Code agents

Gen AI Large Language Model Projects

Alchemy's official MCP Server. Allow AI agents to interact with Alchemy's blockchain APIs.

A library for benchmarking the Long Term Memory and Continual learning capabilities of LLM based agents. With all the tests and code you need to evaluate your own agents. See more in the blogpost:

Codes accompanying the paper "RODE: Learning Roles to Decompose Multi-Agent Tasks (ICLR 2021, https://arxiv.org/abs/2010.01523). RODE is a scalable role-based multi-agent learning method which effectively discovers roles based on joint action space decomposition according to action effects, establishing a new state of the art on the StarCraft multi-agent benchmark.

Notion CLI with AI agent support. Smart queries, Obsidian sync, batch ops, backups, validation and more.

AI-powered text compression library for RAG systems and API calls. Reduce token usage by up to 50-60% while preserving semantic meaning with advanced compression strategies.

The easiest way to use Claude Code with any LLM. Install the app, pick your provider, done.

YGK-a: Your Genius, Knowledgeable assistant, An advanced ChatGPT client from your shell.

SWE-PolyBench: A multi-language benchmark for repository level evaluation of coding agents

A runtime-free MCP server that converts source code into AST🌲, regardless of language.

The first AI plugin that speaks first. Code-enforced learning + active forgetting + PAC (Proactive Accountability Challenge). Works with Claude Code, Gemini CLI, Hermes, OpenClaw.

Open Builder is an open-source AI-powered app generator. Build web applications through natural language conversations.

A skill that convenes a panel of CLI-based AI agents (Claude Code, Codex, Gemini CLI) to deliberate on engineering problems through structured multi-stage discussion, peer review, and synthesis

This repository defines AGENT.md, a standardized format that lets your codebase speak directly to any agentic coding tool.

EOC: open-source operating system for OpenAI Codex workflows with agents, skills, hooks, rules, memory, safety gates, and cross-harness adapters.

Web Graphical User Interface (GUI) for Gas Town multi-agent orchestrator - A companion interface for steveyegge/gastown

An agentic development harness for Claude Code, Codex & Cursor: gated pipeline from spec to green checks.

Composable agent runtime with enforced isolation boundaries

A visual workbench for coding agent orchestration for Windows, Linux & macOS. Chat interface for local & remote LLMs. Built with Tauri 2.x and Svelte 5.

Claude Code plugin: delegate to Codex, Gemini, Cursor, GitHub Copilot, and Qwen CLIs via their native protocols (ACP, ASP). Use /gemini:research, /cursor:debug, /codex:execute, /copilot:review and more — Claude can also auto-dispatch.

Open-source marketing skills for founders. Keyword research, growth strategy, social search audit, competitor analysis. Install with npx skills.

Ultra lightweight API server to convert files (.pdf, .docx, .xlsx) into formatted markdown.

Open-source AI customer support platform — AI chatbot with human handoff, Shopify & Slack integrations, visual workflow builder. Self-hosted alternative to Intercom & Zendesk. Apache-2.0.

Claude Code marketplace for audio plugin development skills.

Monitor Claude Code sessions, costs, config, hooks, agents & MCP servers from a single Rust binary — TUI (9 tabs) + Web interface with live process tracking, budget alerts, and 30-day forecasting

One shared macOS desktop pet for AI agents and apps, with MCP/CLI control and Codex Pets support.

Stop copy-pasting resumes. Maintain a single YAML timeline of your career, and let AI agents generate perfectly targeted resumes for every job application — in minutes, not hours.

Tau Coding Agent - like Pi, but twice as much

Kali Linux penetration testing skill for AI agents (Claude Code, OpenClaw, Hermes Agent). 200+ CLI tools, 15 scenario playbooks. Autonomously plans attack paths, selects tools, and integrates results across phases to adapt the penetration strategy — with human approval gates for high-risk actions.

Claude skill & plugin: turn Claude (or any LLM) into an MBB-grade management consultant. Case-interview coaching, strategy frameworks, market sizing, board-ready problem-solving. 129 reference modules. Free & open-source.

GitHub Actions bot that automatically reviews pull requests using the Claude API, posting inline comments and a summary on every PR.

Turn your team's AI coding sessions, GitHub code, and docs into one shared, searchable memory — a self-hosted git truth store you query right from your editor over MCP.

