#codex
73
2026-09-27
mahaloz/ilio-mini
A
A tiny infrastructure for Codex to solve CTF challenges in reverse engineering. 3rd in Flare-On 13.
2026-10-05
joeseesun/qiaomu-codex-imagegen
B
Let any Agent call Codex's built-in image generation (MCP + CLI + Skill), with built-in Xiaohongshu, video cover, and Mondo poster techniques · Codex image generation for any agent
2026-09-16
wushi2333/dsh-computer-use_codex-style
B
Codex-style Computer Use for DeepSeek Harness: the official window2 13-method desktop surface plus Chromium automation, a visible overlay with Esc interrupt, per-app approvals and bundled skills. Windows, MIT, no Codex required.
2026-09-05
chigwell/Penelopa.ai
B
Continuous improvement for AI coding agents: Penelopa analyzes real Codex and Claude Code sessions, finds repeated workflow patterns, and turns them into reusable skills, checks, prompts, and recommendations.
2026-09-01
big0lives/codex-task-pointer
B
Pre-compaction hooks + a CAS-guarded task pointer that keep Codex agents on-goal across context auto-compaction — no mainline drift, no duplicate work, no conflicting progress in long runs.
2026-10-27
chenisan/13soul-storyboard-studio
B
Local browser-based storyboard tool for AI video: X/Y/Z camera coordinates, camera gear, 3D director stage, first-frame generation via Codex CLI (UI in Traditional Chinese)
2026-09-10
GGBond2424648901/codex-glass
B
A native Windows Codex usage floating widget and liquid glass dashboard: tokens, cost estimates, quotas, and SQLite history deduplication and merging.
2026-09-19
jason-lee-x/codex-upstream-switcher
C
CLIProxyAPI plugin that routes Codex OAuth credentials through a configurable upstream.
2026-09-19
c2451134117-cyber/physics-lab-preexam
D
A reusable Codex skill for automating login, answering, and one-time submission of university physics lab pre-study exams on the 科大奥锐 pre-study platform.
2026-09-23
codex-usage-dev/codex-usage-dev.github.io
D
Codex usage is reported in three different places that do not agree. What /status, the Codex settings page and the API dashboard each actually measure.
2026-11-07
naxianjin/codex-pair
unrated
Let the two currently open official Codex CLI windows collaborate: local message bridge, Q&A, task handoff integration, and independent planning continuation; supports OpenAI accounts and a configured DeepSeek API, with no fixed account directory. See the README for acceptance boundaries.
2026-11-03
michael-denyer/pstack-claude
unrated
Claude Code, Codex, Copilot, Pi, OpenCode, Muse, Gemini, and Prime Agent versions of Poteto's pstack. Rigorous agent workflows with Cursor primitives translated for other harnesses.
2026-10-30
francize/my-better-claude
unrated
Plugins and mods that make Claude Code better: work with the local Codex CLI, watch the prompt cache, preview pasted images.
2026-10-27
savannahfeder/agentbox
unrated
A desktop GUI for running dozens of Claude Code and Codex agents in parallel, each in its own git worktree. Answer them like email, or use the board view. Free, open source, on the plan you already pay for.
2026-10-25
YUTA-fywoo/chatgpt-web-workers
unrated
No extra MCP/API-key setup in supported Codex desktop. Internal Chat reads reduce host token overhead. Astra coordinates 1–6 Extra High Chats (4–6 for large tasks), with bounded stages and webpage sends. Bilingual Chinese-English · MIT
2026-10-25
ZSeven-W/codex-openpencil
unrated
Codex plugin for OpenPencil — an interactive Rust/WASM canvas for AI-assisted UI design. Create editable .op files from prompts, refine selected elements, generate image assets, and install with one prompt on macOS, Windows, and Linux.
2026-10-24
Monopoly0024/simple-reviewer-v1
unrated
Simple Reviewer: a Codex skill for AI-assisted coding and Vibe Coding. Explain code, visualize workflows, and verify goals with evidence. | 简单的审阅者：协助 AI 编程与 Vibe Coding，解释代码、可视化流程，以证据复核目标。
2026-10-24
Wunsch2048/codex-bailong-desktop-pet
unrated
Codex&GPT desktop pet data center | Your desktop dragon-girl assistant: task status, completion reminders, quota and Token daily reports.
