SaaSHub helps you find the best software and product alternatives Learn more →
Top 23 Python codex Projects
-
ui-ux-pro-max-skill
An AI SKILL that provide design intelligence for building professional UI/UX multiple platforms
UI/UX Pro Max is a skill that gives your agent actual design taste. 60,000+ stars. 50+ distinct UI styles, 97 colour palettes, 57 font pairings, 25 chart types, and design system generation. Install it and your agent stops defaulting to the same generic SaaS template.
-
SaaSHub
SaaSHub - Software Alternatives and Reviews. SaaSHub helps you find the best software and product alternatives
-
serena
A powerful MCP toolkit for coding, providing semantic retrieval and editing capabilities - the IDE for your agent
You should add Serena https://github.com/oraios/serena to your list.
Serena gives you symbol-level navigation, reading, and editing via tree-sitter. So you're already getting much of what CoderLM offers — plus Serena has editing capabilities(replace symbol body, insert before/after symbol, rename). GitNexus goes further with the graph/impact analysis layer on top.
I personally use Serena and GitNexus.
The case for using both
- GitNexus tells you what to change (impact analysis, dependency maps, blast radius) -
CodeGen
CodeGen is a family of open-source model for program synthesis. Trained on TPU-v4. Competitive with OpenAI Codex.
-
awesome-ChatGPT-repositories
A curated list of resources dedicated to open source GitHub repositories related to ChatGPT, OpenAI API, and Codex. Searchable via Claude Code skills.
-
claude_codex_bridge
Visible multi-agent CLI teams for Claude, Codex, Gemini, OpenCode, and Droid with project memory and tmux supervision
https://github.com/fengshao1227/ccg-workflow
This one also seems promising, but I haven't tried it yet.
https://github.com/bfly123/claude_code_bridge
All of them are made by Chinese dev. I know some people are hesitant when they see Chinese products, so I'll address that first. But I have tried all of them, and they have all been great.
-
llm-wiki-agent
A personal knowledge base that builds and maintains itself. Drop in sources — Claude (or Codex/Gemini) reads them, extracts knowledge, and maintains a persistent interlinked wiki. Works with Claude Code, Codex, OpenCode, Gemini CLI. No API key needed.
Project mention: Show HN: Claude Soul – cross-session learning engine for Claude Code | news.ycombinator.com | 2026-05-18I'm really interested in trying this out. Currently, I'm using the standard Obsidian MD format for long-term memory (https://github.com/SamurAIGPT/llm-wiki-agent) and asking the agent to access the wiki at the start of the task and then record useful information at the end
-
-
-
graphify
AI coding assistant skill (Claude Code, Codex, OpenCode, OpenClaw). Turn any folder of code, docs, papers, or images into a queryable knowledge graph
Project mention: We Fixed Karpathy’s LLM Wiki - PENgram Is the Typed Knowledge Graph Pipeline Everyone Asked For | dev.to | 2026-04-28Before we built anything, we studied what already existed. Graphify by Safi Shamsi is an open-source codebase-to-knowledge-graph tool that does many things well. Its three-pass architecture is clean and smart:
-
-
I found banteg/takopi in late December 2025. It's a Telegram notifier for AI coding agents, and at first it was an absolute godsend. I could hook up voice-to-text transcription via Telegram, record a voice note, and it would send the task to Claude Code. Brilliant.
-
get-physics-done
The first open-source agentic AI physicist, by Physical Superintelligence PBC (PSI).
-
Project mention: Show HN: Open-Source GTM Skills for Claude Code, Codex, and Cursor | news.ycombinator.com | 2026-03-12
-
-
avibe
The local-first Agent OS — your AI partner lives on your own machine. Drive the official Claude Code, Codex & OpenCode from your browser or any chat app.
Project mention: Show HN: Avibe – your AI agent lives on your machine, reachable from your phone | news.ycombinator.com | 2026-06-07 -
codex-readme
Revolutionize your project documentation with the Codex-README generator, utilizing OpenAI's Codex for intelligent README creation.
