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.
🔂 Ralph loop with PRs: Run Claude Code in a continuous loop, autonomously creating PRs, waiting for checks, and merging
| Date | Stars |
|---|---|
| 2026-07-31 | 1363 |
| 2026-08-06 | 1365 |
Today
+2 stars today
This week
— stars this week
This month
— stars this month
Momentum
43.0
growth rate 0.00%/day
<h1><img width="512" height="294" alt="Continuous Claude" src="https://github.com/user-attachments/assets/26878379-6cff-4803-a50d-c1e3f9455f55" /></h1> <details data-embed="anandchowdhary.com" data-title="Continuous Claude" data-summary="Run Claude Code in a loop repeatedly to do large projects"> <summary>Automated workflow that orchestrates Claude Code in a continuous loop, autonomously creating PRs, waiting for checks, and merging - so multi-step projects complete while you sleep.</summary> This all started because I was contractually obligated to write unit tests for a codebase with hundreds of thousands of lines of code and go from 0% to 80%+ coverage in the next few weeks - seems like something Claude should do. So I built [Continuous Claude](https://github.com/AnandChowdhary/continuous-claude), a CLI tool to run Claude Code in a loop that maintains a persistent context across multiple iterations. Current AI coding tools tend to halt after completing a task once they think the job is done and they don't really have an opportunity for self-criticism or further improvement. And this one-shot pattern then makes it difficult to tackle larger projects. So in contrast to running Claude Code "as is" (which provides help in isolated bursts), what you want is to run Claude code for a long period of time without exhausting the context window. Turns out, it's as simple as just running Claude Code in a continuous loop - but drawing inspiration from CI/CD practices and persistent agents - you can take it a step further by running it on a schedule or through triggers and connecting it to your GitHub pull requests workflow. And by persisting relevant context and results from one iteration to the next, this process ensures that knowledge gained in earlier steps is not lost, which is currently not possible in stateless AI queries and something you have to slap on top by setting up markdown files to store progress and context engineer accordingly. ## While + git + persistence The first version of this idea was a simple while loop: ```bash while true; do claude --dangerously-skip-permissions "Increase test coverage [...] write notes for the next developer in TASKS.md, [etc.]" sleep 1 done ``` to which my friend [Namanyay](https://nmn.gl) of Giga AI said "genius and hilarious". I spent all of Saturday building the rest of the tooling. Now, the Bash script acts as the conductor, repeatedly invoking Claude Code with the appropriate prompts and handling the surrounding tooling. For each iteration, the script: 1. Creates a new branch and runs Claude Code to generate a commit 2. Pushes changes and creates a pull request using GitHub's CLI 3. Monitors CI checks and reviews via `gh pr checks` 4. Merges on success or discards on failure 5. Pulls the updated main branch, cleans up, and repeats When an iteration fails, it closes the PR and discards the work. This is wasteful, but with knowledge of test failures, the next attempt can try something different. Because it piggybacks on GitHub's existing workflows, you get code review and preview environments without additional work - if your repo requires code owner approval or specific CI checks, it will respect those constraints. ## Context continuity A shared markdown file serves as external memory where Claude records what it has done and what should be done next. Without specific prompting instructions, it would create verbose logs that harm more than help - the intent is to keep notes as a clean handoff package between runs. So the key instruction to the model is: "This is part of a continuous development loop... you don't need to complete the entire goal in one iteration, just make meaningful progress on one thing, then leave clear notes for the next iteration... think of it as a relay race where you're passing the baton." Here's an actual production example: the previous iteration ended with "Note: tried adding tests to X but failed on edge case, need to handle null input in fun
Excerpt of 22,680 characters
Read on GitHub
Anand Chowdhary · @firstquadrant-ai
126
50
6
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:6fdbbebebb50f789, topic:ai-agents