workflowstacks
ai-agent

simply: Accelerate LLM Research with a Lean JAX Codebase

A minimal, scalable JAX framework for founders pushing frontier LLM and autoregressive model experiments, enabling rapid iteration and faster breakthroughs.

From the repo · “Minimal and scalable research codebase in JAX, designed for rapid iteration on frontier research in LLM and other autoregressive models.”

585 stars74 forksGoGuide quality 8/10 · reviewed Oct 7Updated 10/23/2026100% free · open source
What it does

Simply allows startup founders to quickly experiment with and train autoregressive models like large language models using a minimal JAX codebase.

When to use it
  • •You need to test novel architectures for autoregressive models without writing extensive code
  • •Your startup requires fast iteration on model training for language tasks
  • •You want to leverage the scalability of JAX for your machine learning research
Ready-to-paste prompt
python train.py --config config.py --model my_language_model
Heads up: Make sure you have JAX installed and a compatible version of Python, as Simply relies on these dependencies to function correctly
Saves to your device
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/simply && curl -fsSL https://workflowstacks.com/api/skills/simply/claude-skill -o ~/.claude/skills/simply/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How simply: Accelerate LLM Research with a Lean JAX Codebase works
Codeflow
Free to inspect

Simply: Accelerate LLM Research with a Lean JAX Codebase is a very large Python project (~156k lines across 540 code files, plus 10 test files). It is a full software project: use it through its install path rather than reading it end to end. Last commit this month, Apache-2.0 license, has a test suite.

Size
Very large codebase
~156k lines · 540 code files · days to read — use, don't read
Setup
Developer setup
A real software project. Use it via its install path; don't expect to read it all.
Runs on
Python
No API keys detected
Python 62%Go 29%Svelte 6%TypeScript 2%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    AGENTS.md
    The instructions the AI actually follows
  3. 3
    simply/main.py
    Where the program starts running
  4. 4
    pyproject.toml
    Dependencies and the commands it exposes
  5. 5
    simply/__init__.py
    Inside simply/ — the main logic begins here
What's in each folder
simply/Core code — the actual logic207 files
docs/Documentation3 files
amplio/Folder360 files
tasks/Folder75 files
scripts/Helper scripts2 files
setup/Folder2 files
.github/CI / automation (GitHub Actions)1 files
READMEHas testsDocumentedCI checksApache-2.0 licenseUpdated this month
Quick Actions
Details
Creator
google-deepmind
Language
Go
Category
ai-agent
Published
3/13/2025

Are you the creator of this tool? and earn 85% of every sale.

Show it off in your README:

Featured on WorkflowStacks
[![Featured on WorkflowStacks](https://workflowstacks.com/api/badge/simply.svg)](https://workflowstacks.com/skills/simply?utm_source=github&utm_medium=badge)
🔥 Hot this week, in your inbox
Skills like this, every Monday.

The five fastest-growing open-source AI skills, ranked by GitHub star growth. One email a week, unsubscribe anytime.

Related skills

More ai-agent tools founders pair with this one.

ai-agent★ 303,974
superpowers
An agentic skills framework & software development methodology that works.
ai-agent★ 277,160
Track GitHub Stars with 996.ICU
Get a popular GitHub star counter for your startup, backed by 276k+ GitHub stars, ideal for founders.
ai-agent★ 253,255
Linux – 251k+ GitHub stars for building custom kernel solutions
Get the complete Linux kernel source in C, perfect for founders needing deep system control or tailored OS components.
ai-agent★ 382
dbt-databricks
A dbt adapter for Databricks.
ai-agent★ 735
VLA-Handbook: Master Vision‑Language‑Action Skills for Robotics Teams
A concise, Chinese, hands‑on guide that prepares algorithm engineers for VLA roles and robotics interview challenges. Ideal for founders hiring AI talent.
ai-agent★ 494
Junie: Ship Code Faster from Terminal, IDE, or CI/CD
Junie lets founders automate code generation with any LLM, delivering ready-to-deploy snippets straight from your workflow. Ideal for teams that want AI‑augmented development without leaving their tools.