claude Code, Codex, and opencode. Includes semantic search, reuse checks, impact analysis, and a VS Code chat and agent supporting local CLIs and API providers—all powered by tree-sitter, SBERT, and ChromaDB.

Run Qwen Code as a coding agent through an OpenAI-compatible API.

Private, self-hosted document chat for attorneys: parse legal PDFs and query them with local open-source LLMs (Ollama) + verifiable page citations. One-click desktop app at docuchat.app.

Prepare any codebase for AI. Wires OpenCode, OpenSpec, codegraph, and agentmemory into a multi-agent development workflow powered by native parallel subagents.

Audit, clean, and harden a WordPress site end to end, with an AI agent (Claude/Cursor/Codex/MCP or SSH). Detects & removes hidden malware — cloaking, backdoors, database injection — scores your security posture, and hardens safely. Free, open-source (AGPL-3.0).

MUSE-Autoskill - A self-evolving LLM agent that builds, tests, and reuses reusable skills — getting smarter with every task.

An Emacs Lisp AI coding agent with multi-agent architecture, permission-based tool access, and LLM integration via gptel.

Athena is a desktop control surface for AI coding agents with shared project context. Built with Electron, React, and FastAPI, it embeds native terminals for Codex, OpenCode, Claude, and Hermes with Hermes memory integration. Features MCP bridge for cross-platform workspace control, embedded PTY terminals, native session discovery, and more.

📋 Prompt-engineering and project-roadmap plugin that crafts professional xml prompts and picks, surveys, and tracks your next tasks.

GitHub Pages website for oh-my-codex - multi-agent orchestration for OpenAI Codex CLI

A local-Llm-first coding agent. Runs Qwen 2.5 and Qwen 3

AI coding tools for InterSystems IRIS — single binary MCP server for VS Code Copilot and Claude Code

A/B test whether pre-gathered context helps coding agents (Claude, Codex, Cursor, Grok) complete tasks faster, cheaper, and better

AI 全链路音乐创作 SaaS — MiniMax API + FastAPI + React，支持 Agent 工具调用 / 歌词 / 音乐 / 翻唱 / 语音合成 / 声音克隆，带 docker compose 一键部署

A privacy-first macOS menu bar app for tracking AI coding quotas, reset times, token usage, and costs across 21+ tools.

Your AI works the night shift — read-only reviews of your projects while you're busy, one digest every morning.

Give any AI agent its own disposable Linux machine. Firecracker microVM sandboxing with millisecond boot times, full network access, and native MCP support.

AgentMesh360 Job Agent — agent-native job search CLI for Boss Zhipin, Liepin, Zhaopin, and 51Job. Built for Claude Code, OpenClaw, Cursor, and Codex.

Profanity-triggered self-audit protocol for coding agents (Claude Code, Codex CLI, Kimi CLI, OpenCode). Python stdlib only.

Local-first AI coding agent for desktop, terminal, VS Code, Visual Studio, and CI code reviews.

OpenCode vision support: automatically saves pasted images and guides non-vision models to recognize them via tool calling. Supports single & multiple images.

EvoX Genesis is an autonomous system for long-horizon software evolution that recursively builds, continues, and transforms complex software from high-level objectives.

Run GPT Responses inside the Claude Code harness with protocol-correct tools, agents, streaming, and compaction.

好想上岸 / JD-Scout · AI agent that analyzes any JD against your resume, built with LangGraph + Chroma RAG + FastAPI. Paste JD, upload resume, get structured match report and rewrite suggestions.

Install AI agent skills from Git into Claude, Codex, Cursor, and OpenClaw with a manifest, lockfile, and shared store

An Electron-based multi-project AI cockpit that orchestrates multiple Claude Code instances with a built-in AI supervisor for one-click dispatch, auto-monitoring, and report aggregation.

🔍 Model Context Protocol (MCP) tool for parsing websites using the Jina.ai Reader

Claude Code agent that routes to external LLMs (Grok, Gemini, GPT-5, etc.) via OpenRouter - just mention the model name

ContextAtlas — context infrastructure for AI coding agents: hybrid retrieval, project memory and retrieval observability via CLI, MCP server or embeddable library. Tree-sitter indexing, LanceDB vector search, FTS5 and token-aware context packing.

The Pentest Agent System is an autonomous penetration testing framework built on the MITRE ATT&CK framework.

