Code agents

Codex AI game studio: 85 skills, 163 curated tools, Unity/Godot/Unreal/Blender workflows, img2threejs, reversible automation, and visual QA.

Plan, run, and track AI coding work feature by feature—with local Markdown cards and Git worktrees.

MCP local - Code intelligence tools — with broad commands that allow agents in a huge repository to do almost anything: identify the right problem → find the right file/symbol → verify the right flow → measure the scope of impact → safely refactor → check API contracts → audit health, all quickly and accurately.

Automatic conversation between 2 OpenAI GPT powered characters who participate in a Turing test together.

专为sub2api打造的iframe嵌入式AI图片生成工具，纯前端实现，无依赖开箱即用。支持文生图、图生图、多种分辨率、批量生成和历史记录功能。

Free, open-source macOS menu-bar app that uses lifecycle hooks to keep your Mac awake while Claude Code, Codex, OpenCode, or GitHub Copilot CLI works.

/party — the skill that lets your agent sessions talk to each other. Claude Code, Cursor, Codex or any other agent: an open-standard skill plus the CLI behind it, on one machine or across machines.

AI API排行榜 - 实时139+中转站,自动排行,最高性价比中转站 Claude/GPT/Gemini/DeepSeek API中转站 | AI API Transit Station Ranking

Import pi / opencode / codex / claude-code sessions, chat history, and agents into DeepSeek Harness — one-click Sync button, slash commands, session-start migration prompt

Cortex is a sophisticated AI coding assistant that combines the power of multi-agent orchestration with Retrieval-Augmented Generation (RAG) to provide intelligent, context-aware answers about your codebase. Built with privacy in mind, Cortex runs entirely locally using Ollama or can be configured to use OpenAI's models.

Keep long-running Codex tasks moving across fresh context windows with validated cumulative handoffs.

Make any Chrome extension with AI agents — autonomous dev loop: plan, build, test in a real browser, iterate, package, release.

Self-maintaining and persistent codebase memory for AI coding agents — a deterministic AST index plus agent-written notes that flag themselves stale when the code changes. Works with Claude Code, Cursor, and Codex via MCP + CLI.

Cut large agent tool output by what it means, not by where it was cut. 13 content-aware reducers + DeepSeek Harness plugin.

Enterprise-grade Model Context Protocol server for the full Hetzner platform. Cloud, Storage Box, and Robot dedicated servers. Cost-guarded, security-hardened, every endpoint live-tested.

DSH 拖拽文件转路径插件：Codex 式拖拽，路径自动插入输入框（Drop File to Path for DeepSeek Harness）

DeepSeek Harness (dsh) Web UI Docker 一键启动 | One-click self-hosted DeepSeek AI agent Web UI. Docker Compose pulls pre-built image from GHCR built by GitHub Actions — no Node.js needed. DeepSeek 智能体、大模型 LLM 容器化部署,拉取即用、自动更新 | dsh web ui, AI coding agent, LLM harness, self-hosted LLM, docker compose, ghcr | DeepSeek 智能体框架, Docker 部署 DeepSeek, AI Agent

JMComic3 APK 逆向修改 AI Skill：自动化去除广告、移除游戏电影板块。一份面向 LLM 的结构化知识文档。

Local-first multi-agent desktop workspace powered by Codex App Server.

Local debugger for AI agents. Answer the question: "Why did my agent behave this way?" with visual replay, behavior diff, and full visibility into prompts, context, memory, retrieval, and tool calls. Open source. Works with Langchain.

TradingView MCP server: search indicators and strategies, fetch Pine Script source. Works with Claude Code, Claude Desktop and Cursor. No API key needed.

Open-source paper auditor that checks scientific claims against cited PDFs, with page-level evidence and explicit retrieval gaps.

Use your OpenAI subscription with DeepSeek Harness to access GPT models, image generation, and web search.

Run Gemini CLI or Antigravity CLI (agy) from inside Claude Code: delegate a task, get a second-opinion or adversarial code review, run it in the background, cancel it honestly. Slash commands, MCP tools, and a credential-free walkthrough.

Steadlith reuses unchanged RAG chunks with content-defined identities, cache-aware planning, and transactional indexing.

Run Claude Code agents on a schedule. They stay silent unless there's something worth telling you — a quiet day costs zero tokens.

Build-time meta-prompting framework for LLM agents. Treats a prompt as an operator, not a key — designs, audits, and scores it across 7 shapes and 3 modes, and ships a verifier.

OnDevice Local AI Studio — run LLMs on iPhone offline. SwiftUI workbench with MLX, llama.cpp, whisper.cpp, RAG, and authenticated OpenAI/Anthropic/Ollama-compatible local APIs.

