# PufferAI/PufferLib

Puffing up reinforcement learning

Repository: https://github.com/PufferAI/PufferLib
Canonical: https://ross.abutalabs.com/products/pufferlib
Homepage: https://puffer.ai/
Language: C
License: MIT
License Family: permissive
Topics: reinforcement-learning
Last push: 2026-08-26T23:14:28+00:00

## Health v2 (maintenance only)
Score: 81/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 46, longevity 100
- inputs: {"age_days": 1447, "days_push": 7, "days_rel": 150, "gap_med": null, "n_releases_24m": 1}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 6306, forks 548 (observed 2026-08-28T04:09:41.609774+00:00)

## What it is
PufferLib is a fast, open-source reinforcement learning library that trains tiny, super-human models in seconds, achieving 1M+ environment steps per second. It bundles its own learning algorithms, hyperparameter tuning, and high-performance C/CUDA environment simulation methods.

## Use cases
- train reinforcement learning agents on game environments at millions of steps per second
- build high-performance custom RL environments in C or CUDA
- run hyperparameter tuning for RL experiments
- train tiny super-human models quickly for research
- run RL demos client-side in the browser
- benchmark and compare RL training methods

## When to choose
- you need maximum RL training throughput on game-like environments
- you want a batteries-included library with algorithms, tuning, and fast environments
- you are doing RL research and want reproducible, fast baselines

## When to avoid
- you need a general-purpose deep learning framework rather than RL
- your environments are slow Python-only and cannot be vectorized
- you need a mature ecosystem of third-party integrations comparable to Gym/Stable-Baselines3

## Facets
- artifact type: library
- maturity: active
- function: reinforcement-learning, machine-learning, simulation, gpu-computing
- domain: reinforcement-learning, machine-learning, gpu-computing
- platform: python, cpp, c, cross-platform
- tags: rl-training, environment-vectorization, high-performance, game-environments, pufferlib, game-development, gpu

## Member repositories
- PufferAI/PufferLib (main) score 81

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:41.609774+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:46:14.010835+00:00, confidence not recorded.
  - readme: https://github.com/PufferAI/PufferLib (fetched 2026-08-28T04:09:41.609774+00:00, sha 6aa2801773e7)
  - homepage: https://puffer.ai/ (fetched 2026-08-29T08:42:42.387917+00:00, sha 76ff64f6ec6a)
- Data as of 2026-08-30T08:39:29.467469+00:00.