Code agents

RetroChat is a powerful command-line interface for interacting with various AI language models. It provides a seamless experience for engaging with different chat providers while offering robust features for managing and customizing your conversations. The code in this repo is 100% AI generated. Nothing has been written by a human.

Swift BPE Encoder/Decoder for OpenAI GPT Models. A programmatic interface for tokenizing text for OpenAI ChatGPT API.

AI-powered annotations for localhost development. Create visual feedback on your apps and let AI coding agents automatically implement fixes via MCP integration.

Native Agent CLIs manager for macOS. Ghostty + Codex app = Ghostex! Embedded browser. Strong agents support.

Research that compiles.

REST API service for ChatGPT to access your email ✉️🦜

caching proxy for OpenAI API, deployable as a Cloudflare Worker

Experimenting with AI our way into the unknown — monorepo: agentx (agentic code generation engine) + shadxn (component registry & transforms)

Using LangGraph to build reliable SQL Agent

Open source code of the paper: "OmniEval: An Omnidirectional and Automatic RAG Evaluation Benchmark in Financial Domain"

Visual planning and context control for shipping big apps with AI coding. Build from scratch or map existing repos. Dossier maps user workflows, sets agent context per feature, builds, tests and ships from one interface.

Temporal Code Intelligence platform. Time-series complexity analysis across Python, JavaScript, Java, and Go. Linear regression trend detection, cyclomatic complexity tracking, confidence scoring, and predictive decay forecasting.

Unified Python API for AI Batch Requests (50% discount on most providers)

Template for AI chatbots & document management using Retrieval-Augmented Generation with vector search and FastAPI.

LLM-based Dialect Translation System

Production-ready multi-agent orchestration framework for Claude Code. Features specialized AI agents, automated Git workflows, and comprehensive development automation.

An MCP (Model Context Protocol) server that turns all pybag Windows debugger functions into native MCP tools. It lets MCP-compatible clients (Claude Desktop, Claude Code, Cowork, OpenAI Codex CLI, Cursor, and custom agents) control user-mode processes, kernel sessions, and crash dump analysis via structured JSON calls.

The open source security engine for AI agent and supply-chain trust.

Context engine for large codebases, exposed through MCP. Gives AI coding agents precise repository context; benchmarked at frontier-agent quality with ~25x lower model cost and 45% fewer tokens with semantic search.

Self-correcting learning engine for Claude Code — persistent identity, behavioral pattern tracking, and cross-session memory

Free ChatGPT API reversed and simplified

This repo covers LLM, Agents, MCP Tools, Skills concepts with sample codes: LangChain & LangGraph, AWS Strands Agents, Google Agent Development Kit, Fundamentals.

🐶 Aibo - AI Bot Integration and Orchestration for Neovim

[Everything Gemini Code] A harness engineering toolkit for Gemini CLI & Antigravity. Tune the runtime around the model, not the model itself

Commander, your AI coding commander centre for all you ai coding cli agents

AI agents and Nix: parametrable skills/instructions and tools, packaged together in a reproducible and modular fashion

Production-ready multi-agent orchestration engine built on Google ADK. Database-driven agent config, 50+ LLM providers, MCP protocol, persistent memory, web dashboard, RBAC.

The Ultimate Agentic Vibe Coding Guide for AI IDEs like Windsurf, Claude Code, Cursor, Codex etc. – AI-optimized rules, best practices, and configuration files for efficient and controlled AI-powered coding.

Local AI API gateway for OpenAI / Gemini / Anthropic. Runs on your machine, keeps tokens counted (SQLite), offers priority-based load balancing, optional OpenAI Chat↔Responses format conversion, and one-click setup for Claude Code / Codex.

An installable, cross-framework AI organization: C-suite agents, expert subagents, curated skills, independent review, and one-command setup across 18 AI client/runtime adapters.

Session-scoped Claude Code agent for ComfyUI video production — 12 specialized skills for image gen, video, voice cloning, LoRA training, and publishing

Zero trust LLM gateway. OpenAI-compatible proxy with semantic routing and load balancing across OpenAI, Anthropic, Ollama, vLLM, and any compatible backend. Identity-based access, virtual API keys, and end-to-end encryption via OpenZiti

The explainable, local-first memory engine for AI agents. One ~9 MB binary fuses vector + graph + columnar under VelesQL; why() returns the evidence path behind every recall. No cloud, no glue code — runs on server, browser, mobile and desktop.