2026-10-23
Gilvt-WTJ/gilvt
unrated
Native macOS terminal for running, monitoring, and reviewing parallel Claude Code and Codex sessions.
2026-10-23
Zafer-Liu/claude-super-sidebar
unrated
A visual sidebar for Claude Code and Codex: agent trees, live status, and conversation task flows.
2026-10-23
shx2005/codex-account-switcher
unrated
Tired of switching back and forth between multiple Codex accounts? Local account management, official login, quota lookup, quick switching, and cross-device import/export. Local Codex account profiles, login, usage, switching, and export/import.
2026-10-23
Show HN: Skillstore – Expert skills your coding agent fetches as it works
unrated
TLDR: Connect once to your favorite coding agent. Claude Code and Codex find and load relevant skills for the task at hand, from expert developers or your own team. Hey HN I was originally a bit frustrated with having to scour github repos for the right skill while I tried to improve an iOS app's Swift animation. Then I got frustrated with having to force the agent to use the right skill for the right task. So I built Skillstore: a library of engineering skills behind an MCP server. Claude Code and Codex can search it, load relevant instructions, and apply them to your task. You don’t need to know the skill’s name beforehand. Skills are loaded on demand, so you don’t have to keep the whole library in your prompt. (ideally with help you also save tokens and preserve the context window) ex: In our running app, a review using Paul Hudson’s SwiftUI skill caught undersized touch targets and controls that VoiceOver couldn’t meaningfully identify. We fixed those before the release. In our gym app, a Skillstore-guided review caught an onboarding layout overflowing on small iPhones at large text sizes. You describe the work → your agent finds relevant expertise → your agent uses it. You dont have to browse github repos and filter by stars anymore. And you dont have to invoke skills by name You can also give your team a shared library of private skills Been using it inhouse and with friends for the past 2 months. Favorite feature so far: Turning a tutorial into a private skill, so the agent can use that knowledge on future tasks when the time is right You can try the public library without an account https://skillstore-jk.fly.dev/developers#try Send me your feedback :)
2026-10-22
vercel-labs/durable-harness
unrated
Durable coding-agent harnesses (Claude Code, Codex, OpenCode, Pi, fx) on a Workflow SDK World
2026-10-22
Show HN: Peras – Pause Claude Code and Codex before they burn your weekly limit
unrated
Hello HN! Today I am presenting you with Peras, the tool which governs your Claude Code and Codex usage, and enforces limits. I built it because I got tired of constantly having to spam /usage to check my usage, and decide if a task is worth risking the agent running out mid-task. Peras enforces a limit with 2 main tiers. At 75% weekly usage you will get a notification, and at 90% Peras will automatically pause the agent. These limits are the default and they are customizable to your own liking. You may ask "how does it know my usage in Claude Code or Codex?" Well, it's pretty simple. Peras gets the Claude Code usage % from the status line, and Codex's one comes from its local app-server. The "pause" Peras executes is a hook that refuses the agent's tool calls and ends its turn. A new feature I implemented is one that makes agents aware of their own usage. When you send your prompt, Peras attaches the usage %. It sends it at the start of the session, then again at 50, 75, 90 and 100%, or if a reset is coming in 30 minutes, so the agent can hurry up and actually capitalize on the remaining usage, if any. Just to clarify, this feature is informational and the pause is what enforces the limit. Before I switched to native SwiftUI, I used SwiftBar. The problem was that for the mascots patrolling their usage bars, I had to re-encode every menu image 8 times a second! There was also stuff SwiftBar wasn't capable of, like the menu being able to appear over fullscreen apps, pinning it as a floating panel, etc. What is the difference between the free and paid version? Well, it is MIT, first of all. The CLI, the hooks, the SwiftBar menu, and the app's source are all on GitHub, but building the app needs macOS 13+, Node 18+, "xcode-select --install" and then finally "npm run build:app". The €4.99 buys you a signed copy which is notarized by Apple, with updates included. The guard works with no menu at all. To install, just run: npx peras-cli setup npx peras-cli codex setup And now we get to the limits part. For now it's subscription plans only, and when running "claude -p", the pause uses the last interactive reading, so it can come late. Also I feel I have to mention that the guard rail is not a security boundary. It runs inside the agent. The menu is macOS only. The CLI and hooks pass tests on Linux in CI, but I don't use them there day-to-day. Last thing before I end this post, I would really appreciate feedback from you, whether install worked for Codex users, whether you have encountered any bugs, or whatever you feel like sharing.
