Code agents

Run OpenClaw and OpenCode in the browser. Self-hosted, multi-user, Helm-deployable.

OpenReviewer is an automated multi-agent system for deep, evidence-driven research paper review, validation, and integrity auditing across methodology, experiments, citations, and cross-section consistency.

In this study, a multi agent chase-escape problem using Deep Q learning. Actors of the problem are smart evader and smart pursuers with opposite goals. At the beginning of the game these agents have homogeneous properties and evader and pursuits don’t have knowledge about the map. The purpose of the pursuer robots is the catching the evader as fast as it could and the purpose of the evader robot is the escaping as much as it could. Such as this game, where a player's gain is in balance with the loss of other players are called zero-sum games. The end condition, which may differ according to the approach applied, in our study is that “any of the pursuers or evader within the same or neighbor pixel with obstacle or map border” or “one pursuer and evader within the same or neighbor pixel”, in other words, Evader catches by the any of the pursuers or evader hits an obstacle or any pursuers hits an obstacle. A new episode of the game resumes after each collision or cath. In this respect, escape-chase problems are also included in the repeat games class. In this study, the question is what any pursuer or evader can do to improve its performance in a repetitive part of the game is questioned. The method used for this study is Deep Reinforcement Learning. Agents receive rewards or penalties based on their moves within a section and update this information into the Neural Network.

Claude Code power-user setup: 5 agents, 32 skills, notification hooks, workflow rules

AI project management for solo agentic development. Persistent memory, expert plan validation, automated code review, and structured workflows — powered by a knowledge graph. Works with OpenCode and Claude Code.

Beyond chatbots: an AI platform that understands user intent and dynamically renders contextual UIs. 1,100+ tools, 30+ models, 100+ integrations.

🚀 A collection of Claude subagents, skills, rules, guides, and blueprints for Developers, Engineers, and Creators. | Covering programming languages, DevOps, Cloud, and beyond.

The building blocks of an enterprise adoption framework for agentic coding — technical training, adoption playbooks, governance policies, industry analysis, proposal templates, and practical workflows. From understanding how AI agents work to rolling them out across teams. Built for leaders driving adoption.

An Agent-native Obsidian wiki + CLAUDE.md skeleton that lets Agent know your project as well as you do.

The Yahoo Finance Agent is an application that combines OpenAI's LLMs, the Yahoo Finance Python library, and LangChain's tools to provide real-time financial data. It features stock information, financial statements, and an interactive chat interface, all while maintaining conversation context and integrating with Langsmith for debugging

Implementing a scalable content team using AI involves creating a framework that blends the strengths of AI technologies with the creative and supervisory capabilities of human team members. This strategy aims to enhance efficiency, creativity, and content output quality.

Data-Driven Cycling using Strava data and GPX data analysis. Digital Personal Trainer using old cycling workout data to predict new workouts

mkenv is a fast, secure, reproducible local isolated development environment generator.

Code for the OpenCV demo of a recipe transcription OCR agent.

(ACL2025 Findings) Official code for the paper "STeCa: Step-level Trajectory Calibration for LLM Agent Learning"

TaskForge runs AI agents in sandboxed Docker containers with capability-based security. Agents start with minimal permissions and must request new capabilities (packages, network access, tools) through a human-in-the-loop approval process. Every approval triggers a container image rebuild, and every LLM interaction is logged for audit.

Code for the RA-L 2024 paper "Contingency Games for Multi-Agent Interactions."

🚀 Enterprise-grade API Gateway for MCP Protocol, built with Java Spring Boot. Supports authentication, proxy, and traffic management for AI tool calling.

The first open-source GUI for GitHub Copilot CLI — a multi-engine AI coding client with zero-config secure remote access from any device.

基于 SenseVoice 的 Windows 本地语音转文字工具，支持 OpenAI 格式 API 润色，低延迟，高精度。

LLM Security Platform.

Implementation of Corrective RAG using LangChain and LangGraph.

