Code agents

Engineering best practices that AI coding agents actually apply — 40+ skills, from secure coding and cloud to compliance and UX writing. BUILD + AUDIT modes. Measured: best-practice coverage 59% → 98% vs. the same model unguided.

transformers gguf code qwen-coder finetune text-generation

transformers pytorch llama text-generation code math

mlx safetensors qwen3_next text-generation conversational base_model:Qwen/Qwen3-Coder-Next

transformers gguf code qwen qwen-coder codeqwen

gguf code codeqwen chat qwen qwen-coder

AI agent skill for end-to-end hotel search and booking—compare live rates across leading OTAs and hotel suppliers, verify availability, book stays, and manage reservations, cancellations, and payments via the TourMind API.

The Regression Testing Framework for AI Agents. Replay · Evaluate · Assert · Catch Regressions — in CI. Like Jest for your AI layer.

ACP-friendly Node.js SDK for local coding agents: run Codex, Claude Code, Cursor, OpenCode, and Pi with streaming, abort, and session resume.

把本机 Codex 工作记录生成可分享的 AI 打工小票：一行命令、完全本地、隐私优先、中英双语、主题切换，并支持扫码导入微信小程序。

X-ray for documents: lossless PDF & PPTX extraction to JSON with bounding boxes, fonts, and colors — CLI, HTTP API, and an in-browser playground. Rust + PDFium.

Structured market intelligence for Indian financial events, macro context, and sector impact.

Open-source marketing skills that run on any model — with a hosted brand-memory engine. No coding agent required.

Quality-per-token GPT-5.6 Sol, Terra, and Luna model router for Codex, Work, CLI, and subagents.

AI-powered writing grader for IELTS and general English writing tasks. Instantly analyze your essays, paragraphs, or stories with detailed band scores, error highlights, and actionable feedback—using OpenAI or any compatible API. Perfect for test-prep, self-study, and language teaching!

Debugger CLI for AI agents — run, control, and inspect binaries programmatically with structured output for LLM tooling

A template repository for guiding AI coding agents to write safe, modern C++20/23/26 code using modules, concepts, modern CMake, Core Guidelines, tests, and repeatable build-test-review loops.

Log Claude Code sessions to Opik, the open-source LLM observability and evaluation platform, built by Comet. Tracing, evaluation, and skills for observable AI applications.

Playwright-powered Fanqie novel publishing skill with guides and thin adapters for OpenClaw, Hermes Agent, Claude Code, Codex CLI, and Cline.

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

Modern open-source ERP platform with CRM, HRM, Inventory, Accounting, Sales, Purchasing, Projects, POS, and workflow automation. Built for scalability, customization, and enterprise-grade business management.

Self-hosted OpenAI-compatible mock server — test your LLM integrations without exposing your API key. By Axium.

CLI tool & MCP server that turns a codebase into text for an LLM to see its context — feed code to ChatGPT, Claude, or any AI coding assistant

Fly the web on a string — a lightweight (~7MB) Rust browser-automation MCP server for AI agents. Streamable HTTP, 21 tools, HTML→PDF, plus a Puppeteer-compatible npm facade.

The loop never sleeps — you finally can. Agents automate the entire development lifecycle (write, review, merge, learn) end to end, with a published safety record. Self-host today; rentable hosted loops in development. Any GitHub repo; Gittensor-native intelligence built in.

Dialogue memory for AI agents (hermes plugin): auto-recall of facts across sessions, LLM fact extraction with a cheap gate, SUPERSEDE versioning. Local SQLite + hybrid search. One-command install.

inplan — a Markdown editor for human ⇄ coding-agent planning. CLI + desktop editor.

A repo-native coding-agent loop harness for Claude, Codex, Copilot, and other CLI agents. Agents can edit. Gates decide what lands. You set the plan in motion. The agents take a prompt, and each iteration must update specs and commit through guardrails.

Portable AI Agent Workbench for safer DNF/DFO Script.pvf inspection and editing. 自包含的 DNF PVF AI 工作台，支持只读分析与受控修改。

Spec-driven Claude Code, dropped into your repo in one command.

Use the pi coding agent (pi.dev) without leaving Neovim — π², a heavily extended fork of alex35mil/pi.nvim

A self-hosted web frontend and SSH gateway for the official Codex app-server.