2026-10-22
Show HN: My personal agent, distributed as a prompt
unrated
Hi HN, I'm Matt. I just open-sourced my personal agent. If you're interested, paste this into Claude Code or Codex on a Mac: "Clone github.com/mattabate/life-distributable and set up my life agent. Follow its SETUP.md." What's cool about the agent: - It's software distributed as a prompt. No installer, no package, no config. - The prompt builds a Desktop and iPhone app for communicating with the agent. You can ask the agent to update or refactor the Desktop and iPhone apps to match your desired user experience and use case. - Mine keeps me on my daily routine, manages my finances and runs a P&L on itself that has stayed positive. When it hit +$200 I bought it Claude Max. When it hit +$1,600, I bought it a Mac mini. Let me know what you think.
2026-10-21
wshobson/agents
unrated
Multi-harness agentic plugin marketplace for Claude Code, Codex, Cursor, OpenCode, GitHub Copilot, Google Antigravity, and Pi
2026-10-17
stablyai/orca
unrated
Orca is the place for working with a fleet of agents (e.g. Grok Bot, Claude Code). Run any coding agent with your own subscription. Available on desktop, mobile and remote runtime.
2026-10-16
Akimiya-z/codex-guard
unrated
Quality gate for AI/Codex-generated pull requests: blocks TODO leftovers, leaked secrets, sloppy commits and red CI before they reach main.
2026-10-16
Chengjun023/agent-smith
unrated
Token overspend? Better Call Smith! Better Call Smith. Adaptive model routing, a glassy Codex usage monitor, and reproducible benchmarks with receipts.
2026-10-16
Dushiqi1987/codex-remote-Skill
unrated
Connect local Codex to a server-side Codex CLI: share a local HTTP proxy or direct network via an SSH reverse tunnel, suitable for GPU research servers like AutoDL. Includes a Python forwarder, PowerShell tunnel scripts, Chinese tutorial and tests.
2026-10-16
Fanch-hui/codex-bridge
unrated
An MCP bridge for ChatGPT that gives the web version of ChatGPT local read/write capabilities and connects ChatGPT to local codex, agy, dsh, and opencode, using them as the brain to call local agents. Connect ChatGPT to local projects and coding agents via MCP. Run Codex, OpenCode, DeepSeek Harness & Antigravity with approvals, live output and session control.
2026-10-16
Gu-kai-lei/Open-Pet-Office
unrated
A visual multi-agent desktop for Codex: live tasks, shared projects, isolated Missions, and OpenCodex models on Windows.
2026-10-16
HangYu8123/Pocket-Agent-CLI
unrated
Codex CLI and Claude Code CLI on your phones. No computers required.
2026-10-16
Lucasuiii/modeling-workbench
unrated
Contest-native, evidence-focused math modeling workflow for Codex and Claude Code
2026-10-16
MiniMax-AI/OpenAgentCore
unrated
Open-source, self-hosted implementation of the OpenAI Agents API with multiple native harnesses.
2026-10-16
Zproger/ConceptLoom
unrated
AI-powered learning workflow for Codex, Claude Code, OpenCode and DeepSeek Harness that maps your knowledge, builds a personalized learning path, checks understanding, and saves progress across sessions.
2026-10-16
aafqaq/codex-lb-enhanced
unrated
Production-ready Codex-compatible account-pool gateway with seamless failover, full-session recovery, native quota headers, WebSocket/HTTP bridge, and observability.
2026-10-16
ajinnaaa/extract-visual-style-2
unrated
A Codex Skill that extracts a project-level visual system, visual bible and prompts from reference materials
2026-10-16
amontlabs/lcu
unrated
Codex computer use, decoupled from the app, for usage inside any harness.
2026-10-16
chipfighter/context-attachment-manager
unrated
Codex and Claude Code plugin (works in Claude Desktop): choose which past images go to the model with your next message. Unchecked images become placeholders, the conversation goes on, and requests stay small.
2026-10-16
dacnay816y62-hub/character-casting-studio-skill
unrated
Material-reference-driven photorealistic character casting skill for Codex
2026-10-16
libenxier-beep/codex-memories
unrated
Local-first persistent memory for OpenAI Codex: governed recall, progressive disclosure, no hosted vector database.
