Code agents

Claude Code plugin for capturing books from Kindle, Apple Books, or PDF — screenshot, OCR via macOS Vision + Claude agents, and structured Obsidian Markdown generation. 4 capture sources, 7 commands, 2 AI agents.

Real-time command center for Claude Code agents. Monitor all agents from one dashboard, send instructions, track costs, detect stuck/looping agents, 7-layer security radar. Works from your phone via QR code.

Engineer user-research methodologies into AI prompts — professional-grade phone interviews at scale. 6 pluggable methodologies, 3 AI skills, 5+ tool compatibility.

Self-hosted personal AI Agent OS / 长驻个人 AI 助手 (JARVIS-style). Kernel + pluggable skill packs (job, game, mail, life…). AgentRuntime · Layer×Scope memory · ReAct · Tool Use Contract (anti-hallucination) · SafetyPlane HITL · MCP server & client. Inspired by Letta/MemGPT, Claude Code, OpenClaw. LangChain/LangGraph/AutoGen alternative

The definitive Claude Code setup, configuration, and mastery skill — CLAUDE.md engineering, MCP servers, agent teams, hooks, CI/CD, and self-updating knowledge base

🛡️ Zero-trust governance for AI agents. Intercept, approve, and audit LLM actions with one decorator. Fail-secure by default.

AI coding agent orchestrator — run parallel Claude Code tasks in sandboxed Docker containers, monitor from a Kanban board or chat bot.

Multi-agent LLM system for autonomous code generation, testing, and debugging with Docker sandboxing

基于LangGraph的多Agent架构全自动OA办公系统

Agent skills for agentic coding tools. Extremely opinionated. Updated (almost) daily.

🚨 The leaked source code of Anthropic's Claude Code. Explore 512k+ lines of TypeScript revealing multi-agent swarms, MCP integrations, Bun runtime, and a React/Ink terminal UI.

Public skill pack for AI coding/automation/penetration-testing agents.

Build and host Coded MCP Servers within UiPath

Semantic grep for codebases — tree-sitter chunking, vector search, shared via Git orphan branch

AgentMap: Build and deploy LangGraph workflows from CSV files. Create complex LLM agent graphs without coding, convert simple spreadsheets into powerful AI agents, and orchestrate multi-agent systems with ease. Integrates with OpenAI, Anthropic, and Google AI models. Includes CLI and FastAPI server for quick deployment.

🛠️ Discover and explore a collection of system prompts and messages, contributing to better understanding and development practices.

Source code of the wahl.chat platform. Our mission: Make politics more accessible.

Bridge Claude Code to ChatGPT Codex via a local Anthropic-compatible proxy.

🎓 Official Anthropic Learn certifications showcasing expertise in Claude AI, API development, Claude Code CLI, and Model Context Protocol. Verified achievements from Anthropic's Skilljar platform documenting the journey from AI fundamentals to advanced MCP implementations. Each certificate is independently verifiable through unique

Never hit a rate limit again.

AI coding plugin that gives you an entire engineering team — CTO, SRE, DBA, Security Engineer, and more — as AI skills.

👌🏻 Pick code into Markdown. Apply Markdown to code. Built for LLMs and quick backups.

Open-source Vibe Testing suite: an MCP server for the coding agent you already run, a VS Code review cockpit, and CI. Your agent explores your app and crystallizes each flow into a plain @playwright/test spec you own — record == replay, runs in CI with zero AI.

SeekLink — hybrid semantic search for markdown vaults. Four-channel RRF fusion, MLX reranker, native CJK support. Fully local.

Local-first MCP coordination hub. One local daemon serves multiple AI assistants across IDEs — shared meetings, tasks, messages, and project registry. Works with Claude, Cursor, VS Code, Zed.