Make your specs actually comprehensive. Pair your specs with tests to make your coding agent stop improvising bad code

AI agents for pentesting, code audit, fuzzing, vulnerability discovery, and reverse engineering — harnesses, sandboxes, security MCP servers, benchmarks, and evals.

Learn Codex

a CLI tool to talk with Ai Agents

Let AI agents manage your Zotero library: headless CLI + Python API to search, import, enrich, export BibTeX, and attach PDFs (Web API + WebDAV) — no desktop app required. Ships with an agent skill & AGENTS.md.

⚗️ Experimental — A markdown brain that gives your AI coding tools judgment and rigor: sharp defaults, real decisions, and the discipline to verify before saying done. For Claude Code, Cursor and Codex. It improves itself over time.

Agent skills that turn Claude Code (or any agent) into an award-winning multi-modal creative pipeline — art, music, video, story. Panel-of-Experts debate, a deterministic state graph, and an immutable continuity block that makes creative drift structurally impossible. Prose contracts, not framework code.

Continuously refine your project’s engineering philosophy — and keep AI coding agents honest with evidence-backed completion.

Manages parallel Claude Code sessions, so you don't have to.

Referee report on your economics paper before a real referee sees it — verified comments and a revision plan your agents implement. Agent Skill for Claude Code & Codex.

Zero-sidecar MCP server inside the Godot editor. AI agents (Claude Code, Cursor) inspect, author, run and SEE your game. GDScript + C#, validate-before-write, no Node.js. Godot 4.2+. Free Lite; Full adds autonomous playtesting.

A memory and continuous learning system designed exclusively for AI — your AI grows smarter the more you use it.

Review and approval for work made by AI agents. Fair Source, self-hostable, and MCP-native.

Lightweight stealth-oriented browser MCP server in Rust — one shared Chrome for many AI agents, 64+ Playwright-style tools, no Node.js runtime.

多功能 AI 编程助手 支持web/本地应用/bot接入 等

Универсальные безопасные Agent Skills для любых конфигураций 1С / Universal safe Agent Skills for any 1C:Enterprise configuration

A native Rust multi-agent operating system and swarm workspace — GPUI desktop chamber, headless gluon daemon, git-worktree isolation and an automatic merge gate.

Skill-Atlas

System design from evidence, not vibes — reads your repo as the current architecture, runs the capacity math, compares structurally distinct candidates, and ships an interactive report. For Claude Code, Codex, Cursor, and other coding agents.

using Stata with AI-Agent

把实现计划派发给另一个 AI 执行，你只负责审——纯 CLI 的协调者/executor 两角色协作工具（opencode / Claude Code / grok / codex，支持远程开发机）

HTTP + WebSocket 反向代理：把局域网端口转发到本地 DSH 服务

Self-host Supabase in production, AI-ready: read-only MCP for your coding agent with zero secret exposure, SSO, PITR backups, monitoring, disk encryption, and one-command migration off Supabase Cloud.

Your coding agent gaslights you. GODKILLER doesn't. Disk gates > vibes. claim_done only after verify.

Скиллы для Claude Code: дисциплинированный пайплайн разработки и два пред-запусковых аудита — сайта и безопасности приложения

Automatic, model-driven permission review for OpenCode

Pi coding-agent harness with durable sessions, causal history, reversible components, and approval-gated host self-extension.

Local-first AI Gateway: Connect Claude Code, Cursor, Windsurf, & Cline to Antigravity, OpenAI, Claude, & Gemini. One endpoint, OAuth auto-refresh, quota pooling & failover.

AI-powered autonomous trading agents for Polymarket prediction markets. This framework enables developers to build sophisticated trading bots using state-of-the-art LLMs, RAG (Retrieval-Augmented Generation), and superforecasting methodologies. Built with Python 3.12+, LangChain, FastAPI, and modern development tooling.

All you need is one API to let AI assist you in music creation—modify MIDI files, get suggestions, and more. No complex setup, just plug and play!

Dependency-free Telegram interaction core for model-driven bots: ordered bubbles, reactions, regular stickers, and one-shot choices over host-owned sync/async transport.

DaVinci Resolve (Free Version and Studio) MCP server for Claude, Cursor, Codex, and Antigravity. Full timeline editing, cuts, camera zoom, and color grading.

All Kind of MODEL IN ONE APP. Workspace for Claude Code & Codex — multi-model parallel sessions, Telegram remote control, scheduled cron tasks with push notifications, usage analytics, permission modes. CLI + native macOS desktop app.