A Git-based package manager designed for AI-assisted development, similar to npm but supporting skills, agents, commands, hooks, and any AI resource types.

OMem (Office Memory) — local-first memory that automatically ingests your real work (mail, calendar, notes, files) from where it already lives, into a Markdown wiki any AI agent can query. macOS today; Windows coming.

ChatCLI is a command-line application that utilizes LLMs—such as those from Anthropic, OpenAI, and others—to facilitate interactive conversations within the terminal. At its core, it features a specialized agent and tools that provide unique expertise.

Pi extension: a persistent second model that reviews the main agent's work each turn and injects concise advice inline.

Top Autonomous Research Multi-Agent System for 2026 Lab Experiments

Search-Then-Verify natural language querying over time series databases (ICML 2026). Includes NLQTSBench.

A configurable Bash/PowerShell loop that runs an AI coding CLI with a fresh session each iteration

🤖 A collection of AI agent skills that automate recurring engineering workflows that can be installed across multiple AI coding assistants.

A Model Context Protocol (MCP) server that exposes PyMOL as a typed tool surface to your agent (Claude Code/Desktop, Codex, or any MCP-compatible client)

transformers safetensors internlm2 text-generation conversational custom_code

transformers safetensors gemma4_unified image-text-to-text gemma4 coding

An Agent Skill to watch the deadlines of latest AI conference.

Official code for "MemGUI-Agent: An End-to-End Long-Horizon Mobile GUI Agent with Proactive Context Management"

小红书图文内容工作台：用 Codex Agent 完成热点研究、内容拆解、原创文稿、去 AI 味、品牌配图与人工确认发布。

BingoCode is a lightweight, open-source CLI orchestrator inspired by Claude Code. It encapsulates powerful AI-driven development capabilities into a streamlined terminal interface, allowing developers to bring their own LLM providers (BYOK) to a local-first, low-latency coding environment.

small coding agent in go

Rust-first reimplementation of a local agent CLI inspired by Claude Code.

Nix flake for earendil's pi, a terminal coding agent.

Providing Duckduckgo AI Chat API, which can use o3-mini for free.

Structured outputs for LLMs

ScrapeGPT is a RAG-based Telegram bot designed to scrape and analyze websites, then answer questions based on the scraped content. The bot utilizes Retrieval Augmented Generation and webscraping to return natural language answers to the user's queries.

The GenAI API wrapper for Delphi seamlessly integrates OpenAI’s latest models (gpt-5 serie), delivering robust support for agent chats/responses, text generation, vision, audio analysis, JSON configuration, web search, and asynchronous operations. Image generation with gpt-image-2. Skills and agents

🚀 Next-generation AI code assistant with Multi Agent methodology

A Java Lib for Google-Bard API (Reverse engineering of Google's Bard API)

Materials for the Call for Code 2020 solution starter kit for crisis communication in the context of COVID-19.

High-performance .NET BPE tokenizer — up to 618 MiB/s, competitive with Rust. Zero-allocation counting, multilingual cache, o200k/cl100k/r50k/p50k encodings + HuggingFace tokenizer.json support.

Early Alpha: A GPTBuilder-like Interface for OpenAI's New Assistant API.

mr-agent: A Node.js service that auto-triggers AI-powered code reviews when receiving Git merge request webhook events. Integrates with GitHub/GitLab/Bitbucket to analyze changes, flag issues, and suggest improvements—streamlining reviews for teams of all sizes.

Live view of Claude Code sessions and the ability to search them

A Python crawler tool that can automatically simulate browser operations to crawl all users' tweet content and save all static resources (videos, pictures) locally without calling the Twitter API. Use the selenium library.

A toolkit that makes Claude Code better at engineering — session memory, dependency analysis, large file navigation, 18 specialist agents, and crew teams for parallel multi-branch work.

🧠 Reverse-Engineered Python Client for ChatGPT Web Conversations

Distributed AI agents that work everywhere with no-code UI

OpenShield is a new generation security layer for AI models

Welcome to GPTNicheFinder, a powerful niche research tool powered by Google Trends data and OpenAI's GPT model. This application provides a streamlined approach to identify profitable niche markets by leveraging data-driven insights and cutting-edge artificial intelligence.

Welcome to AI Agents Handbook — your all-in-one guide for building AI agents, from basics to advanced techniques. Explore code, tutorials, and resources for beginners to experts!

