Code agents

Skill letting Agents scan a repo, ask what it cannot infer, then generate a complete open source file collection i.e. README, LICENSE, contributing, security, changelog, CI, launch playbook, etc.

Claude Code 增强版，支持本地私有化部署，无云端依赖，支持私有化部署；同时适配DeepSeek、通义千问等国产主流大模型，兼顾OpenAI模型兼容，支持中英双语交互，界面与提示中文适配，且会持续迭代更新，优化性能、适配更多模型，部署简单且功能稳定，在保留原版核心Agent能力的基础上进一步扩展实用功能，提升开发体验。

A modular coding-agent runtime for local models with a CLI, full-screen TUI, VS Code extension, and desktop app built on the same tools, safeguards, and workspace state.

A personal financial advisor that runs locally. Plaid CLI + SQLite + Claude Code skills. Fiduciary-grade advice grounded in your real data.

A general-purpose interview training officer for tech roles (Claude Code plugin): mock interviews, debriefs, progressive L1-L5 drilling, capability tracking, pipeline management, resume tailoring.

MCP server that lets your AI assistant read and write Figma in real time — no API token, no rate limits. Works with Claude, Cursor, Copilot, Codex and any MCP client.

通过 HTTP API 让 AI Agent 控制 Android 设备的开源自动化应用

Event-driven AI coding agent for GitHub: watches issues, runs headless Claude Code in isolated git worktrees to triage bugs & features, and opens PRs automatically. Stateless, self-hosted, written in Go.

本机 AI Agent 环境合规检测与修复 — 扫描代理泄漏、时区指纹、MCP 密钥等风控信号，降低 Claude / Cursor 等账号封号风险

把《孙子兵法》当作决策纪律来执行的 AI Skill：先问询后诊断，输出结构化战略诊断文档。适用于 Claude Code / NewMax。

The Fable Method: a structured problem-solving loop that gives any model Fable 5 grade thinking. Four Hermes Agent skills (think/act/prove/grow) + adversarial eval.

One MCP server that fronts many MCP servers + Skills behind a small tool set and routes to the best one, keeping an agent's context tiny. Migrate your Claude Code MCPs/skills behind it.

SAGE — Save AI coding tokens by compressing terminal output, keeping raw logs local, and tracking real savings. 🧠S.A.G.E - Smart Agent Guidance Engine for AI coding assistants. by⚡ PsYc+GoD AI&ML 🤖 | IF YOU DONOT USE SAGE RUN install or PYTEST. SAGE WILL NOT ACTIVATE IN YOUR LOCAL ENVIORMENT.

Three portable Agent Skills for research, repository deployment, and pre-install safety review.

Local room where AI coding agents collaborate on one codebase via MCP — collisions prevented, human in command.

SABBA - Security Templates CLI & MCP Server for coding agents that prove every finding by running it

A launch playbook your coding agent can run — take a shippable AI product, agent, SaaS, or devtool from ready to launched, no audience required.

Usage, cost and account toolkit for Claude Code, Codex and other AI coding agents

The terminal AI agents can drive — and the cockpit to run them from. 99 MCP methods / 21 namespaces, agent Inbox, verified worktree fleets, diff review & rollback. macOS / Linux / Windows, local-first, $0, MIT.

Give your coding agents correct architecture context: design declared once in git, mechanically checked, drift-detected, and rendered into verified briefs

The clean slate a fresh Claude Code should start from — clean context, locked credentials, guarded egress. Isolated profile, pick-and-choose.

W.A.Y? (Who Are You? : I'm not a developer) — a personal AI harness that learns you, not a framework you learn

AI-human engineering platform where AI agents and humans collaborate as teammates to plan, code, review, and ship in isolated sandboxes. An append-only event store gives a full audit trail and DORA-grade metrics derived from the stream, with built-in financial-compliance templates. FastAPI + LangGraph.

Your AI Quality Agent, putting app testing on autopilot.

Plot anything with zero effort. Editable charts, diagrams, figures, posters, and slides.

Local-first memory for AI-assisted coding. Git shows what changed. Backstory shows why.

Turn untrusted source material into compact, attributed AI skills through evidence gates and deterministic safety checks.

Mine reusable skills from your coding agents' transcripts (Claude Code, Codex CLI, or any agent) with outcome-weighted scoring and a local review queue

The tested, tool-agnostic AGENTS.md kit — verified templates, a CI linter, and migrators from .cursorrules/CLAUDE.md/Copilot/Windsurf/Cline/Aider.

A ratified constitution + harness-neutral enforcement regime for AI coding agents — hooks, a cold-startable project-state model, and the adversarial-review harness used to harden them.

Immutable, reproducible, least-privilege runtime environments for AI agents

Portable Agent Skill that removes AI writing patterns while preserving the writer voice. Works with Claude Code, Codex, OpenClaw, Cursor, and more.

