Activity, over time
Daily observations from the public event archive.
Attention
Daily stars & forks
Star accumulation
Cumulative stars
Pull requests
Daily opens & merges
Conversations
Daily issues & comments
Community
Daily accounts & reviews
Releases
Daily releases
Trending history
Daily top 10 · last 90 days · UTC
Mentions
Stars
Forks
Contributors
Latest stargazers
The last 10 distinct accounts we observed this year.
Most active participants
PR, issue, comment & review events in the past year.
Packages
Scan pending.
README badges
Embed a badge in your README or website.
Live mentions · last 30 days
Mentions
10 GitHub Repos That Make OpenAI Codex INSANELY Powerful Turn OpenAI Codex CLI from a simple terminal assistant into a fully autonomous AI development agent! 🚀 We tested and ranked the top 10 open-source GitHub repositories that add MCP server connectivity, AI vision testing, container isolation, and thousands of ready-made agent skills to Codex. 👉 Which repo are you adding to your setup first? Tell us in the comments! ⏱️ CHAPTERS 0:00 Hook 0:45 Ecosystem Overview 1:41 #10 GitHub Agentic Workflows 3:18 #9 Awesome Codex Skills 4:51 #8 Awesome Agent Skills 6:28 #7 Codex CLI Container Sandbox 8:09 #6 Iris Vision UI Testing 9:44 #5 AAS Core Skill Control Plane 11:12 #4 Fullstack MCP Hub 12:21 #3 Awesome Codex CLI Directory 13:21 #2 GitHub MCP Server 14:26 #1 Official OpenAI Codex CLI 15:31 Final Verdict & Summary 🔗 REPOSITORIES IN THIS VIDEO #10 GitHub Agentic Workflows — github/gh-aw #9 Awesome Codex Skills — composio-community/awesome-codex-skills #8 Awesome Agent Skills — VoltAgent/awesome-agent-skills #7 Codex CLI container sandbox — stefanbosak/codex-cli #6 Iris (UI vision testing) — frankbria/iris #5 AAS Core — sickn33/agentic-awesome-skills #4 Fullstack MCP Hub — jbulger82/Fullstack_MCP_hub #3 Awesome Codex CLI — RoggeOhta/awesome-codex-cli #2 GitHub MCP Server — github/github-mcp-server #1 OpenAI Codex CLI — openai/codex ⚠️ Always review a repository's code, permissions and licence before installing it. Some projects in this list are young or small; test them in a sandbox first. This channel is not affiliated with OpenAI, GitHub or any of the listed projects. 🔔 Subscribe to Daily Useful Steps for practical AI and developer tools — small steps, everyday wins. #OpenAICodex #AICoding #GitHub
一条命令装好几个 仓库自带一个安装脚本,从 GitHub 拉 Skill,放到 $CODEX_HOME/skills/<skill 名> 下,没设 CODEX_HOME 就是 ~/.codex/skills/。 git clone ComposioHQ/awesome-codex-skills cd awesome-codex-skills # --path 后面可以跟多个,一次装一批 python skill-installer/scripts/install-skill-from-github.py \ --repo ComposioHQ/awesome-codex-skills \ --path meeting-notes-and-actions create-plan gh-fix-ci 装完一定要重启 Codex,它是启动时读 Skill 元数据的,不重启等于没装。 外部项目那 12 条,安装命令里的脚本路径是 ~/.codex/skills/.system/skill-installer/,比如这条: python3 ~/.codex/skills/.system/skill-installer/scripts/install-skill-from-github.py \ --repo hyhmrright/brooks-lint --path skills/brooks-lint --name brooks-lint .system 目录是 Codex 本地自带的那份安装器,跑之前 ls 一下确认它在。这个脚本要联网,在沙箱里跑会被拦,需要放行。 装没装上,看一眼目录就知道: ls ~/.codex/skills head ~/.codex/skills/meeting-notes-and-actions/SKILL.md 嫌脚本麻烦也可以手动:把 Skill 文件夹整个拷进 ~/.codex/skills/,重启,一两个无所谓,多了还是脚本省事。