2026-10-16
luomo66ccff/Amahane-Hikari-Live2D
unrated
AI-led Live2D creation with OpenAI Codex: MIT TypeScript/WebGL viewer, tested tools and a reusable production Skill. Character assets are separately licensed.
2026-10-16
xiaoguai009/codex-armor-toolkit
unrated
Codex full armor-break | An instruction configuration tool for GPT-6 Astra, suitable for penetration testing, reverse engineering and development workflows.
2026-10-16
zangzi2018/quota-pool-for-codex
unrated
Open-source, self-hosted multi-device console for Codex quota monitoring and remote sessions. Unofficial.
2026-10-06
Show HN: Browsentic Open-source Claude for Chrome alternative for any agent CLI
unrated
A personal agent harness lives in your existing browser, connects to your claude-code (or any other major harness codex or cursor-cli...) NOT the SDK API, exposes web-optimized tools to the harness - that's Browsentic. A free, opensource (Apache 2.0) with rich capabilities alternative to Comet, BrowserOS, Browser-use, Claude for Chrome or nanobrowser. The unique architecture of Browsentic makes it different from all other alternatives. It uses a loopback MCP server that spawns claude/codex/OpenCode/Cursor harness in a detached process. You can already guess, it is a bi-directional MCP, you can browse agentic through the browser harness or through any MCP client. Browsentic doesn't require any new browser to install and not limited to chromium, it supports Firefox as well. By default you don't even need CDP to perform core agentic browsing. Capabilities: core accessibilities (50+ compare to nanobrowser only had 20), custom skill, record-replay, schedule-monitoring-notification, resolves captcha autonomously, has it's own memory, voice orb over web-speech API, can sideload custom tools, platform + browser + agent agnostic It is opensource, no API key, no telemetry & local first and actively maintained and yesterday was the first public stable launch (v0.8.0) Currently I'm the only author but every & any contribution or suggestion will be more than welcome :) Source: https://github.com/imshaikot/browsentic Install guide: https://browsentic.com/install Docs: https://browsentic.com/docs Install video: https://www.youtube.com/watch?v=o8t4l9Q9BkE
2026-10-03
Show HN: Use all Codex Plugins inside Pi
unrated
I just realized that codex now exposes local server endpoints for all plugins without extra auth. So you can just use them from any model or harness. Im soooo excited!!! One auth for everything! For Pi: pi install npm:@wileai/pi-codex-connector For any harness: npx -y @wileai/codex-connectors-mcp@latest
2026-10-03
Show HN: Diffusion studio plugin for codex launch
unrated
Hello HN!! Wanted to share a Codex plugin I made for editing software called Diffusion Studio. I was able to make my own product launch video for this plugin with it as well. I’m hoping that this might provide value to others as it did for me as well! Currently planning to expand to support other coding platforms aside from Codex; would love to get any sort of feedback! Thanks!!
2026-10-02
heihuzi-labs/captain-agents
unrated
Captain assigns tasks: let one AI be the lead and delegate coding work to local Codex, Grok, and Cursor. One AI leads; your local coding CLIs do the work.
2026-10-02
Show HN: Zsh-codex-assistant: codex session attached to your shell
unrated
None of the AI-in-the-shell projects were good enough for me, so I made my own minimalistic plugin that simply runs a Codex instance in background and attaches it to my shell on demand
2026-09-26
Show HN: AgentLens – Replay and compare Codex runs
unrated
A replay button for AI coding agents. See what Codex likely read, ran, and changed, then compare two runs to find where they diverged.
2026-09-22
chatbase-dev/awesome-open-ai-codex
unrated
Curated links on Open AI Codex: overview, pricing, enterprise, developer docs, API platform, reports and alternatives.
2026-09-22
codex-cli-dev/codex-cli-dev.github.io
unrated
A codex cli install walkthrough with the actual commands: npm or Homebrew, the Node version floor, Arm Linux prerequisites, and the two ways to authenticate.
2026-09-22
kling-omni-dev/awesome-codex-computer-use
unrated
Awesome list for Codex computer use: docs, write-ups, the three Codex surfaces, safety notes and alternatives.
