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.
Minimal and scalable research codebase in JAX, designed for rapid iteration on frontier research in LLM and other autoregressive models.
| Date | Stars |
|---|---|
| 2026-07-31 | 550 |
| 2026-08-05 | 552 |
| 2026-08-13 | 554 |
| 2026-08-18 | 558 |
| 2026-08-19 | 560 |
| 2026-08-20 | 561 |
| 2026-08-21 | 562 |
| 2026-08-23 | 563 |
| 2026-08-25 | 564 |
| 2026-08-28 | 565 |
| 2026-08-29 | 565 |
| 2026-09-02 | 567 |
| 2026-09-03 | 568 |
| 2026-09-06 | 569 |
| 2026-09-10 | 571 |
| 2026-09-15 | 572 |
| 2026-09-16 | 573 |
| 2026-09-20 | 573 |
Today
— stars today
This week
+2 stars this week
This month
+11 stars this month
Momentum
22.0
growth rate 0.35%/day
<!-- mdlint off(LINE_OVER_80) -->
# Simply: Minimal Code for End-to-End Frontier LLM Research
*Simply* is a minimal and scalable research codebase in JAX, designed as an environment where both humans and AI agents can rapidly iterate on frontier LLM research.
- *Quick to [fork and hack](#getting-started)* for fast iteration. We aim at minimizing the time to implement new ideas (e.g., optimizer, training loss, RL algorithms, etc) by humans and AI agents.
- *Minimal abstractions and dependencies* for a simple and self-contained codebase. Learn [Jax](https://jax.readthedocs.io/en/latest/index.html), and you are ready to read and hack the code.
- *An environment for automated AI research* An AI agent, which can itself be powered by an LLM served with *Simply*, can read the code, propose new ideas, run experiments, and iterate autonomously or under the guidance of human researchers. See [automated AI research with agents](#automated-ai-research-with-agents) for simple examples.
- *Agent harnesses for long horizon automated research* Besides the [minimal agent](simply/agent/) example, we recently added one fully featured agent harness named [Amplio](amplio/README.md) designed for long horizon runs suited for automated research with *Simply*.
- That's it, *simply* [get started](#getting-started) now :)
## Getting started
### Example commands
#### Local test for debug
```shell
EXP=simply_local_test_1; rm -rf /tmp/${EXP}; python -m simply.main --experiment_config lm_test --experiment_dir /tmp/${EXP} --alsologtostderr
```
Or if you want to debug by printing arrays like normal python code, you can disable `jit` and `use_scan` using the command below.
```shell
export JAX_DISABLE_JIT=True; EXP=simply_local_test_1; rm -rf /tmp/${EXP}; python -m simply.main --experiment_config lm_no_scan_test --experiment_dir /tmp/${EXP} --alsologtostderr
```
#### Running on Google Cloud TPUs
See the [GCloud Quickstart](gcloud_quickstart.md) to run your first experiment on a Cloud TPU, or the [full GCloud guide](docs/gcloud.md) for multi-host training, preemption handling, and monitoring.
#### Running on GKE with XPK
Google Kubernetes Engine (GKE) is supported. See [GKE quick start](gcloud_quickstart.md#optional-running-on-gke-with-xpk) to run your first experiment on GKE, and [GKE section in the full GCloud guide](docs/gcloud.md#running-on-gke-with-xpk) for details.
#### Automated AI research with agents
You can use agents like [Google Antigravity](https://antigravity.google/), [Claude Code](https://docs.anthropic.com/en/docs/claude-code), or [Gemini CLI](https://github.com/google-gemini/gemini-cli) to run automated research experiments. For example, paste the following prompt into your agent from the repo root to have it design and benchmark new optimizers on a toy setting:
```
You are an AI research agent.
Design and benchmark new optimizers for training a small transformer.
Read simply/utils/optimizers.py to understand the interface.
First, run the Adam baseline using the lm_test config and record the final loss.
In multiple research iterations, propose novel optimizers, tune their hyperparameters, and run experiments to compare with the baseline.
In each iteration, you can propose and run 3 experiments, wait for results and then start the next iteration based on the results of finished experiments. Keep running new iterations until you have finished 15 experiments or proposed 10 new optimizers.
Write a report to /tmp/optimizer_report.md.
```
See the [full guide](docs/automated_ai_research_example.md) for more interesting examples including RL algorithm search for post-training. Have fun playing around with different prompts and interacting with the agent for longer research.
Simply also includes a built-in agent harness (`simply/agent/`) with Bash tool and context management for autonomous long-running research tasks. Quick test:
```bash
pip install ".[agent]"
python -m simply.agent.main \
--task_file=simply/agent/example_tasks/code_stExcerpt of 8,563 characters
Read on GitHub
67
2
1
1
1
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:4dc586b434f30bf0, llm:Description: 'Minimal and scalable research codebase in JAX, designed for rapid iteration on frontier research in LLM and other autoregressive models.' Language: Go (likely tooling), but primary codebase JAX (ML).
matched fp:4dc586b434f30bf0, llm:Description: 'Minimal and scalable research codebase in JAX, designed for rapid iteration on frontier research in LLM and other autoregressive models.' Language: Go (likely tooling), but primary codebase JAX (ML).
matched fp:4dc586b434f30bf0, llm:Description: 'Minimal and scalable research codebase in JAX, designed for rapid iteration on frontier research in LLM and other autoregressive models.' Language: Go (likely tooling), but primary codebase JAX (ML).