Claude Code + Codex 双平台 AI dotfiles：统一管理 skills/agents/hooks，并一键同步到 ~/.claude 与 ~/.codex。

Awesome list of AI agents (2026 Edition) — Curating 380+ frontier frameworks, coding agents, MCP protocols, computer use, and commerce rails — featuring LangChain, CrewAI, AutoGPT, Claude Code, Cursor, Devin, and more.

ARI — Artificial Reasoning Intelligence. Personal AI operating system with 7-layer architecture, three-pillar cognition (LOGOS/ETHOS/PATHOS), constitutional governance, and tamper-evident SHA-256 audit trails. Local-first. Multi-agent. TypeScript.

Open-source CLI scanner for agentic AI components such as skills, MCP servers, system prompts

Progressive file disclosure for agentic AI - explore files hierarchically with plugin-based analyzers

gemini cli hooks - adding voice on each hook

Standalone Node MCP server: semantic search + knowledge graph + vault editing for Obsidian, no plugin required

Local‑first MCP server for multi‑repository semantic code search with Qdrant and llama. Turns your entire workspace into private context for AI coding assistants like Claude Code, Codex, Cursor, Copilot, Antigravity and Windsurf.

NordRelay is a secure remote control bridge for coding agents, connecting Codex, Pi, Hermes, OpenClaw and Claude Code to Telegram, Discord, Slack, WebUI with streaming replies, sessions, files, voice, queues, artifacts and access controls.

Token usage dashboard for Claude Code — tracks costs, sessions, models, and tools with real-time updates

Library of multi-agent teams built on Ejentum cognitive harnesses (adversarial code review, eval trio, side-by-side eval, n8n quickstart, harness integration patterns). Drop-in deployable artifacts for any agent runtime.

Proposal-first research, grounded in evidence. ScholarClaw searches the real literature, stress-tests novelty, orchestrates review and revision, and helps turn rough ideas into stronger, more defensible papers.

A comprehensive 10-project curriculum for developers to learn agentic coding mindsets. Covers rapid UI generation, documentation, refactoring, security patching, and performance optimization using state-of-the-art AI coding assistants.

Modular Python 3.11+ coding and agent platform — 130 modules spanning LLM agents (13+ providers), graph RAG, static analysis, git ops, cloud and container deployment, all exposed as 612 Model Context Protocol tools. uv-managed, 36k tests with a zero-mock policy.

High-performance Rust LLM gateway implementing the Open Responses API. Unified access to OpenAI, Anthropic, Google, Mistral, Ollama, HuggingFace, and AWS Bedrock with cost tracking, prompt compression, smart routing, and encrypted credentials.

v0.6.0 causal console. AI-powered network log analyzer with LLM-assisted RCA (Junos / EOS / FRR / SONiC / Cumulus). Local, Claude, or Grok. Sanitize-before-LLM. 423 tests. MIT.

🤖 Explore essential AI tools for building, automating, and monetizing projects across content, video, e-commerce, and more.

The kanban that fills itself in. Watches your email, Slack, meetings, Linear, Jira - reads, writes, and moves cards as work evolves. Open-source, MIT, local-first. Built on Claude Cowork's Live Artifacts.

Spawn and manage sub-agents in visible tmux panes — the orchestrator that makes multi-agent boss mode work for pi coding agent.

63 deterministic quant computation tools for autonomous financial agents. Options, derivatives, risk, portfolio, statistics, crypto/DeFi, macro/FX, TVM. 1,000 free calls/day — no signup.

Android phone control for pi-agent — 36 tools to see, touch, and automate any device via ADB

AI Computer Use for Claude Code — The open-source alternative to OpenAI Codex's playwright-interactive. Dual-engine: Win32 API + Playwright. Control WeChat, DingTalk, Feishu, QQ, Slack, Teams, and any web/Electron app. Automated QA, viewport testing, visual feedback loops.