Security gate for AI-generated code - blocks the build until vulnerabilities are fixed

Anthropic's Hidden Vercel Competitor "Antspace"

Feishu/Lark group chats connected to Claude Code agents. Per-group isolated sessions, streaming card responses, deep Feishu integration.

A Claude Code plugin that solves the same problems as community frameworks (GSD, BMAD, Ralph, Agent OS) — but using the tool's native architecture instead of fighting it.

Controllable reasoning demos for NVIDIA Nemotron 3 Super (120B/12B MoE) — chat UI, CLI, API server, tool calling, budget sweep, and adaptive routing

Zero-dependency browser automation CLI. 70+ commands, 10 test assertions, smart commands (click/fill by text — no LLM needed). MCP server for AI agents with 500x fewer tokens. Extract, observe, script runner. 50KB, pure CDP.

'Cursor' for CAD.

Spec-driven development for AI agents. Define what to build, let the agent build it right. Claude Code · Cursor · Copilot.

Global, unlimited persistent memory for Claude Code agents. Context-activated hints injected automatically via hooks using scatter-gather map-reduce.

AI-powered deep research tool leveraging web scraping for cost-effective, comprehensive analysis. Open-source and API-cost free!

🎙️ Fast CLI tool to transcribe audio/video files to SRT format using OpenAI Whisper API

Cursor IDE extension that automatically re-enables the "OpenAI API Key" toggle when it randomly resets itself.

NotebookLM on steroids — purpose-built for security researchers.

Open source multi-agent platform. Deploy autonomous AI coding agents to WhatsApp, Slack, Telegram, and Discord.

Provider-agnostic AI orchestration for VS Code. Intelligent workspace analysis, Code Execution MCP server, and project-adaptive multi-agent workflows — all natively integrated into VS Code.

A vibe coded final fantasy tactics inspired game using Codex, Claude Code and Agent Skills

AI code knowledge graph for code understanding, graph retrieval, and agent workflows

七天从零实现一个Claude Code。 Complete a Claude code from scratch in seven days.

AI powered automation toolkit which acts as an agent that discovers MCP servers for you. Point it at GitHub/npm/configure your own discovery, let GPT or Claude analyze the API or MCP or any tool, get ready-to-ship plugin configs. Zero manual work.

Parrot is a new library to work with chatbots and agents with a very simple API

AI 多模型 API 聚合与协议转换网关：统一调用并互转 OpenAI Chat/Responses、Claude、Gemini 等格式，Provider 仅需实现原生协议。Multi-LLM gateway & protocol transformer: unify and convert OpenAI Chat/Responses, Claude, Gemini, etc.; providers implement native only.

Taskly is a free and open source project management tool that provides a simplified and user-focused experience.

loopAny is a framework that enables AI Code Agents to carry out fully automated product iteration. It gives Agents the ability to autonomously complete the full process of design, development, testing, and experience optimization without human intervention.

Cut AI agent token usage by up to 90%: record a browser session once with freu-cli and it compiles into a reusable skill command. Constellation-based DOM targeting survives class renames and page reshuffles, so skills keep working. Drops into Claude Code, Codex CLI, Cursor, OpenClaw, and Hermes skills directories.

🥒 Pickle Rick for Claude Code — autonomous PRD-driven coding loops + relentless code review. Ralph Loop toolkit.

写给零基础读者的 Claude Code 中文入门书 · 针对 Claude Opus 4.7 · 27 章 + 10 附录 · 17 万字 · 44 张思维导图 · Mac/Windows 双平台手把手 · A beginner-friendly Chinese guide to Claude Code — tuned for Claude Opus 4.7, from zero programming experience to daily proficiency.

Self-hosted, BYOK outreach intelligence. Scan forums free; draft replies in your voice only on demand.

AI Agentic Trader

OpenGnothia is a privacy-focused desktop app that helps you explore your inner world through AI-assisted therapy sessions, journaling, and dream analysis. All your data stays on your device.

