Code agents

OpenAI-compatible proxy for assistant-ui.com free LLM endpoint. Supports streaming, tool calling, vision, and 5 models.

AI Skill Hub — a cross-platform desktop app to discover, dedupe, organize, and sync AI agent skills across Claude Code, Codex, and a shared pool. Ships an MCP server so your agent can run the whole library — install, align, organize, clean up — every write gated and reversible.

Drag-and-drop Kanban board that delegates coding tasks to AI agents — GitHub Copilot, Claude Code, OpenAI Codex, and OpenCode — with real-time streaming, task groups, and git worktree isolation.

transformers safetensors qwen2 text-generation code chat

🧠 Obsidian plugin that embeds Claude Code as an AI writing companion — smart context, undo, diff preview, multi-thread chat.

Implementation of Podlite markup language

Self-contained, Dockerized offensive security challenges for evaluating AI-powered penetration testing agents. Covers modern tech stacks (Node.js, Python, Go, Java, PHP, Ruby) across diverse vulnerability classes and target environments from basic injection to multi-step exploit chains, sandbox escapes, and defense-enabled environments.

A flexible PHP library providing access to various AI models (OpenAI, Claude, Gemini, DeepSeek and Grok) via a consistent interface.

VisionPower: portable image understanding MCP server for Codex, Claude Desktop, Cursor, and other agents.

Local, persistent and auditable memory layer for Claude Code, Codex, Cursor & Gemini CLI. Your coding agent stops treating you like a stranger every morning.

开源终端 AI 编程 Agent：以在线 Evidence Runtime 验证链（LLM 输出是 Claim、工具结果才是 Evidence）为核心。SWE-bench_Lite 官方评测 40.0% 实例级通过率（同模型 A/B +6.7pp，可复现报告）。7 种推理范式、MCP 工具、落盘补救与验证闭环。Python。

ISO 24495 Plain Language skills and Claude Code plugin

Enterprise-grade graph-powered code intelligence engine. Deep structural awareness for Laravel, PHP, Python, and JS. Powers AI agents with high-fidelity architectural context via MCP & Neo4j.

A golang library that unify all the llm into one interface API

☁️ DevOps & Cloud Infrastructure skill suite derived from iannuttall/claude-agents.

Claude Code skill that forces AI to understand before executing. Three disciplines: cognition check, requirement understanding, method search.

🤖 Sam-assistant is a personal assistant that is designed to understand your documents, search the internet, and in future versions, create and understand images, and communicate with you. It is built in Python, mainly using Langchain and implements most of Langchain

Fully automatic asynchronous AI operated Twitter bot using Large Language Models through OpenAI and Hugging Face to schedule and generate contextual content.

My first attempt at building an AI "agent". The agent will try iteratively solving Advent of Code puzzles.

Matter AI is open-source AI Code Reviewer Agent 🤖 for Code Review, Summary Generation, Bug Detection, Security Vulnerabilities and Tests Generation

The ChatGPT dialogue client utilizes highlight.js and marked for code highlighting and Markdown parsing. It supports MathJax for displaying mathematical formulas. Streamed data and smooth scrolling are employed to enhance the user experience.

Simple keras chat bot using seq2seq model with Flask serving web

Auto review or Auto generate unit tests form your code using openAI model gpt3 gpt4, support CLI command line tool

A simple PHP wrapper for the OpenAI GPT-3 API.

VSCode coding companion for software teams 🦆 Turn your team insights into a portable plug-and-play context for code generation. Alternative to GitHub Copilot & OpenAI GPT powered by OSS LLMs (Phi 3, Llama 3, CodeQwen, Mistral, etc.), made with ❤️ using FastAPI & Ollama.

What your tweets tell about you? Get personalized answers to your questions based on your recent tweets. Our website analyzes your Twitter activity to provide you with accurate and relevant responses to your queries

I thik that is a full function iOS ChatGPT app

Checkmate is a Spec Oracle Engine built for AI-driven development. It verifies that code changes made by autonomous agents actually deliver what your spec promised using real evidence.

Build production-ready AI agents in days, not months. Python 3.13+. Save development time with minimal code, deploy anywhere with confidence, and scale from simple assistants to complex multi-agent systems without the headaches.

LINE Flex 開發人員工具

Code and data repo for "DiagGPT"

Flexible Agent Framework for building Chat Bots, AI agents, and LLM microservices on the JVM.

Code for NeurIPS 2024 paper "AutoManual: Constructing Instruction Manuals by LLM Agents via Interactive Environmental Learning"

Privacy-first Apple Health analyzer — cross-metric insights, behavioral patterns, and health reports. Agent skill for Claude Code, Codex & Cursor.

AI-powered Kanban board with Claude Code automation. Tasks, real-time execution, feedback loops.

