Code agents

Source repo for the blog post Stop Stuffing Your System Prompt: Build Scalable Agent Skills in LangGraph

The authorization kernel for AI agents. Block, allow, or escalate agent tool calls with YAML rules — deterministic-first, LLM fallback.

A reusable template for autonomous software delivery using headless Claude agents. Feed a requirements doc in, review pull requests out.

Real-time voice agents with parallel async background sub-agents — conversations continue naturally while tasks run • Join the builders → https://discord.gg/mqxKaN3UKC

Accountable authority for autonomous agents

OpenClaw Desktop App — No Terminal, No Coding. One-click installer for macOS & Windows.

USB-portable offline AI assistant. AES-256 encrypted history, Turkish-tuned LLM (Trendyol), RAG over PDF/DOCX. KVKK uyumlu, %100 offline.

PandaGenie's official modules source code

AI code editor + terminal coding agent, built in Rust. Works with any LLM via OpenRouter, OpenAI, Anthropic, or Ollama. 20MB native binary, 20 themes, real terminal, git, agent sidebar with tool calling.

让 Claude Code 住进你的微信——收消息、发文件、定时问好、远程审批

Minimize LLM tokens from Python objects, code, logs, diffs, and more. Zero deps. Ultra-Lightweight.

Ultra-fast indexed code search engine — faster than ripgrep on repeated searches, lighter than zoekt. Built-in MCP server for AI agents. Also does fast file finding (fd/find alternative).

ShopFilter 是由 OpenCode AI 智能体驱动的跨平台电商商品聚合与智能选品助手。输入关键词即可触发智能体自动化工作流：多平台并发抓取商品数据，多维条件筛选（价格、评分、评论、包邮等），加权综合评分模型自动排序，最终输出最优购买决策。基于 Qt6 + C++17 构建，采用插件式架构与多线程并发，界面简洁现代。全程由 AI 智能体辅助开发，人机协作打造。

A full-stack, agentic workflow programming platform. Built for vibe-coding and with vibe-coding.

Claude Code harness for disciplined Java backend dev — risk-classified routing, 6-phase lifecycle (Explorer → Propose → Review → Implement → QA → Archive), 13 specialist agents, gate-enforced contracts. Prevents LLM slop via spec-first briefs, TDD, and WAL.

Model Context Protocol server for BlackDuck Coverity Connect static analysis platform

A Python-based logical reasoning system combining rule-based engines with Large Language Models (LLMs) for business automation. Supports deduction and hypothesis testing, partial fact completion, and automated fact retrieval via documents or chat. Features include explainable reasoning, workflow integration, and customizable knowledge bases.

A multi agent healthcare assistant system implemented using Python and Langgraph. The agents include icd10 code extractor, SOAP document generator and medical image report generator. This project uses one of the latest LLMs, MedGemma model.

Intelligent SOC automation framework powered by LangGraph multi-agent workflows for alert triage, correlation, and incident response

Production-grade TypeScript AI runtime focused on reliability, governance, and reproducible LLM systems. Multi-provider gateway, agents, RAG, workflows, policy engine, audit trails, and deterministic testing — built for teams shipping AI in production.

text2sql-skill: A production-ready, secure, and high-performance Text-to-SQL skill engine for enterprise applications. Convert natural language queries into secure SQL queries with comprehensive safety guards and audit capabilities.

Claude Code edits your videos with triple lane on-device pre-processing, then exports to Adobe Premiere. NO CLOUD MICROSERVICES REQUIRED! Plug in hours of footage, wait 30 min and get an edited video back!

Open-source session management platform for Claude Code and Codex — analytics, AI recaps, sharing, and team features. Self-hosted with Docker.

Iterative artifact refinement with investigation-first judge board - constructs problem-specific judges that read the code, understand the problem, and propose evidence-based improvements

Claude Code stock analysis skill: SEC EDGAR + market data, /analyze /score /compare — free, local Python tools. By XVARY Research.

MCP server for Home Assistant — 292 tools across 27 domains: entities, automations, dashboards, energy, voice, HACS, Supervisor, Card Builder (with embedded block schema), BM25 tool search, aggregated snapshot, automation trace debug, git versioning

Agent Squad for Requirements Engineering — 33 Specialists with System 2 Reflection, BM25+ Knowledge Engine (831 entries), Mermaid Diagramming, Jira + Confluence Integration. Runs on Antigravity IDE, Claude Code, Claude CoWork.

AI agents that think must never act. Open-source security framework with composable modules for safe autonomous AI.

Son of Anton, reimagined as a web app — Node + WebSocket + node-pty + xterm.js, zero Electron.

Persistent memory, architectural decision enforcement, pre-execution safety hooks, and session handoff for Claude Code. MCP server plugin for AI coding agents.

Verdict-first output for AI coding agents. Tiny prompt + installer for Claude Code, Codex, Gemini, Cursor, opencode, and 30+ agents.

65 plugins that turn Claude Code into an autonomous development team. 24 agents, 34 skills, 5 hooks. Includes 12-plugin anti-hallucination suite. One-line install.

