Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
The operating layer for Claude Code + OpenAI Codex: persistent project memory, intent routing, safety hooks, cost telemetry, and parallel agent fleets.
| Date | Stars |
|---|---|
| 2026-07-31 | 806 |
| 2026-08-01 | 808 |
| 2026-08-06 | 808 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
35.0
growth rate 0.00%/day
<img src="assets/citadel-hero.svg" width="100%" alt="Citadel, an operating layer for Claude Code and OpenAI Codex" /> <div align="center"> [](https://github.com/SethGammon/Citadel/actions/workflows/tests.yml) [](LICENSE)  [](https://sethgammon.github.io/Citadel/) **An open-source operating layer for Claude Code and OpenAI Codex.** Citadel helps coding agents work reliably across real repositories. It routes requests, preserves project state between sessions, coordinates parallel work, applies repository safeguards, and records verification and handoffs. [Quick install](#quick-install) | [Start using it](#start-using-it) | [Is it a fit?](#when-citadel-is-useful) | [Portable operations](#portable-operations) | [Documentation](#choose-your-documentation) </div> ## Quick install **Requires:** Claude Code or OpenAI Codex, Node.js 18+, and a git repository. Open the repository you want Citadel to manage, then paste this into your coding agent: ```text Install Citadel from https://github.com/SethGammon/Citadel into this repository. Detect whether I am using Codex or Claude Code, show me what will change before applying it, use the current repository as the target, and run Citadel doctor. ``` Follow any printed enable step, start a fresh session if prompted, then run: ```text /do setup --express ``` Setup installs the project hooks and creates the repo-local state Citadel uses to resume work later. <details> <summary><strong>Manual installation</strong></summary> <br> Clone Citadel once: ```bash git clone https://github.com/SethGammon/Citadel.git ~/Citadel ``` From the repository you want Citadel to manage, run the installer for your runtime. **OpenAI Codex** ```bash node ~/Citadel/scripts/install.js --runtime codex --add-marketplace ``` **Claude Code** ```bash node ~/Citadel/scripts/install.js --runtime claude --install --scope local ``` Start a fresh session in the same repository and run `/do setup --express`. </details> Dry runs, generated paths, runtime-specific setup, and rollback are documented in [Installation](INSTALL.md). ## Start using it <img src="assets/terminal-demo.svg" width="100%" alt="A Citadel terminal session routing a request, running checks, and writing a handoff" /> You do not need to learn the skill catalog or operation internals. Start with `/do` and describe the outcome: ```text /do review README.md /do generate tests for the changed files /do next ``` Citadel reveals more machinery only when the work needs it: | Level | Start here | What it gives you | |---|---|---| | 1. Do the work | `/do <request>` | Selects a proportional workflow and verifies the result | | 2. Keep going | `/do next` or `/do continue` | Preserves and resumes work across sessions | | 3. Coordinate | `/dashboard`, campaigns, or Fleet | Makes longer and parallel work visible and recoverable | | 4. Control an operation | `citadel operation ...` | Adds explicit quality, privacy, tool, time, model-fallback, and cost constraints | Most users can stay at Levels 1 and 2. Advanced levels do not replace or complicate `/do`. For a copyable walkthrough in a real repository, use the [demo workflow](DEMO.md). ## When Citadel is useful Citadel is most useful when coding-agent work extends beyond a single prompt: | You are dealing with... | Citadel adds... | |---|---| | Repeated setup and lost context | Repo-local campaigns, decisions, discoveries, and handoffs | | Unclear workflow choice | One natural-language entry point through `/do` | | Risky or multi-step changes | Approval boundaries, lifecycle hooks, and explicit verification | | Several agents or branches | Isolated worktrees, ownership, and shared discoveries | | Work t
Excerpt of 12,690 characters
Read on GitHub
519
14
4
3
Leigh Stillard
1
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:deba47ab069d2120, topic:ai-agents
matched fp:deba47ab069d2120, topic:developer-tools
matched fp:deba47ab069d2120, topic:mcp