Code agents

The Financial Research Analyst Agent is a hierarchical multi-agent system that provides comprehensive stock analysis by coordinating 11 specialized AI agents, 20+ analysis tools, a RAG knowledge pipeline, and a multi-provider data layer — all accessible through a Streamlit web app, REST API, and CLI.

Open-source Legal AI workspace for evidence-grounded legal drafting, matter analysis and verifiable answers.

A curated collection of AI-powered skills, agents, prompts, and workflows for Android, iOS, Flutter, React Native, Unity, and Unreal developers. Build faster, debug smarter, review code, optimize performance, automate tasks, and ship high-quality apps and games with reusable AI productivity tools.

An Orchestrate multiple coding agent desktop app

One line of intent → a presentation-grade, dark-editorial HTML deck. A Claude Code skill.

Opinionated AI agent skills for building applications with MotherDuck

Code for AdaJEPA

Collection of extensions and themes for Pi Coding Agent

Let coding agents see your browser.

This repository contains a collection of templates for building and deploying Gemini Managed Agents using the Gemini API.

Persistent memory and codebase intelligence for AI coding agents, indexes symbols, tracks sessions, and exposes structured project knowledge through an MCP server so agents stop re-reading files and start building on what they already know.

Your central hub for AI coding assistants on Windows, Linux & macOS — install, manage & launch 16+ AI CLIs (Gemini, Claude, Copilot, Codex & more) from one unified interface, plus a 2x2 Beast Mode grid.

Security-oriented three-axis observability for sandboxed AI agents: model intent, app context, and runtime telemetry into verifiable evidence graphs for risk, forensics, and audit.

Keep Claude Code context clean. Open-source toolkit: drift detection, re-read dedup, integrity scoring, AST-aware reads, 15 MCP tools. 62.6% measured savings, reproducible.

CyCode is a lightweight AI coding agent that runs in your terminal. It uses an OpenAI-compatible Chat Completions API and provides built-in tools for reading files, applying precise edits, searching code, running shell commands, and delegating work to sub-agents.

A high-quality, auto-updated (but manually reviewed) set of agent skills that covers key Web APIs supporting Web AI

Local-first control surface for AI coding agents, workspaces, worktrees, terminals, diffs, previews, and paired-device access.

Diagram→code through a deterministic rules gate: the AI proposes, 50 rules verify, only valid architecture lands. Try it: app.solarch.dev

🚀 Multi-agent orchestration for Qwen Code CLI. 24 specialized AI agents and 82+ skills working as a professional dev department. Built for Alibaba's open-source AI coding assistant.

A zero-dependency Python module for inspecting and converting coding-agent session files (.jsonl) — Claude Code, Codex, and Pi — into the messages format expected by Hugging Face Transformers.

Claude Code workflow skills — GitHub issue/PR/release automation and Fable-driven planning. Install via npx or as a Claude Code plugin.

Grok Build resources, reusable .grok/skills, AGENTS.md templates, hooks, prompts, and starter workflows.

gguf code codeqwen chat qwen qwen-coder

transformers safetensors llama text-generation arxiv:2403.04652 license:apache-2.0

A VS Code extension that provides a marketplace for discovering, installing, and managing Agent Skills

A safe, auditable relay between planning AIs and coding agents—without repetitive copy-pasting.

Desktop workbench for Claude Code — live subagent topology, token cost breakdown with drill-down, hook sandbox, config audit. Reads your session files locally. Electron, MIT.

Bounded, inspectable LLM inference pipelines from declared YAML — runs offline against Ollama or any OpenAI-compatible local server, emitting JSONL traces, inspect reports, and stable exit codes.

Your AI agent can now search Youtube, watch videos, create highlight reels, and more

Open-core registry of animated React components, blocks, design systems, and templates. Real, editable code: install with one shadcn CLI command or let your AI agent pull it over MCP.

The Research Playground for the RLMSs and Coding Agents

Agent coordination protocol — declare intents, lock symbols, detect conflicts before code is written

Exocortex template: fork & deploy your AI-powered personal knowledge system with Claude Code

A Codex skill that keeps human outcomes and creative intent ahead of overengineering.