[LEGACY] Use the Codex models included with a ChatGPT Plus/Pro subscription inside LangChain/LangGraph.

A lightweight, extensible coding agent built in TypeScript that helps developers with coding tasks across TypeScript, React, JavaScript, Node.js, Bash, and markdown/JSON.

Chrome browser extension that helps AI Dungeon creators rapidly build multiple choice scenario branches using AI and other useful tools~

Your knowledge graph. Ask questions across all your notes, meetings, and emails — cited answers.

MCP server for Octen Extract — turn URLs into LLM-ready markdown for Claude / Cursor / any MCP client

Learn features by building projects hands-on with Claude Code--no boring videos, outdated blog posts, or stale courses.

Auto sync Claude Code dotfiles (~/.claude) across machines using Git. Keep CLAUDE.md, commands, hooks and settings always in sync.

Turn prompt-based agents into auditable ops: state machine, decision log, risk scoring, and memory for Claude Code, OpenClaw, Cursor, Windsurf, and API workflows.

AGENTIC · INFRASTRUCTURE — Every agent you run, working from the same brain. Open-source framework with a native shared Second Brain.

Turn Claude Code into your personal AI agent. No harness required. No API costs. works with your existing Max subscription.

A self-hosted software factory — define goals, agents decompose and execute them through enforced pipelines, with humans in the loop where it matters.

papersflow-mcp is PapersFlow’s production MCP server for literature search, citation verification, related-paper discovery, and authenticated research workflows across Claude, Codex, Gemini, and other MCP clients.

TokenPack packs long documents, codebases, PDFs, and folders into compact, evidence-dense LLM context using local embeddings, evidence scoring, and budget-aware selection.

问卷星 OpenAPI 全栈工具包：TypeScript SDK + MCP Server + CLI

Cross-platform AI agent desktop app and multi-agent workspace for Claude Code, Codex CLI, and Gemini CLI.

A curated list of awesome OSS, programmable APIs, and autonomous AI agents for developers in finance. Discover resources for quantitative analysis (Quant), algorithmic trading bots, Fintech platforms, LLMs, and portfolio management.

Lionclaw is a local control plane for AI coding agents. It runs AI agents as durable, auditable workers with explicit state, skills, channels, schedules, and bounded permissions.

Multi-agent AI consultation framework for Claude Code via MCP — get second opinions from OpenAI, Gemini, Qwen, DeepSeek

The approval and accountability layer for agentic AI. Identity → Policy → Approval → Trace. Try: npx sidclaw-demo

File-based agent-to-agent messaging for Claude Code — multiple AI instances communicate via JSON files, MCP channels, and auto-wake on a single machine

Governed multi-agent SDLC pipeline for Claude Code and Qwen Code — plan → adversarial plan review → proven-red TDD → security scan → PR, with tamper-evident evidence at every step. Azure DevOps, Jira, GitHub, GitLab, Zoho, and local-markdown providers. Language-agnostic, discovery-driven.

Production-grade, 10,000+ line PRDs that let AI agents one-shot entire applications. Built on CRHQ.ai.

Repositório com minhas skills para Claude, Claude Code, Antigravity, Gemini Spark, Manus, Perplexity, Agno, ADK, OpenClaw, Windsurf, Qwen Code e demais sistemas agênticos.

Market intelligence toolkit for Claude Code. Iterative research workflows, trend modeling with three-valued logic, multi-format reports, and automated GitHub issue creation from findings.

Multimodal prompt generator nodes for ComfyUI, designed to generate prompts for QwenImageEdit and Wan2.2. Supports local LLM / local GGUF models (Qwen2.5-VL, Qwen3-VL, Qwen3.5 and Qwen3.6) and Qwen API for image and video prompt generation and enhancement.

Claude Code skills & agents to eliminate App Store rejections — 31 checks built from real-world rejection cases across all 5 App Store Review Guidelines sections.

ACP adapter for the real Claude Code CLI: Rust PTY bridge for Zed and other Agent Client Protocol clients.

AI trading agent with a skill system: drop a SKILL.md file, declare your tools, ship. Built-in planner, pattern detection, strategy backtesting, 9 LLM providers, multi-agent simulation, and a full Next.js web UI bundled into one pipx install.

CodeGraph MCP - Give persistent learning to your coding agent for a codebase across teams & token saving superpower to the coding agent

VS Code fork with the OpenCode AI coding agent embedded natively as a sidebar SPA via an Electron-main loopback proxy. Open source AI IDE — alternative to Cursor / Windsurf / Claude Code Desktop.

Reverse-engineered system prompts from Claude (claude.ai) and Claude Code CLI, validated against Anthropic's officially published prompts.

Agentic binary reverse engineering for ELF binaries on ARM64, ARMv7, x86_64 - hypothesis-driven analysis with radare2, Ghidra, GDB, QEMU

单 APK 版 Codex 手机版：内置 arm64 runtime、App 内登录/设备码授权、本地 app-server 管理。

Self-healing AI operations platform — Discord bot + RAG + Insight Layer + 99 automation scripts. Runs 24/7, fixes itself, gets smarter. Zero API charges.