A proxy server that intercepts Anthropic API requests and converts them to OpenAI-compatible format, enabling integration with dozens of inference providers such as OpenRouter, Together.ai, Novita AI, and other third-party API services. Primary use cases include Claude Code and other Claude Agent SDK-based tools.

🦙 Opilot: Ollama for GitHub Copilot VS Code Extension – Run Ollama models locally and in the cloud within GitHub Copilot Chat

A modular, fully configurable DataviewJS dashboard for Obsidian — monitor Claude Code sessions in real-time, manage AI agent fleets, track 30-day analytics, and boost productivity with focus timer, quick capture, and more.

A practical framework for AI-Assisted Research in Mathematics and Machine Learning

50+ AI agent skills for Claude, Codex, OpenClaw etc — agentic marketing automation, AI creative agency, and developer productivity tools

Transparent proxy for Claude Code that auto-routes image-bearing requests to a multimodal model — so a non-multimodal primary model never crashes your long-running sessions.

Forge a working, testable, publishable MCP server in 30s. TypeScript or Python, with example tools, the Inspector and tests included.

Deep dive into Claude Code source — 512K lines of industrial-grade TypeScript agent architecture

Practical Agent Skills — English-for-engineers coaching, Pi Agent setup, and more. Install via npx skills add.

A floating, screen-aware Claude Code chat for Windows - it reads your screen to answer, and runs on your own Claude subscription (no API key).

transformers safetensors qwen2 text-generation code qwen

[ICLR 2026] Official Implementation of "FeatureBench: Benchmarking Agentic Coding for Complex Feature Development"

Windows 托盘上的 Kimi Code 用量监控：左键看额度，低额变红提醒。Tauri 2 + Rust，安装包仅 4 MB。

Open-source Agent Skills for planning, drafting, revising, and polishing SCI/SSCI papers—while preserving evidence, citations, and claim strength.

A terminal-first agentic development environment for macOS. Build for Claude Code, Codex, OpenCode and any TUI agent.

Testing and observability for multi-agent delegation, MCP tools, permissions, sandboxed actions, prompts, and workflow replay.

The proxy IP pool, crawling the mainstream free agent, automatically re -processing, automatically testing the availability of the agent, and the common request header has been attached

Bash Guard for Coding Agents

LLM Rag Intelligent Q&A Robot

Assembly block for finding and calling the windows API functions inside import address table(IAT) of the running PE file.

a sample project using Gemini, the Google's latest family of large language models.

Code for Paper: AriadneMem: Threading the Maze of Lifelong Memory for LLM Agents

Supplement of Copilot and Cursor - utilizes AI for batch processing of the entire codebase (对Copilot和Cursor们的补充：用 AI 批量处理项目代码)

A Context Compiler for TypeScript. Deterministic, diffable architectural contracts and dependency graphs for AI coding workflows.

The ultimate sketch to code app made using GPT4o serving 30k+ users. Choose your desired framework (React, Next, React Native, Flutter) for your app. It will instantly generate code and preview (sandbox) from a simple hand drawn sketch on paper captured from webcam

AI - a simple commandline local/remote LLM chat client. Supports any local or remote OpenAI-compatible API endpoint (GPT4o, Gemini, Grok, OpenRouter, Ollama, LM Studio and more), model and system prompt management, multiple conversations support, automatic topic identification and stdin piping (sending files to LLM for inspection)

🚀 Kaggle Problem Solver: AI-powered ML challenge automation Plan, code, and execute Kaggle solutions with intelligent agents. Boost your data science workflow! 🧠📊

Keep your orbit in the cloud galaxy. A typescript framework for DevOps Agent.

self-healing and self-learning loop for coding agents

Mesh-native protocol and Rust connector library for secure AI agent integration with external services: Twitter, Linear, Stripe, Discord, Gmail, GitHub, and more

Complete open-source AI collaboration suite and multi-agent platform featuring LLM orchestration, automation, and virtual assistants. Scales seamlessly from small deployments to large enterprise environments.

AI web scraper built with Crawl4AI for extracting structured leads data from websites.

You say it. AutoCode ships it. 48 skills. Code to deployment in one session. I-Lang v5.0 judgment + secret-safe deploys. Free forever.

用于自动化 OpenAI OAuth 注册与授权流程的 Chrome 扩展，支持 CPA 集成、自动取码与手动验证码接管。

Automated London flat/room hunt powered by Claude Code + Claude in Chrome + Gmail MCP. Scrapes 4 rental platforms on a cron, deduplicates via spreadsheet, prioritises HIGH/MED/LOW, and emails ready-to-send outreach.