Автоматическая отправка откликов на HH.ru с генерацией сопроводительных писем, решением тестов и общением в чате через AI (llama3 / OpenAI-compatible API)

open-source pentest management built to be operated by an AI agent

OpenAI Codex Desktop in-app usage monitor for Windows — tracks subscription quota/reset time, token usage, API accounts and API keys via local CDP injection. No app.asar patching.

Experimental source-available SQLite/libSQL backend for human-and-agent-native workflows, with Studio and scoped MCP access.

The portable trust harness for AI

Real-time multiplayer AI workspace. A Markdown editor where your team and your agents write in the same doc, live. Open source, local-first.

纯 Kotlin 原生 Android AI 智能体：多模型接入、子智能体协作、在线插件市场、技能自动引用、root/Ubuntu 终端、长期记忆

Abandoned, unsupported research archive for a local-first, model-agnostic LLM agent harness exploring orchestration, code retrieval, off-agent verification, deterministic replay, sandboxing, context management, and model routing. MIT.

Deep KiCad skills for coding agents

Live token spend dashboard and notifications for Herdr agent panes

Spring Boot + MyBatis 框架感知代码地图：静态分析调用链/SQL/事务/实体影响面，通过 MCP 喂给 AI 编程工具（Trae/Cursor/Claude Code），省 token、防幻觉

Remote Desktop Control for AI agents: screenshot, mouse, keyboard and window control of another machine over Tailscale, exposed as MCP tools. Built with Rust

A portable AI agent skill and architecture compiler for polished, editable, evidence-grounded Draw.io diagrams.

AI agents are increasingly given real-world power — moving money, executing trades, taking actions with no human in the loop. But autonomy without accountability is dangerous. Most autonomous systems are black boxes: they act, but they can't explain why, and nothing stops a confident-but-wrong model from causing real damage.

croit AIplane — one plane for all your AI. Self-hosted AI infrastructure connecting applications and users with models, agents, tools and enterprise data: an OpenAI-compatible LLM gateway, server-side agent execution, MCP, RAG, memory, sandbox, identity, RBAC and quotas. Routes across vLLM, SGLang, Ollama and hosted APIs.

MCP server for PostgreSQL. Works with VS Code, Cursor, Claude Code, Codex, and Windsurf.

Modified ZCode.

基于 AI Agent 的产业园区项目管理研究 · 原型验证平台（Prototype，不代表最终产出产品）

Local-first AI Career OS — research jobs, tailor resumes, track applications, and learn from every interview.

OpenAI-compatible proxy for Zcode

Names your startup, product or side project, then proves you can actually use it. Checks the domain registry, trademark, GitHub, npm, app stores and search. An agent skill for Claude Code, Cursor, Codex and 75 other agents.

Practical, tested recipes for TypeSafe's Jev decision model on OpenRouter: support triage, database indexing, file organizing, tagging, taxonomies, dedupe, PII detection, extraction, search re-ranking and a browser agent.

Audits a repository for how ready it is for AI coding agents, and returns a prioritized fix backlog with evidence for every finding.

LLM-first SEO skill for AI coding assistants. Features 16 sub-skills, 10 specialist agents, 89 python scripts, and 160+ markdown marketing skills.

Reproducing agentic KV-cache policy claims on real traces. 68k requests from 393 Claude Code sessions. LRU is harder to beat than the papers suggest.

Master Agentic AI with Google ADK: 100+ runnable Python agents for the Agent Development Kit - tools, MCP, A2A, multi-agent workflows, sessions and memory, RAG, Live API voice, adk eval, tracing and Cloud Run deployment

Airdrop optimizer - tracks live campaigns, estimates ROI, allocates capital.

DeFi protocol research agent for Solana. Scores protocols on security, traction, tokenomics, team, and moat using Claude.

Describe a Solana program in plain English - Sigil's AI agent writes the Anchor code.

LLM Engineering Claude Skills

The Hugging Face API wrapper for Delphi leverages cutting-edge models to deliver powerful features, including object detection, music generation, text classification, sentiment analysis, image segmentation, speech-to-text transcription, and text generation.

Platform and API Agnostic library for powering chatbots

150 Fast prompts OpenAi

Stack Overflow Clone with AI Chatbot integration using Open AI API. Check README for update.

A Xojo API for interacting with OpenAI