Searchable football data provider documentation for AI coding agents. Like Context7 for football data.

A Claude Code plugin whose workshop of expert agents learns as it builds: repeated fixes become permanent rules, loved tweaks become taste it remembers - and every change waits behind a write gate you control.

The elite design intelligence layer for AI agents, synthesized from 10+ legendary design books. It primes your AI with the collective strategic wisdom of master designers to generate high-intent UI/UX with zero "schtick."

One command to install, heal & prove ruflo (claude-flow) + agentic-qe + RuvNet Brain — plus ambidextrous Claude/Codex/OpenCode host routing, a host-neutral execution runner, and a live local dashboard. Thin, reversible, cross-platform.

Query-aware context compression for LLMs and coding agents. Cut ~65% of input tokens.

Autonomous AI SOC for Wazuh SIEM — 11 security-expert agents triage, correlate, investigate and plan responses 24/7, every action gated by two-tier human approval. Runs on OpenClaw, Hermes or NVIDIA NemoClaw; any LLM, self-hosted vLLM, or fully air-gapped Ollama. Evidence packs, SOC KPIs, Slack approvals.

Conversational code review on macOS: review a PR or local branch together with a codex agent, and ask about any line instead of just reading its findings.

Lightweight agentic coding environment

Grok Wiki: Bring your local agents. Keep the context yours.

用于统一管理和切换 Claude Code、OpenCode、Codex CLI、Gemini CLI 等 AI 编程助手的桌面优先工作台。

35 portable Agent Skills for Codex, Hermes, and Claude, maintained by Rylai with Vietnamese documentation and upstream attribution.

Shunt Claude Code agents to any model — selective, per-agent inference-layer routing proxy

ProMentor 是一个 AI Coding Agent Skill。装上它，你的 AI 编程助手立刻化身为导师——扫描项目架构、生成阶梯式 Chapter、带你手写核心逻辑、自动判题、AI Code Review。

Learn AI, ML, and NLP with interactive Jupyter Notebook tutorials.

Your own GPT Telegram Bot on Vercel

Emulates Azure OpenAI API on your local machine using Ollama and open-source models.

A migration prompt for moving OpenClaw multi-agent deployments to Claude Code

An MCP server that scales development into controllable agentic, recursive flows, and build a feature from bottom-up

Source code of paper: Process vs. Outcome Reward: Which is Better for Agentic RAG Reinforcement Learning

Cloud based IoT system solution. MQTT Broker, MQTT Agent, SignalR Hub, Data Source API

Local RAG server for code editors. Scans your codebase, builds a local context index, and connects to any external LLM for context-aware completions and assistance.

An opinionated Laravel package that extends FakerPHP and uses openai-php/laravel to generate fake data

UnityGen AI is an AI-powered code generation plugin for Unity. It allows you to quickly generate and save code directly within the Unity editor.

Codex-first toolkit for open-source maintainers: AGENTS.md, skills, automation, and verification workflows.

A VS Code extension to query OpenAI's ChatGPT from inside the editor

This is a Go client library for the OpenAI API

This is a project where it helps the readers to get the summary and the preface , and compare it with other books and have a insights about the book.

Security guardrails for AI coding agents. Prevents accidental file operations outside working directory.

The code for AAMAS2022 《GCS: Graph-based Coordination Strategy for Multi-Agent Reinforcement Learning》

(ICML 2023) The official code for RACE: Improve Multi-Agent Reinforcement Learning with Representation Asymmetry and Collaborative Evolution

A common client library for Python-based agents

提供主題 or Markdown 講稿，透過 Agent Skills 單一 HTML 課程頁面。

The best coding agent for open models

Tensorflow 2 source code for the PI-SAC agent from "Predictive Information Accelerates Learning in RL" (NeurIPS 2020)

OpenCode plugin that prevents agents/tools from reading or editing sensitive .env* files, while still allowing safe inspection via EnvSitter.