基于 DeepSeek 大语言模型的 AI 编程助手 Agent —— 自然语言驱动的终端编码助手。支持自动读写文件、代码搜索、命令执行、Git 管理，复杂任务智能拆解与多 Agent 并行执行。

Multi-agent social simulation as a Claude Code skill. Zero dependencies — predict anything with /crowdcast simulate.

A notification inbox solution for tmux, because things happen while you're not looking now. Put in the intray and check at your own pace. 🤖 📨 👨‍💻

Agentic knowledge retrieval redefined with an AI agent system that combines traditional RAG (vector search) with knowledge graph capabilities to analyze and provide insights about big tech companies and their AI initiatives. The system uses PostgreSQL with pgvector for semantic search and Neo4j with Graphiti for temporal knowledge graphs.

Agentic Working with LibreOffice

MCP server that turns Claude into a Fantasy Premier League analyst. 11 tools: captain picks, transfer suggestions, player comparison, hit calculator, chip strategy, differentials, fixtures, price predictions, live points, squad scout. pip install fpl-intelligence

Repo-local verification protocol for AI coding agents: acceptance criteria, separate verifier roles, proof artifacts, and evidence-backed done claims.

Local Rust codegraph and verifiable workflow for AI coding agents — project maps, change and test impact, MCP queries, and diff-backed implementation audits.

Build Your Own AI Employee. The complete starter kit for OpenClaw + Hermes Agent. 155 deduplicated skills, drag-and-drop workspace, case studies, install scripts.

LLM multi-agent quantitative trading system for US equities. 9 specialized agents (8 daily + 1 quarterly meta-reflector) with schema-enforced reasoning chains, deterministic Python risk filters, real Alpaca integration, and quarterly self-evolution under a 10-invariant safety system.

Multi-agent platform using OSINT tools to create geopolitical analysis

Open-source AI coding agent — 61 tools, 6 modes, 24 personas, 20+ models from 8 providers. Creative Studio for images, video, music, voice. 3M free tokens or BYOK.

Claude Code skills that wrap your full dev cycle — ticket intake, ATDD planning, code review, doc-drift audits, PR writing, and changelogs.

AI Acceleration Repository

Agent Task Markdown: a Markdown runbook format and CLI for organizing agents into repeatable, inspectable, and coordinated workflows. 一种 Markdown 格式拓展和 CLI工具，用于把多个 agent 组织成可复用、可检查、可协同的工作流。

🏛️ AI招投标全流程智能助手 | 商机甄别→投标研判→标书编制→合规审查 | 12大环节一站式闭环 | 政府采购·工程招标·服务类项目 | WuKong/Claude/OpenClaw Skill

The Open-Source MCP Firewall & Security Gateway for AI Agents. Inspect, redact, and control tool calls. Proxy mode (universal) and Inline SDK mode (Go).

🔁 Finishes your entire backlog while you sleep. The AI orchestrator that DOES the work end-to-end on ANY LLM — discover → implement → verify → merge → 24/7 — behind safety gates, at up to 90% fewer tokens. 48 extension points. Not a chatbot. A worker.

IntentFrame security plugin for Hermes Agent (Nous Research) — an external policy checkpoint that gates terminal, code, file, and cron tool calls before they run on your machine.

Methodology evolution engine — distill transferable principles from literature, search by problem structure

Browser workflow CLI for LLM agents

Collective AI memory for multi-agent teams. 10-stage GAMR search engine, knowledge graph (Apache AGE), document ingestion, 40 MCP tools.

macOS AI workspace — chat, multi-agent orchestrator, code agent, design tool in one sidebar. Supports Anthropic, OpenAI, OpenRouter, Ollama, Gemini, and any OpenAI-compatible provider. MIT.

Standalone Windows desktop dashboard for Claude Code usage — session & weekly limits with a reactive Clawd mascot. Software-only port of Clawdmeter, no ESP32 hardware.

Run Claude Fable 5 on Opus 4.8 in Claude Code. The Mythos-class model pulled by export controls — brought back as a system prompt. One clone + install: leaked Fable 5 prompt, a measured execution playbook, test-after-edit + grounding hooks, and design/MCP/test skills. "Fable 5 Lite," done right.

