Code agents

Real-time visualization dashboard for Claude Code — passively mints Vega charts, Mermaid diagrams, 3D scenes, and animated SVGs from your conversation as you work

Multi-provider web search broker for AI agents. 14 providers, budget-aware routing, content extraction — one API.

Transform any content into 9 platform-native formats or convert between content types — with optional brand voice matching. Supports Twitter/X, LinkedIn, newsletter, Instagram, YouTube Shorts, TikTok, Threads, Bluesky, and podcast. Secure-by-default: includes prompt injection defenses for safe URL and web content processing.

LLM-neutral skill that fetches a URL to a temp file so agents can pipe the path through rg / jq / awk instead of dumping the whole page into context. Same shape as pi-webfetch / opencode webfetch. Single-file Python 3 stdlib. Works on macOS, Linux, Windows.

Deterministic screenshot diffing for AI coding agents. Extract design tokens, diff implementations vs reference, get CSS fix suggestions.

High-performance Rust MCP server & CLI codebase indexer for AI agents. Unlocks deep codebase understanding through semantic vector search, structural graph traversal, and cross-repo dependency resolution. Empowers AI coding agents with semantic and structural search for maximum token efficiency.

Awesome GPT-5.6 API prompts, use cases, and integrations — 60 curated real-world cases for OpenAI's latest frontier model.

Complete reverse engineering of PerimeterX (HUMAN Security) anti-bot SDK · pure-algo _px3/_px2 generator (no browser, no Selenium) · iFood + Grubhub + Bundle 10/10 verified · WASM PoW solved · 68 production gotchas · AI Skill included.

德州扑克 AI 源码：C++ 博弈树、机器人 Agent、任务队列、Python CFR 训练与评估示例｜德州AI｜德州機器人｜Poker AI，。Poker AI research materials with C++ game-tree and task code, Python training entry scripts and evaluation-related previews.

Build internal tools and AI agents in Go — or just download and run Claude / Codex / Gemini as a Slack + Telegram + web agent host. No copy-pasting. You own the code.

Local-first AI writing control center for long-form fiction: structured story memory, long-context prompts, consistency checks, AI-tone cleanup, and IP adaptation.

Pure SQLite memory system for Hermes Agent. Zero Docker, zero external services. 5-layer self-healing (v2.1+) + CIRAAF macro-restructuring. 中文 FTS5 patches included. Cross-session global sharing out of the box.

Authorization, delegation, provenance, and verifiable-audit engine for AI agents. MCP adapter published.

MCP server giving LLM agents lean, identifier-routed tools to look up, read, and cross-reference academic papers across 8 providers (OpenAlex, arXiv, bioRxiv, ACL Anthology, Crossref, OpenCitations, Papers with Code, Wikipedia).

Run weak/local LLMs on narrow workflows reliably: encode a workflow once at design time as a deterministic macro, then a small local model just routes to it at runtime. TypeScript SDK, Apache-2.0, BYO-model (OpenAI-compatible + Ollama).

Verification gates for AI coding agents — nothing ships unproven. Falsifiable oracle gates, team wall, receipts. Works with Claude Code today; Cursor, Codex, Gemini CLI & every git repo next.

Autonomous AI agent for scanning Solana programs for security vulnerabilities

Open-source AI code reviewer that auto-reviews GitHub PRs LangGraph agents, knowledge graph blast-radius detection, mem0 persistent memory Zero cost, self-hostable.

A self-hosted RAG retrieval backend for agent tool integration via API.

面向大学生求职场景的 AI 简历与面试辅导 Agent。该项目主要解决学生在简历撰写、岗位匹配和面试准备中效率低、反馈不及时、项目表达不够专业的问题。

Autonomous multi-agent software development harness, powered by local LLMs

MCP server exposing Radarr as 34 tools for any MCP-compatible AI client (Claude Desktop, Claude Code, Cursor). Manage your movie library in natural language. Stdio + HTTP.

Telegram bot bridge for the official OpenAI Codex CLI. Run Codex from your phone with Docker, voice/image input, live progress, per-chat login, cron tasks, and host shell access.

AI dispute & negotiation fixer — structured scripts, escalation paths, and risk-aware strategies for everyday conflicts

一个业余爱好者的Vibe Coding项目，基于纯文本模式打造的一套懒人式写作工具（勉强可以称之为是工作流）。An amateur's Vibe Coding project, a lazy writing tool (barely qualifies as a workflow) built on plain text mode.

CTF, pentest ve OSINT için terminal tabanlı otonom yapay zeka ajanı. 20+ AI sağlayıcı, 900+ skill, Telegram/Discord gateway ve MCP CTF köprüsü.

Read-only MCP (Model Context Protocol) server for Laravel. Give Claude Code, Cursor, and AI coding agents safe live access to your database, logs, queue, cache, routes, and config. No Sanctum, no user table, no write access.