Ruby gem for calling observability APIs

Demo of simple wine RAG-based assistance with function calling and multiagent testing

Data Neuron is a powerful framework that enables you to build text-to-SQL applications with an easily maintainable semantic layer. Whether you're creating customer-facing chatbots, internal Slack bots for analytics, or other data-driven applications, Data Neuron provides the tools to make your data accessible through natural language

Deterministic security layer for Openclaw(Clawdbot), Cursor and Claude Code. Write secure code, prevent data exfil, and more

Enterprise-grade Rust implementation of Anthropic's MCP protocol

Source code of our paper "Multi-Agent Consensus Seeking via Large Language Models".

The developper starter pack for document processing

A user-centric AI SaaS Platform, powered by Next.js 13 App Router. It can function as chatbot, image, music, code, and video generators

Heavy3 Code Audit: Agent skill that uses multi-model consensus to review plans, code, and PRs for coding agents

The official codes for "M^3Builder: A Multi-Agent System for Automated Machine Learning in Medical Imaging"

Open-source codebase for MAZero, from "Efficient Multi-agent Reinforcement Learning by Planning" at ICLR 2024.

Kilo is the all-in-one agentic engineering platform. Build, ship, and iterate faster with the most popular open source coding agent.

FullStack-Agent: Enhancing Agentic Full-Stack Web Coding via Development-Oriented Testing and Repository Back-Translation

30 ready-to-deploy OpenClaw agent packs — Sales, Engineering, Marketing, Legal, Finance, Customer Support, and more

AI agent whose purpose is to conduct vulnerability tests on LLMs from SAP AI Core or from local deployments, or models from HuggingFace. The goal of this project is to identify and correct any potential security vulnerabilities.

Self-hosted portfolio tracker and AI trading assistant with daily reports, natural-language holdings updates, backtesting, multi-market support, and OpenClaw integration.

Go SDK for Anthropic Claude Code CLI – unofficial Claude Code Go agent SDK

Your AI Platform Engineer. Self-hosted cloud built for AI agents — deploy, monitor, and operate your infrastructure through natural language. One VPS. One command.

A thinking process, not a template. 4-stage planning framework with 21 anti-pattern checks, adversarial hardening, and 8-domain detection for Claude Code.

Browse, search, and export your Antigravity AI conversations — VS Code Extension

A comprehensive full-stack healthcare application that leverages AI-powered voice interactions for patient triage, symptom analysis, specialist mapping, and appointment booking. It is built with modern technologies including FastAPI, PostgreSQL, React, and integrated with leading AI models like Gemini and GPT-4.

Enhanced MCP code execution. Agent framework-agnostic (optimized for Claude Code). Skills framework (99.6% token reduction), multi-transport, sandboxing

Official Code for MTSQL-R1: Towards Long-Horizon Multi-Turn Text-to-SQL via Agentic Training (In ACL 2026 Main)

EYEJOKER agent stack — thin carry layer over upstream NanoClaw (host-executor MCP, gpt-proxy provider, Discord adapter)

A real-time voice/call AI agent that lets you talk to a LangGraph agent over LiveKit — similar to "voice mode" experiences in ChatGPT Voice, OpenAI Realtime API sessions, and Gemini Live. This repo demonstrates adapting any LangGraph agent into a full-duplex, low-latency voice assistant using LiveKit Agents.

Real-time .NET proxy and dashboard for inspecting AI coding agent API calls (currently supports Claude Code)

CLI text optimizer built on GEPA. Uses Agentic Coding CLI's as mutator and observer -- no api keys required

Automatically monitors YouTube channels for new videos, extracts transcripts, auto-detects the content type (stocks, crypto, podcast, tech review, education, news, etc.), generates tailored summaries using your choice of LLM (Gemini, OpenAI, or Claude), and emails them to you.

AL LSP marketplace for Claude Code

AI Harness Engineering Template — guardrails, gates, and boundaries for AI coding agents. One-command install. Zero dependencies.

Official code for TimeSeriesGym: A Scalable Benchmark for (Time Series) Machine Learning Engineering Agents