Move your Claude Code history, memory, and sessions between machines (Linux/macOS/Windows), with paths fixed automatically.

Persistent decision memory for AI coding agents. MCP server for Claude Code, Cursor, Cline.

Make Claude admit when it half-assed your task. A Claude Code skill. (Now, can be used for Codex as well as Antigravity).

Eight security skills for Claude Code: secret scanning, Python SAST, prompt-injection testing, and HTTP, JWT, Dockerfile, CORS and dependency auditing. Standard library only, no runtime dependencies.

Local WhatsApp-to-persona workbench for parsing chats, ranking fine-tuning paths, and exporting SFT/DPO datasets, memory profiles, and character files.

Self-hosted private AI agent workspace for local and OpenAI-compatible models. Chat, code, use tools, manage memory/skills, route tools intelligently, and deploy Docker-backed apps from one browser UI.

A 7-layer scaffold for production AI agent system prompts. Security-first, multi-tenant by design.

🚦 Senior-QA review skill for Claude Code: runs a regression hunter + a change reviewer in parallel, then gives one read-only SIGN OFF / DO NOT SHIP verdict with file:line evidence.

Advisory file locks so multiple AI coding agents can share one Git worktree.

An event-sourced knowledge runtime for coding agents.

Local observability for Claude Code. Captures sessions, sub-agents, and tool calls to Postgres via HTTP hooks.

Reflection/judge layer for OpenCode & Claude Code — catches premature stops, enforces workflow gates (tests, CI, PRs). 78% of agent stops are premature.

Persistent memory, BM25 code search, MCP tools, and hook guardrails for AI coding agents — Claude Code, Codex CLI & Antigravity. One local-first .ai/ layer per repo. No SaaS, no network on hot paths.

Local AI / LLM harness for professional programmers

Arc Gate — LLM proxy with prompt injection detection. Bendex Geometry.

Multi-model consensus debate via the filesystem. LLMs propose, peer-review, rebut, vote and synthesize a group-confirmed answer. CLI + MCP.

Offline AI assistant - chat with your documents locally. No cloud, no API key, no data leaks. Built with Python + FastAPI + Ollama + LangChain.

Claude Max — Anthropic extended plan with 20x message volume, Fable 5 model access and extended thinking for deep research and coding workflows.

Turn a local codebase into a source-linked, refreshable design wiki that becomes the context layer for agent-assisted development.

It turns Playwright specs from deterministic test scripts into AI-readable QA scenarios for live staging validation.

MCP server that wraps the xAI Grok CLI. Lets Claude Code, Cursor, Cline, and any MCP host use Grok as a peer code reviewer, adversary, and second-opinion consultant.

Real-time cross-machine MCP relay for Claude Code agents

Claude Code 委派 plugin:把任务派给换脑的子 agent(也可 --codex 委派给本机 codex),既省主 Claude 的 token,也借不同模型/harness 的视角。

[ICML'26] Codebase for PersistBench: When Should Long-Term Memories Be Forgotten by LLMs to benchmark cross-domain leakage and sycophancy in memory augmented LLMs.

Swift/SwiftUI library for rendering LLM-generated <artifact> blocks in chat interfaces. Supports Markdown, JSON, CSV, Code, SVG, GeoJSON, HTML, React, Mermaid, LaTeX, Vega-Lite, GLTF, USDZ.

Mcp server code to setup muapi to work with clients like Claude, Cursor etc.

The operating system an executive runs their company from — research, communications, CRM, content, and operations. Claude Code is the foundation; HEADING OS is the value built on top: sovereign, security-first, your data kept private.

Connect Google ADK (Agent Development Kit) agents to Telegram, Discord, Slack, and WhatsApp with minimal code, featuring real-time cross-device session synchronization.