A complete, modern, developer-focused handbook for mastering Claude Code, Vibe Coding techniques, AI-powered workflows, project planning with PLAN.md & PROGRESS.md, and intelligent agent-driven development.

An Agent Skill for vibe coding and AI workflow development。Built for when you hit these walls:Vague requirements → no baseline, endless rework、Only one prompt phrasing → can't tell if the problem is you or the model、Model says "looks good" → but features are missing 、great output last time, no idea how to reproduce it.

One .agents source of truth to sync MCP servers, skills, and instructions across Codex, Claude Code, Gemini CLI, Cursor, Copilot, and Antigravity.

学习 learn-claude-code 后的 PR Review Agent 实践项目：构建 Debate Council 多 Agent 审查、Tool Calling、结构化报告与 AI Judge 评估。

A Claude Code framework for multi-llm planning and development agents

Building a Senior Staff Engineer with Sub-Agent Teams in Claude Code

Three.js MCP server — inspect and edit scenes, materials, shaders, lights in real time from any AI agent

A Claude Code skill for authoring Workflow tool scripts: deterministic multi-agent orchestration. Preview of an unreleased feature.

Self-hosted AI agent system built on Claude Code. Multi-channel chat, persistent memory with semantic search, scheduled tasks, and a single-file dashboard.

Andrej Karpathy's LLM Wiki pattern as a skill & Claude Code plugin — turn accumulated sources into a self-maintaining, scalable markdown knowledge base.

Open-source, self-hosted AI phone receptionist powered by OpenAI Realtime API. High-fidelity speech-to-speech voice agent. Drop-in replacement for overpriced AI receptionist SaaS.

Legal flags a risk. Finance flags another. We connect and cite. Open-source forensic M&A due diligence: 13 AI agents read your data room across 9 domains (Legal, Finance, Commercial, Tech, Cyber, HR, Tax, Regulatory, ESG), cross-reference findings no single reviewer connects, and trace every one to an exact page & quote.

A Claude Code skill for web report decks — richer ECharts charts, one file per slide (edit one page, save tokens), and complex structure diagrams. 16:9 & vertical, PDF/image export.网页版 PPT 汇报的 Claude Code skill：ECharts 把数据画得更好看、每页一个文件改一页省 token、能做复杂结构图（架构/框架/价值链）。16:9 + 竖屏，导出 PDF 和图片

A mobile agent developed for Android, iOS, and HarmonyOS, allowing it to connect to Codex and other software on your computer so you can perform remote development and code editing from your phone.

Checkpoint/rewind extension for the Pi coding agent. 1 checkpoint per turn, /rewind command, diff preview, safe restore, redo stack.

Release-oriented agent skill hub and CLI for analyzing repos, installing high-signal Codex/Claude Code/OpenCode skill profiles, and safely tracking managed files.

Local outcome-loop + reward layer for coding agents — remember what worked, ship the next move, measure how it landed. Docs at nimroboai.com

Rust MCP server and CLI for serial/UART devices, with JSON macro automation and agent skills for repeatable timed workflows.

在自己的 Mac 上搭一套常驻、自愈、走订阅、墙内也能用的自托管 AI 伴侣 · 人看版讲思路，机看版给完整规格 · 文 / 小C & Grace

eBPF Information Flow Enforcement for AI Agent safety, security and effectiveness

transformers safetensors internlm feature-extraction chemistry text-generation

The standard library for agent-built SaaS

The official codebase for our paper, FLEX: Continuous Agent Evolution via Forward Learning from Experience.

Know what to fix next — local .pm governance skill pack for AI coding agents (Spec Kit–inspired).

一个生成 「影视飓风(Mediastorm)」风格中文口播稿 的 Claude Code / Agent Skill。

A powerful Python API, CLI, and set of Agent Skills for CX Agent Studio to automate, evaluate, and scale your agents with ease.

Control 1 or more machines using computer use tools that integrates with your agents

A companion for coding agents to help you understand large outputs

Production-Grade Autoresearch. Ideal for agent harness engineering, prompt engineering, ML model development, GPU kernels, and other optimizable code.

Run the pi coding agent as a service — triggered on demand, on a cron schedule, or by a GitHub or GitLab issue, comment or pull/merge request — in a container you control, with a durable queue, a spend cap, and a live admin panel.

Use Duckduckgo AI Chat to provide an OpenAI-compatible API that can be used for free with o3-mini.

A Chat Synced Discord Bot using OpenAI ChatGPT API & Firestore Database 🚀