Multi agent penetration testing AI

code for DyPS: Dynamic Parameter Sharing in Multi-Agent Reinforcement Learning for Spatio-Temporal Resource Allocation

Code for the NeurIPS 2023 Paper: Robust Multi-Agent Reinforcement Learning via Adversarial Regularization: Theoretical Foundation and Stable Algorithms

🔧 Base64 Proxy Tool - Cloudflare Workers代理工具，支持递归Base64解码、自定义UA和多层编码处理 A Cloudflare Workers-based proxy tool with recursive Base64 decoding, custom User-Agent, and multi-layer encoding support.

Multi-Agent AI system that automatically retrieves the latest Football news and creates a newsletter

Step-by-step plans for forking OrcaSlicer and adding Bambu printer support via a process isolation bridge. Fed to an AI agent — you follow along.

Bridge AI agent CLIs (Claude Code, OpenCode) to Discord via tmux - remotely control long-running AI tasks

An open-source AI agent for infrastructure debugging.

Clone into any startup repo. An LLM agent auto-generates and executes a marketing plan from your codebase. 7 distribution-first strategies.

Codebase context compiler for AI agents. Graph-ranked, token-budgeted, tier-compressed output. Smarter than the existing ones.

Formula WorkPaper and XLSX recalculation runtime for Node.js services and agent tools: edit cells, recalc, verify readback, persist JSON.

Agent Builder API - Backend service for Agent Smith extension

This repository demonstrates how to use AutoGen to integrate local and remote MCP (Model Context Protocol) servers. It showcases a local math tool (math_server.py) using Stdio and a remote Apify tool (RAG Web Browser Actor) via SSE for tasks like arithmetic and web browsing.

🚀 一键部署！支持语音聊天与数学逻辑处理! 基于各项LLM的 QQ 聊天机器人！支持 任意GPTLike的API，人设自定义,对话自然 🚀

Private AI Hub (P8Hub) - Host and use your own AI Services. Keep everything simple and private.

A fullstack web application implemented using Angular, NestJS and the Gemini API

CopperAI offers a hands-free, voice-to-voice interaction system with a Large Language Model (LLM)

Synced from GitLab - Deploy your own Serverless Telegram bot webhook to quickly interface with OpenAI's ChatGPT Completion API (gpt-3.5-turbo / gpt-4)

一个拥有长期记忆, 表情动作, 语音对话/打断/声纹识别, FunctionCall, 多模型支持的AI Waifu客户端.

Lightweight AGI: Building General AI with Golang and Flexible Language Models

Convert Python code into JSON consumable by OpenAI's function API.

Ask Me Anything GPT-3

This is an unofficial C# library for the OpenAI API. As there are no official libraries available, we have created our own to help C# developers interact with the API easily.

An elegant NodeJs library for openai api.

Welcome to the ProjectsHub Platform repository! 🚀Your go-to platform for hackathons, coding challenges, project concepts, and freelance tasks. Join now to explore, learn, and collaborate with fellow tech enthusiasts. Let's create something amazing together! 🚀

MediBeng Whisper Tiny improves doctor-patient transcription by training the Whisper Tiny model to translate mixed Bengali-English speech into English, making it easier for analysis, record-keeping, and using AI in healthcare.

Passliss is a web application that allows you to generate secure passwords, test the strength of exiting ones and more.

Based on the Evol-character framework and OpenAI API, enabling fine-grained role-playing data generation 🎭🧩.

Voice memos recorded from the microphone, transcribed offline to text and converted to Joplin notes

chatsnack is the easiest Python library for rapid development with OpenAI's ChatGPT API. It's an intuitive interface for creating and managing prompts, templates, and responses, making it convenient to build complex, interactive conversations with AI.

A lightweight coding agent that runs in your terminal.

LLM Platform Security: Applying a Systematic Evaluation Framework to OpenAI's ChatGPT Plugins

This repository contains a basic Node.js example demonstrating how to call functions using the OpenAI API. The example showcases a conversation with the OpenAI GPT-3.5 Turbo model, including making function calls and processing their responses.

SQL function for SQLite to directly query OpenAI's ChatGPT

Mashang Claude Code: 社区增强版 Claude Code 工具集，支持一键启动面板、多服务商接入与开发者模式。

💁 Example code for a blog post series about using a RAG system on a local codebase.

Open source NLA. Hosted service in private beta, signup now! Alternative to Zapier NLA

Use Gemini Pro LLM via VertexAI to create an engaging quiz game incorporating TMDB API data

The official codes for "Can Modern LLMs Act as Agent Cores in Radiology Environments?"