A local, SQLite-backed memory and project-ops layer for coding agents (Claude Code, Codex).

transformers safetensors bananamind2_pro text-generation causal-lm chat

X-ray for TypeScript agents: inventory, refs, slop, dupes. Offline. No API.

Claude & Codex CLI but with safety 3rd and God Mode always.

Interview your idea into a PRD.md any AI coding agent can execute. Claude Code · Codex plugin. Works for non-devs. Pure markdown output.

Design minimal AI agent packs for Codex and Claude from project descriptions.

Compliance-first coding harness for working with sensitive biomedical research data.

Drive Claude Code from your phone — the same session as your desk. tmux + Tailscale + Termius, installed by Claude.

Terminal cockpit that asks Claude, Codex, Gemini, and local Ollama one question in parallel and synthesizes one verdict. Your life as markdown. GPL-3.0.

Vynix MCP server. Give AI coding agents access to your visual feedback and bug reports.

Advanced Codex migration automation for macOS and Windows.

Скилл для Claude Code: превращает сервис без API в CLI-инструмент, которым управляет агент. Режим разработчика браузера → скрытый API → CLI → Skill.

O que já existe e onde quebra — a camada que falta entre um agente e um projeto Remotion

Use third-party and Chinese model APIs as bounded Codex subagents while keeping Codex as the main agent.

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

Production-style Retrieval-Augmented Generation document Q&A: LangChain ingestion, Chroma/pgvector store, hybrid retrieval, citation-grounded answers and a streaming chat API.

Swarm (legacy) — web dashboard + autopilot for AI coding agents. Superseded by miopea/swarm-next; maintenance only.

The factory that builds software — and itself. A runtime for self-improving agentic loops: the tracker is the control plane, git is the truth, CI is the gate.

SDL, tools, runtime, and a reference backend for reproducible agentic environments.

A knowledge base for coding agents, built from Markdown, backlinks, semantic search, and Git context.

Autonomous multi-agent AI coding assistant as a JetBrains IDE plugin. Routes tasks through a Tolkien-themed fellowship (Gandalf→Aragorn→Celebrimbor→Samwise) with offline-first local Qwen inference, cloud fallback (Alibaba/Gemini/Amazon Q), and tools for code editing, terminal, git, web search, and project scanning.

An Android-native local AI runtime with MCP tools, phone capabilities, and OpenAI-compatible APIs.

AI SSH client for DevOps: terminal, SFTP, Monaco editor, encrypted vault, and OpenAI-compatible ops agent with plan-and-confirm execution.

Reference architecture and working case study for Codex × Antigravity agent-runtime collaboration.

Skills and Agents for modeling, solver tuning and more for Mathematical Optimization with AMPL. Compatible with agentic tools like Claude Code, Codex, Cursor...

DSH Studio — a local development workbench for DeepSeek Harness: project tree, Git review, terminal, and plugin marketplace (Desktop + Web)

Grok Build 从零到精通 · 智见 AI 蓝皮书 · 面向小白与 Claude Code / Codex 迁移用户的 AI Agent 实战指南 · HTML/PDF 免费下载

国内租房全能助手 · Agent Skill：一句白话提问，自动采集多平台公开口碑，生成带地图、可点回原帖的可视化报告——小区尽调/选址对比/找转租房源/租房咨询。An open-format agent skill for renting in China.

DeepSeek Harness long-term memory & self-evolving plugin: L0 capture -> L1 memory extraction -> L2 scene grouping -> L3 user persona, auto recall injection + skill synthesis, fully local.

Provenance-aware runtime security for AI agents with deterministic ALLOW / REVIEW / BLOCK enforcement.

Public Brain Researcher code, contracts, docs, and service stack

Single-binary GGUF model runtime in C — CPU/CUDA/Metal, OpenAI-compatible. Serves, scores, and trains LoRA directly through the quantized weights it deploys, with byte-reproducible adapters. Tool calls survive the token limit; sparse MoE and schema-constrained decoding included.

A desktop control plane for Grok Build, speaking ACP to a local grok agent.

免费额度找半天、领一圈，模型还不好用？帮你挑值得领的免费 AI token——太蠢的大模型不收录，吃点好的。 Find worthwhile free LLM API credits and AI trials, with eligibility, expiry dates, and claim links checked.

Evoflux is an open-source, local-first workspace where AI agents build software, conduct deep research, automate browser tasks, and collaborate in parallel. Connect any model, keep control of your workspace and data, and take complex work from idea to completion—all in one place.