Behavioral guidelines for LLM tools (AGENTS.md). Installer wires Claude Code, Codex, OpenCode, and Kimi Code; Cursor/Cowork via paste. Principles 1–4 Karpathy-derived; 5 by maintainer.

AI software factory control plane for GitHub issue-driven autonomous workflows, isolated agent sandboxes, governance, artifacts, and human review.

GitHub-native Loop Engineering skill: evidence-gated Issues and Projects workflows over the official GitHub MCP Server.

Disciplined minimal code orchestrator with gated multi-model review before subagents ever start writing code.

Claude code / Open Code Skill guiding you step by step, to generate continuous-shot video using Gemini web interface

An open-source digital micropad for agentic work — turn your phone or tablet into a physical-feeling control deck for AI coding agents

Open-source Outcome Packs that turn rough ideas into coordinated, independently verified outcomes with Codex.

120 brand design systems as plain-text DESIGN.md specs for AI coding agents. Real colors, fonts, components and guardrails, reverse engineered from live production sites.

Plan, execute, and review coding-agent work in one desktop workspace.

The agent-first IDE: run a fleet of coding agents (Claude Code, Codex, Gemini, Copilot, Antigravity) across isolated git worktrees, with a commit-time review gate. macOS · Windows · Linux.

Production-ready memory framework for AI agents. Dual-agent synthesis, self-evolution, composite scoring, multi-tenant isolation. REST API, Python SDK, CLI.

Local, offline safety net for AI coding agents — records every file change and reverts anything (one file → a whole rm -rf), and alerts on secret reads. Claude Code · Codex · Cursor. Zero deps · MIT.

A ready-to-run Buzz workspace in your browser — one command starts the Buzz desktop, relay, storage, and optional Codex, Claude Code, and Goose agents

Privacy-first open-source contract review CLI. Multi-agent AI pipeline strips PII locally (fail-closed) before any cloud call. 21 contract types, 17 AI providers, local-first by default with Ollama. Runs as terminal command, TUI, or Python library.

Turn one decision into a judged tournament of solutions, then pick the best — a Claude Code skill that generates candidates, auto-derives the rubric, judges independently, and returns a defensible winner.

⇄ Port your session between coding agents (Claude Code, Codex, Grok Build). Type /seshport, open the other agent, resume with full context. On npm, PyPI, crates.io & Homebrew.

Find what your AI agent gets wrong — before you have a rubric. Qualitative eval for PMs.

Cross-session memory and recall for AI agents — git-synced knowledge base, hybrid semantic+TF-IDF search, auto-distillation with secrets scrubbing

A modular Agent Skill system for strategy, creative, content, and brand teams—from brief framing and evidence to insight, narrative, visual direction, and delivery review.

The open-source control plane for AI agents — skill routing, context governance, trustworthy execution, evidence, security, and multi-agent orchestration.

MCP server that drives Google Flow (Veo / Nano Banana) through its internal tRPC API, with a hard credit-cost gate

Multi-Agent Code Evolution Platform — 4 LLMs compete, evolve, and breed code through a JIT compiler judge

MCP server for SERPHouse API. Enables LLMs to perform live, geo-targeted Search engine queries. Built with TypeScript.

Use existing brand guidelines with AI. Turn websites, PDFs, and Figma into a portable .brand runtime through MCP.

Public source of the Dreadnode capabilities in app.dreadnode.io — agents, tools, skills, MCP servers, and workers.

🧠 ctx is a queryable world model of a codebase, built to ground and govern the language models that modify it

Let AI agents see, debug and drive running WPF apps - visual tree, bindings, screenshots, clicks and text input over MCP. Snoop + Playwright for AI.

Offline-first, precision-first security linter for SKILLS, MCP, plugins, configs and other AI infrastructure.

Team operating model for hybrid human+AI delivery: one shared, drift-checked contract for authority, risk tiers, evidence, review, and done — with cloud-expert guardrails (Google Cloud, AWS, Azure, Alibaba Cloud) and Google ADK/Antigravity skills built in, routing agent-craft work to companion skill plugins.

Local-first action assistant for durable, reviewable software work.

Evidence-bounded cannabis cultivation operations Augment for crop plans, diagnostics, calculations, harvest review, and operating records.

Know what your agents are doing

Bridge Claude Code → Grok Build: shared rules/skills, hook adapter hard-gates, optional memory mirror

Share agent-generated Markdown as links — GitHub gists or self-hosted, via MCP

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

Multi-agent medical assistant for medical Q&A, RAG, web retrieval, and medical image analysis with human review.

A codebook demonstrating Gemini tool usage and function calling execution

The unified, OpenAI-compatible AI router. 12+ providers, 100+ models, automatic fallback. Built solo from a rented room in Peru. Star + donate to keep it alive.