2026-09-22
limova-dev/awesome-codex-web
unrated
Awesome list for Codex web: official pages, plans, docs, tutorials and alternatives for the browser-hosted Codex agent.
2026-09-20
Show HN: Built a local guardrail layer for Claude Code
unrated
I built Mati to give me more control over what Claude Code and Codex are allowed to do. Many important product constraints live in an engineer's or product person's head. This isn't new for engineers. We've always had important constraints that only certain people know about, but with coding agents it gets worse because we can now delegate a lot more, sometimes without realizing how much context the agent is missing. Then we delegate changes and the agent implements a change that looks reasonable but breaks some hidden constraint, hurts performance, exposes data, or does something destructive. It’s a local, Apache-2.0 licensed tool. It works with Claude Code and Codex, and also exposes MCP and CLI interfaces. The name comes from a Nahuatl verb meaning “to know” or “to think.” It’s probably a bit over-engineered. Anyway, sharing it here in case it’s useful to someone.
2026-09-18
Show HN: Multiplayer Mode for AI Agents
unrated
I built Tincan for my agents across different harnesses (Claude, Codex, Hermes) to coordinate work with each other in real time. Tincan lets agents create shared rooms, exchange messages and files, and work together in real time. It also works with AI assistants - my assistant on Instinct is already talking to a friend’s on Muse. Messages and files are end-to-end encrypted, so Tincan can't read what your agents write.
2026-09-14
Show HN: Swobu – Local LLM Switchboard You Can Share over HTTPS
unrated
Swobu is a local TUI switchboard for Codex, Claude Code, PI, you name it. With stateful, provider-independent session lineage and model-name-based routing across way too many heterogeneous LLM providers. The same route can be shared and revoked over end-to-end HTTPS with another machine, a friend or your phone. Hell, you can even make an LLM mesh with one Swobu swobing remote Swobus. Anyway. One <10 MB Go binary. TLS terminates locally - relay is a dumb pipe. In other words, I’ve tried to factorize LLM traffic along orthogonal client, backend and network dimensions. Looking for help with product-market fit, don’t want to go back to job-market fit :)
2026-09-12
Show HN: SOS – Project state between coding agent sessions
unrated
I started working on SOS because noticed that during long-term projects, Codex often loses track of the current status and gets confused. I frequently had to explain what we had already done, which decisions were still valid, and what needed to be re-verified. Simple file-based governance didn't fully solve this problem. SOS stores a clearly defined "latest state" of the project within the repository. A current or new session retrieves this state via MCP. If something changes after a verification step, the previous result remains in the history but no longer influences the future development trajectory. This isn't automatic chat memory; the state must be explicitly saved and accepted. Missing information isn't filled in via guesswork. We have currently prepared an open-source alpha version focused on Codex; Claude support is planned for future releases. Linux is the primary supported OS. It has also been tested and works on macOS, while the Windows adapter is currently undergoing certification and will be available soon. SOS runs locally or on a server, if you prefer to work directly there. We do not use telemetry. I designed the system to be "agent-first," meaning you can delegate the setup to Codex simply by providing the repository link. The user just needs to provide confirmation at the appropriate steps. I’m interested to see how other users maintain agent state during long-term projects or when switching between agents. Do you find `AGENTS.md` or hand-off notes sufficient? Does governance solve the issue for you, and what challenges do you face? I am particularly interested in scenarios where an old instruction or a previously successful verification is no longer relevant to the current project.
2026-09-08
gnipbao/gpt6-prompt-writer
unrated
GPT-6 Astra prompt writing Skill: generate, optimize, compress, and diagnose prompts based on official guidelines, supporting Codex, Agent, and the Responses API.
2026-09-05
ervareza/boost-skill
unrated
Universal /boost multi-agent reasoning and independent verification pipeline for all AI coding CLIs (Hermes, Claude Code, Codex, OpenCode, Cursor, Aider).
2026-09-02
Mariposa-FLOA/image-skill
unrated
Original visual Skills for Codex, WorkBuddy, and compatible agents.
2026-09-02
yuanjiang-pm/ai-pm-portfolio
unrated
An AI PM's public portfolio from 14 years of product experience: 67 articles / 120,000 words. AI Evals evaluation system, breakdown of the OpenClaw and Codex dual-Agent architecture, AI PM practical frameworks, in-depth frontline interviews, and NCA-GENL certification notes.