Codex: open-source projects on GitHub
849 repositories on Codex, picked by the REDDYX AI agent. Each has a summary, key features and a breakdown. Sorted by stars.
// RELATED TOPICS
RESEARCH-UNITS-PIPELINE-SKILLS - SMART PIPELINES FOR RESEARCH
The project proposes treating skills as executable units with declared inputs/outputs, acceptance criteria, and guardrails, providing an evidence‑based approach to resear
★ 519 · PythonLEARN WITH AI AGENT
A recursive learning system with Socratic dialogues and TDD-style exercises right in your code assistant.
★ 519 · TypeScriptSYRTIS: MONITOR AI TOKENS
Tracks token usage and quota of 25+ local AI agents in the macOS menu bar. Native Swift with Liquid Glass and a 3D contribution graph shows usage of Claude Code, Codex, C
★ 518 · SwiftUNITING AI AGENTS IN THE TERMINAL
Runner unites Claude Code, Codex, GitHub Copilot CLI and pi in one terminal, giving each agent its own TUI while working on a shared task. Written in Rust, the project ha
★ 518 · RustTRADING DESK FOR AI AGENTS
Hyperliquid trading desk with 7 roles and 17 skills for AI agents. Keyless market research, execution via your API wallet and approved tickets. Supports Grok Bot, Claude
★ 518 · PythonIdea Analysis in 10 Minutes
AI agents turn your startup idea into a full validation and go‑to‑market plan in just 10 minutes. They run on Claude Code, OpenAI Codex, and Cursor.
★ 517DOTNET-SKILLS: AI SKILLS IN ONE
Installing and using .NET skills for AI assistants: Codex, Claude, Copilot and Gemini.
★ 516 · C#OPERATOR-MEMORY SELF-LEARNING ENGINE
operator-memory is a context engine for AI agents that self‑improves its knowledge from code and dialogs. It stores, searches and updates the agent's memory in real time,
★ 514 · TypeScriptWHITEBOARD WITH MCP FOR RESEARCH AI AGENTS
Local whiteboard and MCP server where every agent claim traces back to the code and run that produced it. A deterministic engine tracks evidence chains and flags stale cl
★ 512 · JavaScriptLOCAL LATEX EDITOR WITH AI AGENTS
Lattice — macOS app for LaTeX with live PDF preview, annotations, and Overleaf sync. Works locally, integrates AI agents to assist in writing papers.
★ 511 · TypeScriptAI LAWYER FOR CONTRACTS
AI skill for contract review: CUAD risks, benchmarks, and ready redlines for lawyers. Works with Claude Code, Codex, Cursor, and 26+ tools.
★ 508DANUS: Agents of Mathematics and Reasoning
The project combines reasoning agents with a fact‑graph memory to solve complex mathematical problems.
★ 507 · PythonPROJECTATLAS REDUCES TOKENS IN CODE
ProjectAtlas guides AI agents through code using metadata and a dependency graph, saving over 90% of tokens.
★ 507 · RustAGENT-KANBAN FOR AI TEAM
Kanban board for managing AI agents. Mission control of your artificial intelligence workforce.
★ 506 · TypeScriptMEMORIX MEMORY FOR AI AGENTS
Cross-agent memory layer for coding agents via MCP. Compatible with Cursor, Claude Code, Codex, and others.
★ 505 · TypeScriptNADIRCLAW: LLM Routing for Savings
Routes queries to cheap local models and premium LLMs, saving 40‑70% on API costs.
★ 504 · PythonBENCIUM MARKETPLACE: SKILLS
A platform for sharing and using skills built according to the Anthropic Skills guide. It speeds up AI‑agent development with ready‑made modules.
★ 499AI CODE REVIEW WITH 4 PROBES
Skill for Claude Code and Codex audits code with four independent probes. Each finding is backed by evidence, and merge decisions use JSON reports. 397 stars on GitHub.
★ 499 · PythonCAD SYSTEM WITH AGENTS FOR CADQUERY
Desktop app for creating parametric 3D models via CadQuery code. An AI agent writes Python code, SOMA builds the model and shows the result in a 3D viewer.
★ 490 · TypeScriptCLAW ORCHESTRATOR UNIFIED AGENT
Run Claude Code, Codex, Gemini and other CLIs in a unified environment with OpenClaw plugin support.