Local-first control plane for AI-agent development — watch every Claude Code session live, ledger tasks/worktrees/resources, track token spend and cost, enforce rules.

peft gguf chatgpt codex v2 unsloth

Codex HUD is a persistent heads-up display for OpenAI Codex CLI.

One-click installer and updater for OpenAI Codex CLI, with optional Codex Windows App setup

A creature for every git worktree, living in your coding agent's status line. Deterministic species, rarity bands, and one view across every live session.

Official guide to CodeSoul Agent Native Skills

Agent Skills for PocketBase development — 64 best-practice rules across 9 categories, current as of PocketBase v0.40 and JS SDK v0.28. Works with Claude Code, Cursor, Copilot and other Agent Skills-compatible tools.

Graph Engineering for Agent Skills: a specification and toolchain for dynamically discovering context and building observable, testable, and recoverable agent workflows.

Claude Code usage for SwiftBar.

基于 Codex 的网络小说创作工具集skill — 从构思到完本的完整工作流，面向番茄、起点、七猫、刺猬猫小说等阅读平台。

Hellhound is an autonomous bug bounty reconnaissance and triage assistant designed for professional security researchers and bug hunters. It automates repetitive enumeration workflows, verifies asset validity, checks for dangling DNS takeover vectors, and extracts endpoints.

An autonomous local-first AI Agent that generates, runs, and self-heals Python unit tests in real-time. Supports Ollama, Groq, and many frameworks such as pytest.

macOS menubar utility to monitor your AI coding quota — track OpenAI Codex and Claude Code usage at a glance

An open-source autonomous AI OS Agent for Windows. Features zero line-drift coding, lifelong memory, Android ADB control, and proactive HITL.

Open-source AI gateway for LLM and agent traffic — multi-provider routing, guardrails, semantic caching and MCP support. Written in Go.

Always-fused retrieval over a bitemporal knowledge graph on Azure - Gremlin traversal, ingest-time contradiction detection, two-threshold entity resolution. Part 2 of the persistent knowledge layer.

Evidence-aware Bilibili video research MCP for language, vision, and multimodal analysis.

Annotate any webpage with drawings, comments, and highlights. Real-time collaboration for Chrome.

Agentic coding with personality, for every model, cloud or local

Knowledge engine for AI agents: your documents become a git-versioned markdown knowledge graph the agent navigates over MCP. Curated summaries, typed edges, cited answers, SQL over your spreadsheets, no chunking. Same 12B local model: 0/11 on multi-hop questions as top-k RAG, 11/11 as a navigator. Python, Apache-2.0, self-hostable.

Turn WordPress into an MCP server for Claude, ChatGPT & Gemini: OAuth 2.0 + API-key auth, 107 built-in tools, 36 toggleable integrations (WooCommerce, Elementor, ACF, SEO & more).

Autonomous agent platform with a Rust-native harness, permission-scoped remote access, and multi-frontend support. Built solo, from scratch.

Local-first orchestrator for AI coding-agent workloads

Watch any AI agent think. Embeddable visual tracing for chain-of-thought, skills, tool calls, and MCP - live inside the chat UI you already ship. No account, no API key.

Product-Driven Development for coding agents

Agent skill for Claude Code & OpenClaw 🦞 — remove the "Made with Gamma" watermark from PDF & PPTX exports. Free web version: gammaremover.com

Local-first technical leader workspace for reliable Coding Agent planning, handoff, evidence review, and FPGA competition workflows.

面向中国大陆行程的 AI Agent Skill：整合官方、高德、小红书、美团和国内 OTA，生成可校验的对话攻略与响应式 HTML，支持 npx 安装和引导式线上部署。

A markdown knowledge base for agents that's CLI and skill driven. Full featured with Google's OKF support and network vaults to share between users and systems.

Evidence-first legal workflow for Russian civil practice, with intake, drafting, review gates, document assembly, and privacy controls.

Advanced self-hosted AI agent harness: terminal chat, OpenAI-compatible API and MCP. Office automation with documents (Word, Excel), eMail, Telegram and SIP voice. Privacy-first, GDPR-ready.

The directory is the agent: durable Ruby coding agents in mandatory microsandbox microVMs

Turn the coding agent you already use into a focused job-search copilot.

Track every Claude Code and Codex session from your macOS menu bar. Know which AI coding agents are working, done, or waiting on you - from their official lifecycle hooks, never from CPU. Free, open source, no telemetry.

a Lua-scriptable experimental coding harness

ChatGPT backend plugin for Backstage. Handles the interaction with OpenAI and exposes an API for the front end plugin