AI Dev Impact Lab JA
← Topics ranking · 2026-05
GITHUB TOPIC

#codex

GitHub repositories that have self-applied the topic "codex" — a creator-tagged metadata that surfaces how AI projects describe themselves.

41
tagged repos
87
top 40 stars
17
with tool sigs
40
shown

REPOS Repos for #codex (top 40 by stars)

Cmochance/codex-app-transfer

Local desktop gateway that translates OpenAI Codex CLI's Responses API into Chat Completions for Kimi / DeepSeek / Zhipu GLM / Bailian and other OpenAI-compatible providers.

Rust 33 AI 90 1 sig
daystar7777/agent-work-mem

Persistent shared memory and handoffs across any combination of AI coding agents — Claude Code, Codex CLI, Cursor, Aider — using nothing but markdown.

9 AI 100
duytrandt04-afk/hooker

Real-time hook event monitoring dashboard for Claude Code and Codex (expand in the furure), with session timelines, diff views, and token usage analytics.

TypeScript 8 AI 70 Solo live ↗
prevu-cloud/prevu

Open-source CLI and agent skills for Prevu — preview/staging environments for coding agents like Claude Code, Codex, Cursor, OpenHands, even OpenClaw and Hermes Agent

TypeScript 7 AI 70 live ↗
IlhamriSKY/TEDI

TEDI - Terminal Environment & Development Infrastructure. Forked of terax-ai.

TypeScript 5 AI 70 Solo 1 sig live ↗
Ozzeron/prompt-pack

Curated AI coding skills focused on reducing AI-generated technical debt — reuse before create, convention discovery, token discipline, structured review and handoff.

PowerShell 4 AI 70 Solo live ↗
oomkapwn/enquire-mcp

The most advanced MCP server for Obsidian. Hybrid retrieval (BM25 + ML embeddings + BGE reranker, RRF-fused), HNSW + int8 quantization, standalone .base file execution, GraphRAG-light wikilink communities, PDFs + OCR, stateful remote MCP. For Claude Code, Claude Desktop, Cursor, ChatGPT, Codex.

TypeScript 4 AI 70 Solo live ↗
htahaozlu/context-hud

Local-first repository context and native macOS HUD for Claude Code and Codex.

Swift 4 AI 70 Solo live ↗
skiLLM-Labs/skiLL.Md

skiLL.Md is a structured, open-source collection of reusable, self-contained markdown modules that describe how to perform specific software engineering tasks.

3 AI 70
s-w-choi/codex-failover

Local failover router for Codex/OpenAI-compatible requests

TypeScript 2 AI 90 1 sig
aayushostwal/nexus

Plugin-first AI terminal workspace for Codex and Claude Code with planning, CI/CD debugging, reusable agents, skills, TODOs, and MCP tool integrations.

JavaScript 2 AI 70
benthamite/agent-sync-template

Toolkit for keeping Claude Code and Codex instructions, skills, and hooks synchronized.

Python 1 AI 100
usernotfinded/atlas-agent

Trading agent that learns from his mistakes

Python 1 AI 100 1 sig
smartmemory/compose

AI-powered product lifecycle orchestrator — takes a product idea from intent to shipped code through agent-driven pipelines (Claude + Codex) with human gates, postconditions, and auditable traces.

JavaScript 1 AI 70 1 sig live ↗
imthor/dispatch

agent-dispatch is a small tmux-based dispatcher for running AI agent tasks in the background.

Shell 1 AI 70
metyatech/symphony-metyatech

TypeScript implementation of the OpenAI Symphony service specification: a long-lived CLI service that polls Linear, creates one workspace per issue, and launches a Codex app-server worker.

TypeScript 1 AI 60 Solo 2 sig live ↗
zauberzeug/game-of-cards

Agile for age of agents — turn work into durable, inspectable cards that humans and LLMs can collaborate on.

Python 1 AI 45 2 sig live ↗
DeanThompson/agent-skills

Portable Agent Skills for coding agents: Git workflows, linked worktrees, GitLab MRs, Cloudflare DNS, and agent context files.

Python 0 AI 100 Solo 1 sig live ↗
Taz33m/codex-demo-day-arena

Product-foundry control plane for AI coding agents: validator gates, buyer scoring, compute allocation, and Demo Day-style investment decisions across startup product candidates. Next step would be in automating outreach to get real PMF validation and iterate from there.