"A cozy, you-owned, private local alternative to frontier platforms, Character.ai, SillyTavern, and hosted companion platforms. Vanilla HTML/JS client using your own API keys. Released CC0."

In this tutorial, we have added step-by-step instructions to build your own AI chatbot with ChatGPT API. From setting up tools to installing libraries, and finally, creating the AI chatbot from scratch, we have included all the small details for general users here. We recommend you follow the instructions from top to bottom without skipping.

A modern, fully-typed PHP client for the OpenRouter API — chat, streaming, tools, structured outputs, memory & more.

A local-first desktop dashboard for macOS and Windows that turns Codex CLI and app logs into clear insights on token usage, estimated costs, models, and projects.

Codex CLI tweaked for Android/Termux (self-update + build version)

Telegram bot for controlling a local Codex CLI session from an allowlisted chat.

Anthropic/OpenAI-compatible API layer over the Codex API with multi-account routing.

PageIndex-inspired agentic RAG app for vectorless document QA, FastAPI, multi-document retrieval, context compaction, and self-hosted AI workspaces.

The code intelligence layer for AI coding agents. Semantic indexing, graph navigation, and repository intelligence

Frontend-agnostic seamless session continuity and switching for Claude Code and Codex

🤝 装在你电脑上的 AI 编程搭档（macOS GUI + CLI）：把项目文件夹丢给它，用聊天布置任务——自动读代码、改代码、跑命令验证，全程可见。支持 DeepSeek / Kimi / 任意 Anthropic 兼容模型；截图粘贴看图干活；技能系统；数据全本地。

PheroPath is a stigmergy-based communication protocol that allows AI Agents to leave invisible "pheromones" (signals) on files to coordinate tasks, warn of risks, or share insights without modifying the file content itself.

基于“躺着学”长期雅思教研与学员服务实践整理的 IELTS Agent Skills，覆盖学习计划、作文批改、口语陪练、阅读与听力复盘、词汇和模考复盘，支持 Codex、Claude Code、Cursor、WorkBuddy 等本地 Agent。

全能型 Minecraft 启动器 | 基于 CustomTkinter 现代化 UI，内置 BMCLAPI 国内镜像加速，支持 Forge/Fabric/NeoForge/Quilt 等 8 种加载器与版本管理；集成模组/整合包/服务器管理、P2P 联机、AI 助手、音乐播放器、性能悬浮窗、动态主题、成就系统、崩溃分析、插件系统、多语言、自动更新。

Intent-driven idea development and work system for AI coding agents. Plain-Markdown intent stores serve as durable project memory, intents link into a provenance graph, work moves through a fixed intent development life cycle with human sign-off at every gate - or hands-free in auto mode.

Claude Code skills for IWE — graph-aware reads and refactors of markdown knowledge bases

Catalogue francophone de skills portables pour Claude Code, Codex, Cursor, le Figma Agent et Figma Make, fondé sur le standard Agent Skills.

The debugger for AI agents — capture every run, inspect every decision, pause and inject live, fork from any step.

Ready-to-install skills and plugins for Codex, Claude Code, and AI coding agents: practical workflows for app delivery, architecture, research, design, and agent tooling.

Infrastructure access broker for AI agents — SSH & Kubernetes. Per-operation ephemeral credentials minted by a separate signer; the model never touches one. MCP stdio / HTTP+OIDC.

Chinese template for designing Multica multi-agent + skill workflows around task type, budget, models, and verification gates.

Organize cloud infrastructure context, orchestrate AI agents, and serve structured cloud data through MCP.

Local-first SIEM flight recorder for AI coding agents: MITRE-mapped audit trail, sequence detection, DLP

Local Codex orchestration for solo developers running long tasks without babysitting: fresh worker and critic cycles, files as memory, self-improving loops, a live dashboard, and ChatGPT control via MCP.

Eyes for AI coding agents 👁️ — render → perceive → report → fix → re-render. A machine-graded visual feedback loop (DOM/contrast/OCR-grounded + optional vision LLM) agents consume to self-correct before claiming done.

Product discovery workflows for Claude Code: from hypotheses to validated PRDs, with evidence your AI coding agent can read.

A taste system for AI agents. 288 skills, 80 agents, 12 rules, and 8 hooks that turn generic AI output into work with genuine design quality. Anti-slop detection, typography craft, color systems, brand voice, product strategy, and 50+ specialized reviewers across UI, industry, platform, and content domains.

MCP server + CLI that turns existing task systems into persistent agent context. Keyword/native retrieval by default; optional dense retrieval; RRF and provenance. Adapters: TickTick, Obsidian, Notion, GitHub, Airtable, Google, OKF, Taskmaster, Beads.