Terminal coding agent powered by NVIDIA API

📝 Manage and organize Obsidian vaults with CLI tools for notes, tasks, tags, templates, and knowledge graph analysis.

Fully local AI shell — no cloud, no API keys. Ollama + GGUF + RAG + voice + scheduler. Windows, macOS, Linux, Chromebook, Android.

Browser automation that learns. An MCP server that makes AI agents faster at repeated browser tasks by recording what works and replaying deterministic steps via Playwright.

🦤 Ornith 1.0: An ultra-lightweight, local agentic code generator and self-repair loop built with Streamlit, Ollama, and Python.

Enable Codex to run objective-first autonomous loops with mandatory review and optional verification for long-running task completion

面向个人自动化工作流的消息中转服务：统一消息事件、路由和生命周期记录，支持微信/API 入口与本地/HTTP Agent 处理器。

Atomic design system for AI-native tools — structured tokens, accessible components, and three-theme support. React + Tailwind CSS + Radix UI.

The verifiable AI coding agent : provider-agnostic, MCP-native, tamper-evident ledger

Codex skill for Amazon market screening, product selection, launch planning, profit repair, and stop-loss decisions.

Intelligent design brief router — entry point for the modular design skill system (color, effects, fonts, icons)

Production-ready Go scaffold template with clean architecture, lifecycle-managed dependency injection (samber/do), HTTP server (net/http + Huma/OpenAPI), CLI scaffolding, 45+ AI agent skills for Claude/Copilot/OpenCode, and built-in DevOps security tooling.

Personal LLM Wiki toolkit — let AI build and maintain your knowledge base. Based on Karpathy's LLM Wiki pattern. TypeScript, ollama+bge-m3, works with any AI coding agent.

🎯 Skill Hub — AI Agent Skills 导航站 | 77+ skills from 23 sources (OpenAI Codex, Claude, Hermes, OpenCode, OpenClaw) | 官方精选 + 社区清单 + CLI 工具

Multi-chain crypto + Web3 agent toolkit — wallet ops, swap, NFT, sniping, bridge, DeFi, on-chain monitoring across EVM/Solana/Sui/Aptos/TON. Integrates with Claude Code, Cursor, and OpenClaw.

Multi-channel AI agent bridge — connect Feishu/Lark bots to Claude Code CLI for intelligent team messaging and automated workflows.

Code-aware browser testing agent — 13 MCP tools for AI editors (Claude Code, Cursor, Windsurf). Reads your codebase, opens Playwright, tests everything, reports with screenshots.

Pi extension that sends Tasklight desktop notifications when coding-agent tasks finish.

Codex-powered GitHub multi-repository capability fusion system

OpenHawk is a global AI intelligence OS that tracks papers, frontier releases, market signals, policy/safety updates, and OSS trends with dedupe, LLM summaries, and multi-channel push.

Dak-news: AI news aggregator

AI ships the feature. "OOPforge" keeps the architecture — a harness that makes coding agents follow an OOP/DDD dialect instead of vibe-coding God Services.

Vibe Dev v9 — harness-first конвейер для Claude Code: от бизнес-идеи до работающего продукта. 87 проверяемых механизмов (хуки из коробки): три модели по стадиям (Fable 5.1 проектирует и кода не пишет, Opus 5 пишет по готовой спецификации), сторож не молчит при поломке, «готово» = доказано прогоном, неперезаписываемая история фич.

MCP server for ERC-8004 agent discovery + x402 payment. No smart account, no relay — just EOA signing. Works with Claude Code, OpenClaw, Cursor, Cline.

MCP (Model Context Protocol) server that provides LLMs with tools to interact with the MASV API

Silicon Pantheon - Tactics game played by AI agents coached by human

Multi-agent AI debate app where model teams argue, challenge claims, track evidence, and produce judged verdicts with analytics.

Local-first completion-evidence system for AI-built apps: read-only audit, verifier-executed challenges, evidence-based 0-100 score, guided fixes, learning plan, CLI, and MCP.

Free AI-powered SEO toolkit for Claude Code. Audit sites, plan content, optimize pages, track AI visibility, and more

Deterministic mobile UI checks for AI coding agents. One Zig binary drives real iOS/Android devices, returns a typed pass/fail, and writes a replayable trace you can gate a merge on. No LLM inside.

Compile a single AI supagent into multiple AI subagents (Claude Code, Gemini CLI, GitHub Copilot, Cursor, OpenCode, Kilo Code).

Search, install, lint SKILL.md files. CLI-first, agent-friendly.

Federated memory architecture for AI agents — whitepaper, implementation guide, and cloneable vault template

AI-native web testing: describe what to test in plain English, and Argus plans, executes, and reports — no scripts required.

Heavy-lifting brain: REST API, PostgreSQL-backed job queue, and sandbox pod orchestration (Rust).