Secure every action your AI agents take (Claude Code, Codex, MCP). Blocks secret access, gates risky commands, and enforces allow/deny/approval before actions run.

Agentic SQL & RAG engine (MCP server) for Oracle Fusion. Features local schema caching, semantic search, and real-time SQL execution for AI agents

Give Claude Code a permanent memory — 100% local, zero config, graph-powered

Project memory layer for coding harnesses

Bamboo — a local-first AI agent harness & runtime in Rust. Persistent memory, 22 built-in tools, skills, MCP, sub-agents, workflows & schedules behind one HTTP + WebSocket API. Embed it as a crate, or run it as a server.

Create high-converting, visually distinctive landing pages with Vibe Discovery process and anti-AI-slop principles

Claude Code skill for learning English through real conversations, corrections, and micro-lessons.

Autonomous coding-agent task runner — queue work and Lea runs it headlessly with Claude Code or Codex the moment your limit resets. Menu-bar app on macOS, a real windowed app on Windows/Linux. MIT.

CLI coding agent powered by the MiMo large language model

Storage engine for AI agents to navigate, store, and retrieve structured data. PostgreSQL ltree, built-in versioning, scoped queries.

⚡ Synerix — 高性能 AI 编程终端 | 多智能体协作 + TUI 界面 + 安全沙箱

Tell Claude Code what you want once. It works until the job is verifiably done — and gets smarter every time. Self-correcting goal loops with independent verification and growing memory.

Keeps AI assistants on track during long conversations by tracking tasks across sessions

Copy and paste prompts for cursor agent. Free for anyone to use or add to. This repository provides a curated collection of advanced .mdc rules for Cursor IDE to optimize AI agent behavior, memory management, and development workflows.

An open-source companion repo for Agentique.io: a free community hub for discovering, sharing, and reusing trusted AI agent resources.

One AI engineering team for Claude Code. Install once — every project gets a full-stack specialist team that auto-specializes to its stack.

[ICML2026] The official code of "Beyond Gemini-3-Pro: Revisiting LLM Routing and Aggregation at Scale"

Proactive 5h usage guard for Claude Code (macOS). Pause before extra wallet on long batch/subagent runs. Account-level window visibility. /usage-guard skill + daemon. Not affiliated with Anthropic.

The canonical standard for building production-grade agentic products — autonomy ladder, composition patterns, the 8-layer harness, eval discipline — plus a Claude Code skill set that operationalizes it.

Generate a production-ready, best-practice Claude Code harness tailored to your use case in minutes -- at any skill level. Or validate, update, and improve a harness you already have.

The recursive self-improvement loop for your skills (including itself) — runs a retro after every session and turns corrections into permanent skill improvements, so skills compound instead of plateauing.

154 Web3 MCP tools for Claude Code, custody-free. Plus an agent wallet prompt injection can't drain: per-tx, daily, and on-chain (ERC-4337) spending caps the model can't bypass. EVM + Solana + Tron DEX/DeFi, perps, prediction markets, contract deploy + audit.

Tlamatini is a self-hosted AI developer assistant for local or cloud LLMs: hybrid RAG (FAISS+BM25) over your codebase, a 100+ tool Multi-Turn engine, an 86-agent visual workflow designer, 28 SKILL.md skills, a universal MCP client, and ACPX, a runtime for external coding agents like Claude Code, Codex, Cursor and Gemini CLI.

Search your Claude Code conversation history by content (not just titles), then resume any session. grep + fzf, no index.

Open-source AI agent operating system: one file-native brain (230+ skills, 160+ specialist agents) run across many sealed client arms, with per-client token attribution and opt-in budget caps. Organic, portable, MIT.

Claude as subagents in Codex — scoped workers, resumable sessions, git-ignored logs.

Claude Code Skills, Agents & Plugins — UitKit

Agent tools from many descriptions in a single integration. Authorize operations, not just tool calls, and approve them when a human is required. The agent gets its own identity and never holds your credentials.

🤖 Self-Evolving Multi-Agent AI System | 116+ Skills | TrendRadar · Reviewer | Learn, Build & Evolve

Agent Switch: Claude Code, Claude Desktop, Codex CLI, Codex Desktop, Hermes, OpenCode, OpenClaw and AI agent config switcher, model router, and local OpenAI/Anthropic gateway

Zero-human full-stack deployment as a bundle of /sc-* Claude Code slash commands — GitHub + Convex (self-hosted & Cloud) + Dokploy + Vercel + Hostinger DNS, source to verified live URL. Node ≥18, no runtime dependencies. 8 skills implemented, 5 stubs.

MCP server that lets AI agents (Claude, Cursor) debug your .NET / ASP.NET Core app

Deterministic, scripted, resumable multi-agent orchestration for LangChain deepagents — a community port of Claude Code's Dynamic Workflows.