Real-time behavioral intelligence for call centers. Transcribes support calls, redacts PII, extracts emotional tone, classifies issues, and delivers insight-rich dashboards — powered by GPT-3.5 (cheap tokens), Whisper, DuckDB, and a polished React+TypeScript frontend. No Azure. No Power BI. No vendor lock-in. Just full-stack AI that runs local.

Understanding CLAUDE.md, MEMORY.md, SKILLS.md, SOUL.md, and Related Prompting Mechanisms

🕰️ Time machine for Claude Code sessions - Automatic snapshots, granular rollbacks, and visual diffs. Never fear AI mistakes again.

Production ready Personal AI Agent Platform using Claude Code CLI. Focused on productivity, reliability and security at it's core

Infrastructure Context for your Coding Agents (Claude Code / Cursor)

A phase-aware operating system for coding agents that helps them explore, ship, harden, and verify without losing the plot.

Production-grade memory operating system for agentic AI. Interoperates with every major framework via MCP, OpenAI-compatible gateway, and native /v1/* REST — Claude Code, OpenClaw, ZeroClaw, Hermes, MemPalace, LangChain, LlamaIndex, CrewAI, AutoGen, Mem0, Letta, Zep. In production use since December 2025. Apache 2.0.

The friendly guide to Claude Code. Zero jargon — from first install to daily operating system.

Telegram MCP server (MTProto). Connect Claude, Cursor, Claude Code, VS Code, Codex, Cline, Windsurf to a real Telegram account — read/search/send messages, moderate channels, manage stories/contacts/folders, transcribe voice, and call any raw MTProto method. Browser-based sign-in. 100+ tools.

The decision layer for personal AI. Local-first runtime where agents automate across GitHub, Slack, Gmail & 45+ services — but every risky action can stop for your yes, workers (agents) earn autonomy from track record, and every decision leaves a receipt. Your models, your machine, your policy. Includes an MCP bridge: 180 IDE tools for Claude Code.

Human-in-the-loop multi-agent task orchestration platform for Git-based software workflows.

Open-source platform that monitors 25+ AI/tech data sources, processes signals through LLM-powered agents, and surfaces actionable market intelligence

Build system for AI coding-agent context. Generate deterministic, explainable context artifacts for Claude, Codex, Cursor, and MCP.

纯协议逆向实现 ChatGPT 官网注册全自动流程，支持 MaliAPI 邮箱收码、PKCE 凭证链及完整 Token 换取，注册成功率接近 100%

Per-task isolated worktrees for parallel Apple development with AI agents. Run multiple Claude / Codex / Copilot / Cursor sessions on the same Xcode project without build.db locks, DerivedData thrash, or simulator collisions.

Official Code of LabOS: the AI-XR Co-Scientist that Sees and Works with Humans

The starter kit for Claude Code — your agent remembers across sessions: date-tagged memory under three hook-enforced caps, per-session handoffs, stale-refs detection, multi-project isolation, audit-driven promotion via /close-session, plus an opt-in multi-agent orchestration layer. Zero deps.

Public adapters and discovery catalog for Triptych OS (Agent OS): agent frameworks, MCP/A2A/x402 protocols, workflows, wallets, SDKs, and examples for execute-first routing, governed handoffs, and receipt-aware agent commerce.

Marketplace of domain-specific plugins for AI agents (Cowork, Claude Code, OpenClaw). Build autonomous business workflows for finance, banking, legal operations, and sales using modular agent skills and commands.

⚡ Production-ready LangGraph interrupt template with modern web interface | Human-in-the-loop AI workflows | FastAPI backend + Next.js frontend

Local-first autonomous coding agent that plans, executes, validates, and finishes software tasks end-to-end.

Local MCP server that gives AI coding agents persistent, searchable memory of your codebase

Model Context Protocol (MCP) server for Amazon Seller Central - Access sales data, inventory, returns, and reports through the Amazon SP-API

Self-hosted semantic code search platform — Go server with web dashboard, CLI, and AI-agent skills. Search code by meaning, not text: hybrid BM25 + dense embeddings via llama.cpp.