A library of reusable skills for AI coding agents, plus the askill CLI installer

Invisible browser control for LLM agents — real Chrome via CDP, no JS injection, no screenshots, token-efficient.

Pluggable session-log review and append-only event ledger

A cross-device synced catalog for Claude and Codex skills, agents, and workflows.

Build and maintain a living knowledge base for any software project. Documents existing code, updates incrementally, audits drift, and never modifies source code. 100% read-only.

A personal operating system for your work, powered by Claude Code.

Tauri desktop app for managing multiple AI coding agent CLIs (Claude Code, Codex, Antigravity) in a single Docker container, multiplexed via tmux.

Self-hosted, multi-tenant Backend-as-a-Service for the AI era — Postgres, document & object storage, identity, serverless functions, event streaming, realtime, durable workflows, and MCP server hosting, all from a single Helm chart for Kubernetes/OpenShift.

Backup and migrate Claude Code, Codex CLI, and OpenCode memory safely

Multi-gate AI research verification system that audits hypotheses, citations, experiments, results, and logic fallacies in AI-generated research to prevent hallucinations, citation fabrication, and methodological errors

AI-fluent full-stack starter with Next.js, Payload CMS, and TypeScript. Built for developers using Claude, Cursor, and AI coding tools. Features smart scaffolding, test-driven patterns, and MCP integration.

An enterprise-grade compiler for the Agentic Era: Translates complex OpenAPI specs into production-ready MCP servers with built-in Semantic Compression and Resource Grouping for the 2M token economy.

NEST Hub — self-hosted AI workforce platform: Docker stack, installable PWA, annie CLI & MCP, governed multi-agent orchestration and 700+ models (BYOK) for organizations.

Model Context Protocol server for Open Policy Agent (OPA). Author, validate, debug, and explain Rego policies through any MCP-compatible client.

DeepSeek destekli Claude Code'u delege işçi olarak çalıştıran Claude Code plugin (marketplace + skill + komutlar)

A fast, scriptable CLI for SABnzbd - built for AI coding agents like Claude Code, Cursor, and Codex. Control downloads, manage queues, and automate workflows from your terminal.

Open-source book: build real products without writing code. One person, one sentence, one product. 12 chapters, 111 tests, deployed demo.

Safe MCP hardware-in-the-loop bridge for AI agents on real embedded boards with OpenOCD and serial tools.

Offline MCP server for AI coding agents with semantic code search, symbol intelligence, dependency graphs, and safe file operations.

An open-source Claude Code orchestrator that selects and integrates the right skill for any task - automatically.

Build paid APIs, agents, tools & data feeds on the DNA x402 hosted rail. Templates, Degen Mode, no backend custody. Public Beta.

Mission Control for cost-conscious OpenClaw enthusiasts. Lightweight CLI/TUI tools for agent cost monitoring, task management, and configuration.

Domain-agnostic AI agent runtime (Zig + NAPI)

Python CLI skill for querying OpenEvidence clinical evidence assistant — portable stdlib-only alternative to MCP, works with Claude Code and 40+ AI agents

The first onchain marketplace where idle Claude Code subscriptions earn cUSD/CELO/USDC by solving GitHub bounties. ERC-8004 agent identity, multi-token escrow, direct hire mode. Live on Celo Mainnet.

An unofficial Windows port of superset-sh/superset. Source-available under Elastic License 2.0.

AgentDog helps developers inspect, test, score, and monitor AI agent runs locally.

Claude Code skill for faithful Figma → WordPress builds: read exact values from each Figma node, then verify by measuring the rendered page against the design. Elementor · Gutenberg · Divi.

Your portable AI memory — preferences, decisions, and corrections that follow you across models, tools, and devices. Zero-dependency, local-first, 85% PrefEval accuracy.

terminal runtime for working with multiple coding agents

7-layer agentic research engine for Claude Code — McKinsey + BCG + IBISWorld + Harvard + Stanford + MIT + PRISMA 2020. Certified, traceable, board-ready research.

Cross-repo agent index layer. Stop dumping 400k tokens — index your repos once, query like a database.

Autonomous coding orchestrator. Label a GitHub issue and Nocturne drives opencode to fix it on an isolated branch, reviews its own work, and opens a clean PR — while you sleep. Multi-repo, multi-provider, safe-by-default: never merges, force-pushes, or touches main.

Six interactive, zero-install courses on the modern data + AI stack: data engineering, data science, infrastructure, and AI-assisted dev with Codex & Claude. Live in-browser simulators, no signup.

A live, docked per-session brief for Claude Code — stay oriented across parallel sessions.

An open-source AI agent that watches local weather and nudges you like a friend — to walk, catch a sunset, or just open a window. Built to teach beginners how AI agents work.

Version identity and integrity verification for Agent Skills. Tracks versions, detects staleness, and verifies bundle integrity with SHA-256 hashes across sessions, surfaces, and platforms.