★ 489 · TypeScriptVisual Build Agent Skill
An agent skill that iteratively builds visual outputs to match reference images or videos within a quality threshold and time limit.
★ 489 · JavaScriptAUTOMATING SCIENTIFIC PAPERS IN LATEX
An agentic framework for creating arXiv-ready ML/AI papers with automatic citation checking and a controlled LaTeX workflow.
★ 487 · TeXPR-COCKPIT: LOCAL AI REVIEWER FOR PR
Local AI reviewer powered by Claude and Codex. Reviews code in isolated worktrees, GitHub comments appear only after your approval.
★ 486 · TypeScriptSKILL.COLOR-EXPERT — COLOR EXPERT FOR CODE
AI agent with deep knowledge of color spaces, accessibility (APCA, WCAG), palette generation, pigment mixing, and the history of color theory.
★ 485Drissionpage-MCP-Server - Browser Automation for Clients
The DrissionPage MCP server provides browser automation for Claude Code, Codex, and other MCP clients. It allows controlling web pages from Python.
★ 481 · PythonKUBESHARK DEFEATS HALLUCINATIONS
This skill for Claude Code and Codex eliminates LLM hallucinations when working with Kubernetes and Helm. LLMs no longer lie — only official best practices.
★ 480USE CHATGPT SUBSCRIPTION IN DSH
Connect your ChatGPT Plus/Pro subscription to the DeepSeek Harness to access the GPT‑6 and Codex models,image generation, web search, and quota without a separate OpenAI
★ 478 · JavaScriptPUPPETMASTER - AGENT SWARM MANAGEMENT
Puppetmaster provides a management plan for resilient agent swarms: subprocesses, leases, artifacts, and deterministic state stitching.
★ 475 · PythonAI-COLLAB-PLAYBOOK - Practical Guide
Practical playbook for collaborative AI work: research, writing, reading, and coding with prompts and agent rules.
★ 474 · PythonHUD FOR 25+ CODING AGENTS
agent-hud-open shows quotas, tokens and sessions for Claude Code, Codex and 25+ agents in one view. Answer requests and jump back to coding in one click. Works on Mac, Wi
★ 473 · RustChorus: Multi-LLM code review
Chorus organizes collaborative code review with 2–4 LLMs before deployment. Use your CLI and Chorus will bring in other models for checking.
★ 469 · TypeScriptTHREAT MODELING FOR AI AGENTS
grim-prompter points Claude Code, Codex, or any agent at your repo and delivers an evidence-traced threat model. Covers 36 architectures and 29 methods (LINDDUN, STRIDE).
★ 469RYUGI: ARTIFACTS FOR AI AGENTS
Ryugi provides artifacts for coding agents: mockup artboards, design docs, whiteboards, HTML benches, and verify reports. Comments on artifacts are sent back to the agent
★ 467 · JavaScriptAVIBE - Your Local AI Agent
Avibe is a local OS for AI agents that lets you run Claude Code, Codex, and OpenCode directly in your browser or any chat app.
★ 466 · PythonKEY MANAGER FOR PROMPT PROFILES
Keysmith-switch unifies management of Keysmith prompt and instruction profiles in a single desktop app. Switch profiles instantly, sync updates, and export/import setting
★ 465 · RustHIROUTE — SMART AI MODEL ROUTER
Local router routes routine tasks to cheap models, complex ones to powerful. Reduces Codex and Claude Code subscription costs while preserving quality. Written in Rust.
★ 465 · RustSwarmVault: Local Wiki for LLM
Open tool for building knowledge graphs, RAG database, and agent memory. An Obsidian alternative for personal knowledge management and AI second brain.
★ 463 · TypeScriptAI-NATIVE JAVA
plinth is an open-source workflow for modernizing the Java SDLC with reusable Skills, Agents, and MCP servers.
★ 462 · JavaCUT AI COSTS
Index your code in code-context-engine and save up to 94% AI tokens when working with Claude, Codex, and other assistants.
★ 461 · PythonUI-CRAFT: Perfect AI Agent UI
A system for creating high-quality UI using AI agents. Installs as a ready‑made skill for your coding agents.