A complete Retrieval-Augmented Generation (RAG) application that demonstrates modern AI capabilities for answering questions about Ultimate Frisbee rules and strategies. This project showcases how to build a production-ready RAG system using cutting-edge technologies.

Light weight Claude Skills and Agents for every day tasks.

LangGraph Mastery Playbook: guided, code-first lessons for building memory-aware LLM agents and workflows with LangGraph, TrustCall, and LangChain.

A multi-agent research MCP server + mini client adapter - orchestrates a net of async agents or streaming swarm to conduct ensemble consensus-backed research. Each task builds its own indexed pglite database on the fly in web assembly. Includes semantic + hybrid search, SQL execution, semaphores, prompts/resources and more

HTTPS C&C Framework with encrypted beacons, web dashboard, and Windows agent.

The AI-native JupyterLab — open-source Cursor for notebooks. Cmd+K inline edit, multi-step agent with cell-level tools (read/edit/run), chat with @cell/@file context, ghost-text completion, one-click traceback fix. BYO model: Anthropic, OpenAI, Gemini, Ollama, vLLM. Local-first, privacy-first, fully open source.

The Mastercard Developers Agent Toolkit allows popular agent frameworks to integrate with Mastercard Developers Platform for service discovery and integration guides.

Official Code for "Continuous Locomotive Crowd Behavior Generation (CVPR 2025)"

A Rust-based agent orchestrator enabling a swarm of Claude Code instances building software.

VSCode extension that exposes GitHub Copilot through OpenAI and Anthropic compatible REST APIs, enabling external apps to use Copilot outside VSCode. Built with VSCode Language Model API to access Copilot's powerful AI capabilities.

Voice AI agent for reactivating cold leads through personalized calls, assessing their interest with AI agents, and syncing insights directly to your CRMs.

Python SDK for interacting with the Moorcheh Semantic Search API v1. Moorcheh provides ultra-fast, highly accurate vector similarity search and analysis capabilities based on information-theoretic principles.

👋 Claude Code & Codex harness insights dashboard — visual catalog and token analytics for skills, agents, plugins, hooks, memory, and more!

Advanced Mastra AI coding agent with secure sandbox execution, comprehensive file management, and multi-language support for Python, JavaScript, and TypeScript development workflows

An highly configurable desktop client for your favourite LLM

AI Lawyer is an intelligent reasoning legal assistant powered by DeepSeek , Ollama RAG and LangChain, designed to streamline legal research and document analysis. By leveraging retrieval-augmented generation (RAG), it provides precise legal insights, and contract summarization. With an intuitive Streamlit-based UI, analyze legal documents.

Deep research agentic system using Time Test Diffusion

Multi-agent AI platform on Cloudflare Workers — public preview (v0.1.x)

Symbiont lets teams build production agentic applications where every action is governed, every tool is verified, every agent has identity, and every decision leaves an audit trail.

Self-contained offline environment providing local AI chat, offline Wikipedia/content archives, IRC communication, audio streaming, file server, and development tools. Designed for zero internet dependency - download once, run anywhere. Perfect for remote areas, emergency scenarios, or escaping surveillance capitalism.

An AI marketing team you can clone and run in 30 minutes. 4 specialized agents, 5 skills, structured handoffs, persistent memory. Built on Claude Code.

10 installable Claude Code skills that turn your terminal into a GTM command center. ICP building, signal scanning, lead scoring, outreach sequences, battlecards. Built by Earleads.

The open-source foundation for production Voice AI. Build, scale, and own your AI calling infrastructure. Bridge legacy SIP to modern LLMs over ultra-low latency WebRTC pipelines. Zero platform fees, BYOK, and full data sovereignty.

AgentLimits is macOS widgets that display Codex/Claude Code usage limits and ccusage tokens, cost, heatmap

Agent-first Memory Bank skill pack for Codex CLI, Claude Code, and similar runtimes.

A simple utility to switch Codex accounts

memweave is a zero-infrastructure, async-first Python library that gives AI agents persistent, searchable memory — stored as plain Markdown files

Local LLM-maintained personal wiki, built on Karpathy's LLM-Wiki pattern. Runs on Ollama + Qwen3 + QMD.

Novel Engine is a desktop app that lets you construct novels. Seven AI agents handle the editorial pipeline — from pitch to published manuscript — while you focus on the story. Powered by Claude, Codex, and Ollama. Open source. Free. No gatekeeping.

Extract Google Maps business leads and enrich contact details using AI & web scraping

A business question goes in. A consulting-grade deck comes out. Four composable skills for Claude Code and Codex: strategy storyboarding, brand identity, pixel-perfect PDF, native editable PPTX.