Rolling context compression for Claude Code — never hit the context wall. Auto-compresses old messages while keeping recent context verbatim. Zero config, zero latency. Works as a Claude Code plugin.

AI agent engineering meets system design: Claude Code dynamic workflows, loop engineering (bounded evaluator-optimizer gates) and runnable workflow scripts, plus real-world architecture case studies (Uber, Netflix, Stripe) and 15 engineering-blog deep dives, as Mermaid and draw.io diagrams.

Awesome AI directory 2026 — 800+ AI tools incl. Kimi K3, AI agents, LLMs, MCP servers, generative AI & dev resources. Updated.

The most comprehensive MCP server for Meta's business platform. 200+ tools covering Facebook Pages, Instagram, Threads, Ads Manager, Commerce, Conversions API, Audiences, Insights, and Ad Library.

Local AI coding agent for your terminal. Open-source, offline alternative to Claude Code, Cursor & Copilot — powered by Ollama and any local LLM. Private by default, free forever.

SAM Sovereign Agent Mesh

Docker image for a self-hosted WhisperLive real-time speech-to-text server, powered by faster-whisper. Provides WebSocket streaming for live audio transcription and an OpenAI-compatible REST API. Supports all Whisper models, VAD, NVIDIA GPU (CUDA) acceleration, offline mode, and multi-arch (amd64, arm64).

free and open source terminal agent harness 🤖

Run Hermes Agent + Claude Code locally on llama.cpp — zero API costs. A 4h / 7M-token session that would have cost $94 on Claude Opus 4.7

Automate a WeChat group's daily work-report roll-call — start, chase non-submitters, and LLM-summarize for the manager. wxauto + FastAPI + hot-reloadable rules.

🚦 Stop AI agents from deleting data, leaking secrets, or taking irreversible actions without approval. One ⭐ takes us a long way :))

rUvOS — the agentic operating system. A single static Rust binary that runs as an MCP server, giving Claude Code persistent memory, resumable signed sessions, multi-agent orchestration, a knowledge graph, safety guardrails, and a signed audit trail. Zero Node.js, zero SQLite, zero daemon.

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.

A local-first macOS debugger for LLM context windows, token usage, tool calls, and agent execution.

AI Agent Skills for content planning, multi-agent discussions, and role library expansion — compatible with Codex, Claude Code, and Cursor.

Claude Code skill that applies Naur's Programming as Theory Building to coding-agent workflows.

Claude Code Architecture Deep Analysis — 14-chapter report, 7 languages | Claude Code 架构全景分析 — 14章报告，7种语言

Ripple is a Codex-powered agent workspace for sessions, files, connectors, automations, and multi-platform clients.

Agent Skill for creating UESTC course report templates for Claude Code and Codex

FAIR cyber risk quantification toolkits, agent-based control simulation (FAIR-CAM), threat event frequency estimator (PyPI), LLM classification validator (PyPI), Monte Carlo risk engine with IRIS benchmarks.

WebLLM Gateway：让 Qwen/DeepSeek 网页模型接入 OpenAI/Anthropic 兼容 Agent 工具链，支持 OpenClaw、Hermes、Claude Code、Codex 工具调用

AEO tracking toolkit (CLI + dashboard) built for AI agents like Claude Code, Cowork, Codex, OpenClaw, Gooseworks

A rich web UI layer for AI agent interactions — human-in-the-loop, click-to-edit, preference learning. Built for Claude Code, CodeX and OpenClaw.

• 基于 FastAPI + LangGraph 的医院导诊 Agentic 助手：整合 Redis/Elasticsearch/Milvus 做症状与流程的 RAG 对话，支持多轮意图识别、检索重写、答案生成，以及 rich 驱动的多会话 CLI 体验，便于参考构建生产级医疗导诊/问诊系统。

Godot AI agent CLI, Skill, and MCP server with structured JSON/schema output — headless scene/script/export automation plus live runtime control.