★ 459 · GoLAUNCH AI AGENTS IN OBSIDIAN
The plugin lets you run Claude Code, Codex and other CLI agents directly inside Obsidian notes. You get an interactive terminal with AI support without leaving your works
★ 459 · JavaScriptOPENTEAMS - AI TEAM FOR CODE
openteams lets you create, plan, and deliver code using a team of AI agents instead of a single developer.
★ 455 · TypeScriptMOBILE HARNESS: PHONE MANAGEMENT
Library for managing Android, iOS, and cloud phones through scripts and API. Simplifies test automation and CI/CD.
★ 453186 SHADERS FOR AI AGENTS
Library of 186 GLSL functions for Claude Code, Codex, Cursor, Copilot and Gemini CLI. Includes SDF raymarching, procedural terrain, water, clouds and generative art. Come
★ 452 · GLSLNIGHTSHIFT: AUTONOMOUS CODING SHIFTS
Nightshift runs long autonomous sessions for Cursor, Codex, and Claude Code. Persists state, recovers from crashes, and gives a clean report: done, in progress, parked, o
★ 451 · ShellSMITHERS - KEEP CODE UNDER CONTROL
Smithers ensures reliable execution of agent code: it survives failures, waits for human confirmation, and rolls back errors. It supports Claude Code, Codex, Gemini, and
★ 449 · JavaScriptSIMVYN: MANAGE ALL DEVICES
simvyn — a universal devtool for iOS, Android, and real devices: control them via a unified panel and CLI.
★ 446 · TypeScriptHARNESS-REMOTE: AGENT MANAGEMENT
Application for remote management of coding‑agent harnesses: OpenCode, PI, Oh My Pi, Claude Code and Codex CLI from phone or PC.
★ 445 · TypeScriptMETIS: BOOSTING AI/LLM CODING EFFICIENCY
Metis is a TypeScript agent that boosts AI/LLM coding performance by 50%. It has already garnered 297 stars on GitHub and offers ready‑to‑use skills for automating testin
★ 443 · TypeScriptCCLOAD: AI Gateway No Switch
AI gateway with smart routing, auto-failover, and real-time request monitoring.
★ 440 · GoFILE-BACKED HARNESS FOR AI AGENTS
repo-harness is a file-backed harness for reliable Claude Code and Codex sessions. Saves context to files, restores state after crashes, and manages agentic-workflows via
★ 436 · TypeScriptDEVCODEX UNIFIED AI CODING
DevCodex — runtime for intent‑driven AI coding: unified context, skills, approvals, validation and handoffs between six AI hosts. Written in JavaScript, works with Claude
★ 434 · JavaScriptPRYSAI PLAYBOOK: COMPLETE LLM GUIDE
LLM playbook on practice: 8 locales, unified core, Codex track and adapters for ChatGPT, Claude Code, Gemini, DeepSeek, Grok.
★ 433 · PythonMCPTOON: SAVES 99% OF MCP TOKENS
Standard MCP discovery burns 71,929 tokens. mcptoon drops it to 581 — 99.2% savings. Zero dependencies.
★ 431 · HTMLMODELS - AI MODEL BROWSER
TUI and CLI for browsing AI models, benchmarks, and providers directly from the terminal in Rust.
★ 430 · RustAI AGENTS PARALLEL CODE
Workspace for AI agents. Specialists plan tasks, and Claude Code, Codex and Cursor work in parallel — locally or in the cloud.
★ 430 · JavaScriptContext Layer for AI Agents
Ktx is an executable context layer that lets Claude Code, Codex, and any AI agent precisely query data via MCP using the agent's skills and memory.
★ 427 · TypeScriptBACKTEST STOCKS WITH CLAUDE CODE
Official FinLab skill for backtesting Taiwan and U.S. stocks. Run strategies via Claude Code or Codex on real market data. 420 stars on GitHub.
★ 427 · PythonOPENSOURCE MEMORY FOR AI AGENTS
ownmem — open-source, Git memory for AI coding agents. Provides local recall for Claude Code, Codex, Cursor, Gemini CLI and compatible tools. Indexes the repository and s
★ 426 · JavaScriptCODEx-PPT-SKILL: AI Generates Presentations
Codex skill for creating PowerPoint presentations based on images using gpt-image-2. 424 stars on GitHub.
★ 424 · PythonNew projects on this topic in Telegram
Telegram →