Minimal and scalable research codebase in JAX, designed for rapid iteration on frontier research in LLM and other autoregressive models.
☆551Jul 24, 2026Updated this week
Alternatives and similar repositories for simply
Users that are interested in simply are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- MoE training for Me and You and maybe other people☆395Mar 15, 2026Updated 4 months ago
- ☆304Jul 15, 2024Updated 2 years ago
- A transformer that executes a one-instruction Turing-complete computer — two approaches: hand-coded weights (no training) and learned fro…☆41Mar 3, 2026Updated 4 months ago
- Minimal yet performant LLM examples in pure JAX☆269Jul 4, 2026Updated 3 weeks ago
- Our library for RL environments + evals☆4,413Updated this week
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- Agentic RL Training at Scale☆1,759Updated this week
- ☆24Jan 22, 2026Updated 6 months ago
- AI-Driven Scientific and Algorithmic Discovery☆591Jun 14, 2026Updated last month
- autonomous nanogpt optimizer speedrun☆109May 14, 2026Updated 2 months ago
- The Automated LLM Speedrunning Benchmark measures how well LLM agents can reproduce previous innovations and discover new ones in languag…☆145May 6, 2026Updated 2 months ago
- Puffing up reinforcement learning☆6,200Updated this week
- Open-source framework for the research and development of foundation models.☆1,226Updated this week
- NanoGPT (124M) in 90 seconds☆5,601Updated this week
- Compile programs directly into transformer weights. Includes a 2D convex-hull KV cache with O(log n) inference.☆213Jun 1, 2026Updated last month
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- WIP☆96Aug 13, 2024Updated last year
- Dion optimizer algorithm☆498Updated this week
- Deriving steepest descent convergence bounds and hyperparameter scaling laws in machine learning optimization from first principles, form…☆16Apr 11, 2026Updated 3 months ago
- Pure C / AVX-512 port of Craftax-Classic. 47.8M SPS on a Ryzen 9 9950X3D -- 3.2x an RTX Pro 6000 Blackwell on the same env.☆24Jul 14, 2026Updated 2 weeks ago
- ☆21Jul 7, 2026Updated 3 weeks ago
- slime is an LLM post-training framework for RL Scaling.☆7,696Updated this week
- A Python DSL to write Nvidia PTX for Hopper and Blackwell in JAX and PyTorch☆369Jul 9, 2026Updated 3 weeks ago
- Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.☆1,809Updated this week
- Lightweight Zotero MCP server for AI agents☆15May 16, 2026Updated 2 months ago
- Open source password manager - Proton Pass • AdSecurely store, share, and autofill your credentials with Proton Pass, the end-to-end encrypted password manager trusted by millions.
- ☆31Mar 13, 2026Updated 4 months ago
- A simple, performant and scalable JAX-based world modeling codebase.☆156Jan 15, 2026Updated 6 months ago
- The best ChatGPT that $100 can buy.☆56Updated this week
- Simple & Scalable Pretraining for Neural Architecture Research☆340Mar 31, 2026Updated 3 months ago
- Kernels, of the mega variety :)☆788May 26, 2026Updated 2 months ago
- Lab Cookbook☆38Updated this week
- Checkpoint-engine is a simple middleware to update model weights in LLM inference engines☆984Jul 4, 2026Updated 3 weeks ago
- 100M tokens. Infinite compute. Lowest val loss wins.☆518Jul 3, 2026Updated 3 weeks ago
- A Gym for Agentic LLMs☆503Jan 21, 2026Updated 6 months ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- [NeurIPS 2025 Spotlight] Reasoning Environments for Reinforcement Learning with Verifiable Rewards☆1,469Apr 17, 2026Updated 3 months ago
- A Quirky Assortment of CuTe Kernels☆1,080Updated this week
- Tokamax: A GPU and TPU kernel library.☆256Updated this week
- Post-training with Tinker☆3,949Updated this week
- SkyRL: A Modular Full-stack RL Library for LLMs☆2,102Updated this week
- Tile primitives for speedy kernels☆3,571Jul 13, 2026Updated 2 weeks ago
- Physics of Language Models: Part 4.2, Canon Layers at Scale where Synthetic Pretraining Resonates in Reality☆356May 20, 2026Updated 2 months ago