-
evo
A plugin for Claude Code and Codex that turns your codebase into an autoresearch loop — discovers what to measure, instruments the benchmark, then runs tree search with parallel subagents.
Project mention: a claude code/codex plugin to run autoresearch on your repository | dev.to | 2026-04-17 -
vim_codex
Supercharge your Vim editor with AI-powered code completion using OpenAI Codex. Boost productivity and save time with intelligent suggestions.
-
ResearcherSkill
One file. Your AI coding agent becomes a scientist. 30+ experiments while you sleep.
Project mention: Show HN: A Markdown file that turns your AI agent into an autonomous researcher | news.ycombinator.com | 2026-03-22 -
agent-skills
Official Qt AI engineering skills for Claude Code, Codex, Copilot, Gemini,and other AI coding tools (by TheQtCompanyRnD)
I disagree. Not all skills are useless. For example, I sometime use Qt for GUI projects and I have found their skills [0] very useful to improve the quality and performance of my projects. I their absence, I would each time have to direct the agents to find the docs or specific tools, wasting tokens and thus decreasing the quality of the output.
[0] https://github.com/TheQtCompanyRnD/agent-skills
-
kicad-happy
AI coding agent skills for KiCad electronics design. Works with Claude Code and OpenAI Codex. Analyze schematics, review PCB layouts, EMC pre-compliance, SPICE simulation, download datasheets, source components, and prep boards for fabrication.
Project mention: Show HN: Spice simulation → oscilloscope → verification with Claude Code | news.ycombinator.com | 2026-04-16Hit this exact wall six months back building Claude Code stuff for KiCad review[1]. First pass let Claude read .kicad_sch directly via grep/read. It happily invented pin numbers that didn't exist. Rewrote it with Python analyzers that spit out JSON, now Claude just reads the JSON, problem mostly went away.
Curious how spicelib-mcp handles models that aren't in the bundled library. Do you pass the .lib path as a tool arg, or does the server own a registry?
[1] https://github.com/aklofas/kicad-happy
-
-
DocMason
DocMason is a repo-native agent that turns your complex office files into a local LLM knowledge base and your second brain. The repo is the app. Codex is the runtime.
Python codex discussion
Python codex related posts
-
Show HN: Mnemo – local-first AI memory layer for any LLM (Rust, SQLite,petgraph)
-
google-analytics-mcp VS onequery - a user suggested alternative
2 projects | 1 Jun 2026 -
mcp2cli VS onequery - a user suggested alternative
2 projects | 1 Jun 2026 -
I built an open protocol to make AI coding agents follow senior-engineering workflows
-
I built a coding agent that runs on Gemma 4 — here's what 2B parameters can actually do
-
I shipped cc-audit as a GitHub Action. Now your CLAUDE.md gets linted on every PR.
-
How I cut my multi-turn LLM API costs by 90% (O(N ) O(N))
-
A note from our sponsor - SaaSHub
www.saashub.com | 9 Jun 2026
Index
What are some of the best open-source codex projects in Python? This list will help you:
| # | Project | Stars |
|---|---|---|
| 1 | ui-ux-pro-max-skill | 87,871 |
| 2 | serena | 24,975 |
| 3 | CodeGen | 5,174 |
| 4 | awesome-ChatGPT-repositories | 3,067 |
| 5 | claude_codex_bridge | 2,899 |
| 6 | llm-wiki-agent | 2,858 |
| 7 | sketch | 2,282 |
| 8 | zsh_codex | 1,715 |
| 9 | graphify | 1,469 |
| 10 | aws-agent-skills | 1,112 |
| 11 | takopi | 1,004 |
| 12 | get-physics-done | 816 |
| 13 | goose-skills | 722 |
| 14 | codex_py2cpp | 505 |
| 15 | avibe | 456 |
| 16 | codex-readme | 402 |
| 17 | evo | 359 |
| 18 | vim_codex | 289 |
| 19 | ResearcherSkill | 230 |
| 20 | agent-skills | 214 |
| 21 | kicad-happy | 181 |
| 22 | ida-headless-mcp | 130 |
| 23 | DocMason | 127 |