Python 0 AI 100
yucx-go/agent-knowledge

AI agent knowledge & long-term memory · MCP server, knowledge graph, BM25 + RRF retrieval · drop-in for Claude Code/ Openclaw/ Cursor / Codex / Hermes

Python 0 AI 100 Solo 1 sig live ↗
izhiwen/aiplus

Rust-first AiPlus CLI for project-local AI-agent workflow kits

Rust 0 AI 100
Mearman/agent-permissions

Cross-agent permission policy schema, evaluator, codecs, and CLI — one .agents/permissions.json for every coding agent

TypeScript 0 AI 100 2 sig
wxkingstar/ai-output-runtime

Schema-validated JSON blocks for AI-generated reports — Markdown source, safe runtime, zero AI-generated HTML/CSS/JS. Works with Claude Code, Codex, any agent.

JavaScript 0 AI 100 Solo 1 sig live ↗
ai-os-dot-net/AI-Native-Linux

AI-native Linux cognitive shell with typed actions, policy kernel, semantic runtime, and unified KDE/Web UX.

Astro 0 AI 100 1 sig live ↗
szpack/ai-task-flow

AI 任务流转台: turn rough ideas into structured AI coding tasks, generate Codex or Claude prompts, and backfill execution results.

JavaScript 0 AI 100 Solo live ↗
xuio/claude-code-codex-subagents

Claude Code plugin for launching OpenAI Codex subagents via a daemonless MCP server

TypeScript 0 AI 90 Solo live ↗
cskwork/symphony-multi-agent

Multi-agent fork of OpenAI Symphony — drives Codex, Claude Code, Gemini, and Pi CLIs from one orchestrator with a Jira-style CLI Kanban TUI

Python 0 AI 90 1 sig
Superordinate-complacence439/awesome-codex-pets

Browse and install over 174 animated pets for the OpenAI Codex CLI using this community-curated collection.

0 AI 90
xiangyugongzuoliu/openai-codex-tutorial

OpenAI Codex 中文教程:CLI、IDE、App、Cloud 怎么选、怎么配、怎么用进真实项目。Chinese tutorial for OpenAI Codex.

0 AI 90 Solo live ↗
Barrierml/tako-cli-oss

Unified launcher and agent session manager for Claude Code, Codex, Gemini — with external-LLM-driven approval gating

TypeScript 0 AI 70 Solo live ↗
uesugitorachiyo/ao-operator

Local autonomous agent CLI for turning Codex and Claude Code subscriptions into repeatable agent teams. Start here.

Python 0 AI 70 2 sig
aihxp/ready-suite

Ten composable AI skills covering the full arc from idea to launch. Discovery hub for prd-ready, architecture-ready, roadmap-ready, stack-ready, repo-ready, production-ready, deploy-ready, observe-ready, launch-ready, harden-ready. Plug into Claude Code, Codex, Cursor, Windsurf.

Shell 0 AI 70
dyed-eye/texpop

LaTeX parser and popup renderer for Claude Code & Codex CLI - press a hotkey, see your AI's math beautifully rendered over the terminal. KaTeX, focused-chat detection, DPI-correct, no VS Code required.

PowerShell 0 AI 70
L1f4Is6o0d2Yuu/tokenusage

Local-first token usage dashboard for AI coding tools (Claude Code, Codex, DeepSeek, ...). Reads your gateway/CLI logs, never phones home.

TypeScript 0 AI 70 2 sig
mobetter20/lemon

Crowd-sourced sentiment barometer for Claude and Codex — weekly complaint rate from public discourse.

Python 0 AI 70 Solo live ↗
ppwnr88/noyap

Less yap, more code. Multilingual AI communication rules for coding agents.

TypeScript 0 AI 70
quiescencycommonrush642/goal-prompt-builder

Build precise goal prompts for Claude CLI agents using a five-section template to ensure audit-friendly execution and efficient token usage.

0 AI 70
raydenai/queen-protocol

Queen Protocol v2.12.0 — Automated enforcement daemon (colony-watcher.sh runs every 10 min via launchd, auto-normalizes failing reports + seals stale state) + 6 operator-discipline patterns from Elev-W1 22-shard colony. 22/22 reached CONVERGE_AUDIT_PASS this session. Workers: claude/kimi/codex/gemma4-local.

Python 0 AI 70 Solo live ↗
q1zhen/nightshift

Nightshift is an overnight AI agent harness that fixes bugs, manages TODOs, and implements features across your projects while you sleep, with a morning digest waiting when you wake up.

Python 0 AI 70 1 sig
lucasvtiradentes/pretty-session

✨ pretty-print claude, codex, and gemini session streams

TypeScript 0 AI 70 Solo 1 sig live ↗

RELATED Other topics · full topics ranking →

#claude-code

122

#ai-agents

73

#claude

73

#mcp

71

#llm

67

#python

56

#developer-tools

49

#ai

45

#anthropic

42

Aggregated by case-insensitive match against topics_json of each repo's latest content snapshot. methodology