Engineering-grade ROS 1 / ROS 2 skill for Codex, Claude Code, and Gemini CLI.

Build & connect smart devices using AI. Vento is your playground for building with AI, code and hardware — no limits, just creation.🚀🚀

Premortem skill for Claude Code — finds the concrete ways a plan could fail before commitment. Multi-agent silent scan, mitigation triplets, history snapshots, reverse-premortem. Klein 2007 + Kahneman outside view.

An open-source Android AI voice assistant built with Kotlin, Jetpack Compose, and on-device ML (BERT + TFLite, MediaPipe, ML Kit).

Clyro is a governance platform for AI agents. While most tools let you watch agents fail, Clyro stops failures before they happen, catching infinite loops, runaway costs, and policy violations in real time.

44 open-source financial skills for AI agents — P&L, budgeting, tax prep, debt payoff, and more. Works with Claude Code, Wilson, Cursor, Codex, and Paperclip.

EvE is an open-source framework for co-evolving ensembles of coding agents. Wrap Codex into an evolutionary loop that co-evolves solvers and agent guidance.

Open-source deep research MCP. Qwen3-30B-A3B-Thinking via OpenRouter, cited web synthesis for Claude Code, Codex, Cursor, Hermes and any MCP-compatible agent.

One key. Every model. Anywhere. — A curated map of AI API relay stations & LLM gateways.

AI agent skills and MCP integration for Credyt — real-time usage-based billing for AI products. Works with Claude Code, Cursor, Codex, and Copilot. Add wallets, credits, usage metering, and a customer Billing Portal to any project with a single prompt.

Korea's first legally-safe (Capital Markets Act compliant) finance MCP. 15 tools (ECOS · Real Estate · DART · KRX) + 2 Korea-unique synergy tools.

Baton — clean session handoffs: pass in-progress work to the next agent with a single verified markdown file. A Claude Code / Codex skill.

Agents, Commands and Pipelines for Claude code & other harnesses

AgentCat is an analytics platform for MCP server owners 🐱.

Sistema RAG con 6 arquitecturas implementadas como microservicios independientes en FastAPI + Docker: Naïve RAG, Advanced RAG, Modular RAG, GraphRAG, Agentic RAG y Hybrid RAG. Cada una incluye embeddings locales con sentence-transformers y se conecta a cualquier LLM vía API compatible OpenAI. Ideal para aprender, comparar y prototipar patrones RAG.

MIT-licensed, backend-agnostic AI agent orchestration loop in Python: orchestrator→worker→reviewer as a deterministic harness. Drive coding-agent backends through an MCP server + CLI.

Duckduckgo AI Chat to OpenAI API that can be used for free with gpt-4o-mini, llama-3.3, claude-3-haiku, o3-mini , mixtral-8x7b.

A desktop task manager for AI coding agents like Claude Code and Codex, with multi-project workspaces, live terminals, session tracking, permission-aware execution, Git integration, and usage analytics.

Claude Code account switcher, real-time usage monitor with a CLI, TUI and MCP

Caller-owned Discord operations for AI agents - 208 typed tools, safety controls, resumable guild builds, and Activity Evidence.

Own your LLM's web search: a local search->fetch->rank pipeline that replaces hosted web-search tools. Measured: matches hosted accuracy at 66% lower cost and up to 88% fewer tokens, plus a precision-tuned semantic caching with query-dependant TTL that no API offers.

A fast, local, indexed code search tool optimized for AI coding assistants. Written in Rust using Tantivy for full-text indexing.

CometChat docs search + implementation bundles: add chat, voice, video & moderation to your app through your AI coding agent.

Auditable multi-agent A-share factor research, knowledge base, long-only backtesting, AutoCombine and QuantCombine.

Open Swiss legal corpus + MCP server: 1M+ court decisions (1875–today), 21k laws, 10M-edge citation graph, 42 MCP tools. CC0 data, MIT code. Live at mcp.opencaselaw.ch

Synapse is a local-first personal memory operating system designed for AI agents. It provides durable, typed, and highly reliable long-term memory using only local SQLite — giving agents the ability to remember, update, and reason over facts across sessions with full user control.

OpenAI/ChatGPT library for Java - Requires JDK 11 at minimum.

💫 An AI-powered coding assistant, built to try out the ChatGPT API

An agent that accelerates scientific research by autonomously analyzing provided datasets,great for generating hypotheses, and validating them through code real quick with a single prompt

基于 claude code sdk 的 agent api，兼容Skills + Sub Agents

MCP server connecting AI agents to ITASCA PFC — run DEM simulations through natural conversation

My attempt at implementing retreival augmented generation on Ollama and other LLM services using chromadb and langchain while also providing an easy to understand, clean code for others since nobody else does

Analyze your code locally using a GPT LLM.