MDM-ready scripts for detecting and monitoring OpenClaw (clawdbot, moltbot) on managed devices. Detect, audit and secure shadow AI agents across macOS, Linux and Windows endpoints.

[NeurIPS 2024] GenRL: Multimodal-foundation world models enable grounding language and video prompts into embodied domains, by turning them into sequences of latent world model states. Latent state sequences can be decoded using the decoder of the model, allowing visualization of the expected behavior, before training the agent to execute it.

🧠 High-performance persistent memory system for Model Context Protocol (MCP) powered by libSQL. Features vector search, semantic knowledge storage, and efficient relationship management - perfect for AI agents and knowledge graph applications.

Secure clipboard sharing over SSH for remote work and agentic coding tools.

Lightweight markdown-based workflow for collaborating with AI coding assistants using spec-driven development methodology

[NeurIPS'24] RedCode: Risky Code Execution and Generation Benchmark for Code Agents

Code repository for "Building Agentic AI" by Sinan Ozdemir. Practical examples, experiments, and implementations covering LLMs, embeddings, agents, RAG, fine-tuning, and optimization.

A unified, self-hosted platform for testing and debugging regular expressions. OpenRegex uses isolated polyglot micro-workers to guarantee 100% native engine consistency, featuring ReDoS protection, real-time analysis, and an AI-powered assistant.

Development Plugin for Avalonia

🇨🇳 claude-howto 完整中文翻译版 · 基于 luongnv89/claude-howto

Local-first agent plan annotator

Code intelligence CLI — function-level dependency graph across 34 languages, 34-tool MCP server for AI agents, complexity metrics, architecture boundary enforcement, CI quality gates, git diff impact with co-change analysis, hybrid semantic search. Fully local, zero API keys required.

Python port of Claude Code's agent-runtime architecture, on LangChain

A judgment layer for AI coding agents - make your AI think, verify, and communicate like a senior engineer

Coding Agent Session Manager

A coding agent CLI powered by DeepSeek V4 Flash

Unified API for running OpenCode, Claude Code, Codex agents

A collection of structured AI agent skills that enable Claude Code, Cursor, GitHub Copilot, and other AI coding assistants to create, operate, debug, and govern Harness CI/CD workflows through natural language.

Visual polish and useful context for the Pi coding agent TUI

A round AMOLED desk display for your live Claude Code usage, weather, background-agent health, and a daily voice greeting. ESP32-S3 + macOS BLE daemon. Fork of Clawdmeter.

Antigravity 2.0 不开启 TUN、无需使用 Proxifier 的登录代理修复方案。通过提供已配置好的 version.dll 和 config.json，让 Antigravity.exe 与 language_server.exe 走本地代理，解决 Sign In、Agent 初始化以及 daily-cloudcode-pa.googleapis.com 请求超时问题。

专为数学建模竞赛设计的数模 Agent Skills：MCM/ICM 美赛、CUMCM 国赛、华数杯、M3、HiMCM 等，面向 Claude Code 与 Codex 的获奖级建模工作流。Math modeling contest skills for Claude Code & Codex.

AutoConference is an Open-sourced AI-agents platform that simulates an openreview-style autoresearch conference with AI acting as every researcher role in the AI conference submission - publication cycle including researchers (authors), reviewers, ethics reviewers, area chairs, program chairs, etc.

BootAgent is a local management tool of AI agents. It turns a fresh machine into a usable, repeatable setup without asking you to edit several tool-specific config files by hand.

Cross-platform compatibility layer for AI agent skills — pre-flight dependency checks, MCP-native, works with Claude Code, Cursor, Codex CLI, OpenCode and more

Google Gemini CLI with Rust (Previsouly Bard)

Quantitative trading research infrastructure for AI Agents - backtest, sweep, radar, deploy

Low-overhead Java agent for the Autonomous Verification Layer. Captures real runtime traces, SQL queries, and HTTP payloads in Spring Boot apps to enable trace-based testing.

AI-powered browser automation for Go — describe tasks in plain English, let the agent handle the clicks.

Auto-Use Computer Use — drives your OS, browser, scours the web, writes your code. One agent, end to end.

Connect instant messaging bots to your APIs.

NLP Cloud serves high performance pre-trained or custom models for NER, sentiment-analysis, classification, summarization, paraphrasing, intent classification, product description and ad generation, chatbot, grammar and spelling correction, keywords and keyphrases extraction, text generation, image generation, code generation, and more...