Will Brown

Research Lead at Prime Intellect

Starred Projects (88)

cmux by manaflow-ai

Parallel coding agent CLI manager

timsuchanek:

mjackson:

katt:

hsbt:

Created 7 months ago

Updated 5 hours ago

flue by withastro

TypeScript framework for building autonomous agents

dguido:

timsuchanek:

transitive-bullshit:

didierrlopes:

Created 7 months ago

Updated 1 day ago

hermes-agent by NousResearch

Autonomous AI agent for persistent learning and task automation

mckaywrigley:

osanseviero:

didierrlopes:

hugs:

Created 1 year ago

Updated 8 hours ago

clanker by bgdnvk

AI-powered CLI agent for multi-cloud infrastructure

vincentweisser:

transitive-bullshit:

Created 1 year ago

Updated 1 month ago

opencode by anomalyco

CLI tool for AI-assisted coding in the terminal

geohot:

karpathy:

tobi:

khou22:

Created 1 year ago

Updated 5 hours ago

nmoe by Noumena-Network

High-performance MoE trainer for NVIDIA B200 GPUs

pgarbacki:

Created 8 months ago

Updated 5 months ago

verifiers by PrimeIntellect-ai

RL for LLMs in verifiable environments

karpathy:

rasbt:

jeffchuber:

hammer:

Created 1 year ago

Updated 14 hours ago

kosong by MoonshotAI

LLM abstraction layer for AI agent applications

Created 1 year ago

Updated 1 month ago

stagehand by browserbase

AI browser automation framework for production

chiphuyen:

luiscape:

sorenbs:

didierrlopes:

Created 2 years ago

Updated 19 hours ago

rlm-minimal by alexzhang13

Minimal Recursive Language Models (RLMs) with REPL environments

john-b-yang:

okhat:

JohannesHa:

Created 10 months ago

Updated 8 months ago

torchforge by meta-pytorch

Agentic RL library for scalable PyTorch experimentation

hammer:

abidlabs:

vincentweisser:

Created 1 year ago

Updated 1 day ago

tinker-cookbook by thinking-machines-lab

Advanced LLM fine-tuning SDK and example cookbook

ebursztein:

pcmoritz:

Jiayi-Pan:

hammer:

Created 1 year ago

Updated 2 days ago

frontier-evals by openai

Code repo for OpenAI preparedness evals

swyxio:

shizhediao:

JustinLin610:

transitive-bullshit:

Created 1 year ago

Updated 4 months ago

firecrawl by firecrawl

API service for turning websites into LLM-ready data

tobi:

dirkenglund:

binarybana:

mmcc:

Created 2 years ago

Updated 19 hours ago

batch_invariant_ops by thinking-machines-lab

Enhance LLM inference determinism

Edward-Sun:

zhyncs:

ekzhang:

zhuohan123:

Created 1 year ago

Updated 10 months ago

semtools by run-llama

CLI tools for semantic search and document parsing

didierrlopes:

jerryjliu:

Created 1 year ago

Updated 6 months ago

SkyRL by NovaSky-AI

RL training pipeline for multi-turn tool use LLMs, optimized for real-world tasks

didierrlopes:

gakonst:

infwinston:

zhyncs:

Created 1 year ago

Updated 1 day ago

agent-lightning by microsoft

Train any AI agent with rollouts and feedback

pgarbacki:

dguido:

torantulino:

omarsar:

Created 1 year ago

Updated 1 week ago

judges by databricks

LLM evaluation library for classifiers and graders

rotemweiss57:

Created 2 years ago

Updated 1 year ago

gpt-oss-recipes by huggingface

OpenAI GPT-OSS model optimization and fine-tuning

eugeneyan:

hiyouga:

lysandrejik:

lewtun:

Created 1 year ago

Updated 1 year ago

gpt-oss by openai

Open-weight LLMs for reasoning and agents

karpathy:

danielhanchen:

borzunov:

chiphuyen:

Created 1 year ago

Updated 1 month ago

openbench by groq

Provider-agnostic LLM evaluation infrastructure

shizhediao:

mchiang0610:

mlabonne:

lewtun:

Created 1 year ago

Updated 2 weeks ago

gem by axon-rl

Agentic LLM training environment for interactive reinforcement learning

didierrlopes:

lewtun:

hiyouga:

vincentweisser:

Created 1 year ago

Updated 7 months ago

terminal-bench-1 by harbor-framework

Benchmark for LLM agents in real terminal environments

gaearon:

ebursztein:

ogabrielluiz:

transitive-bullshit:

Created 1 year ago

Updated 2 months ago

llm by simonw

CLI tool and Python library for LLM interaction

hugs:

binarybana:

willingc:

gakonst:

Created 3 years ago

Updated 2 days ago

ring-flash-attention by zhuzilin

FlashAttention extension for ring attention

JohannesHa:

pgarbacki:

CodeCreator:

Jiayi-Pan:

Created 2 years ago

Updated 1 year ago

evalchemy by mlfoundations

LLM evaluation toolkit for post-trained language models

hammer:

mlabonne:

casper-hansen:

JustinLin610:

Created 1 year ago

Updated 6 months ago

tokasaurus by ScalingIntelligence

LLM inference engine for high-throughput workloads

ShishirPatil:

xiezhq-hermann:

chiphuyen:

Created 1 year ago

Updated 9 months ago

cartridges by HazyResearch

Lightweight long context representation for LLMs

vincentweisser:

w4nderlust:

aksh-at:

xiezhq-hermann:

Created 1 year ago

Updated 5 months ago

RL2 by ChenmienTan

Reinforcement learning for large language models

CodeCreator:

winglian:

jaredpalmer:

merrymercy:

Created 1 year ago

Updated 3 months ago

CommonGround-legacy by Intelligent-Internet

Build and observe collaborative AI agent teams

Created 1 year ago

Updated 1 year ago

inspect_evals by UKGovernmentBEIS

LLM evaluation suite with diverse benchmarks

hammer:

Created 1 year ago

Updated 1 day ago

open-deep-research by Nutlope

AI-powered research reports

Created 1 year ago

Updated 1 week ago

helix-db by HelixDB

Graph-vector database for RAG and AI applications

tobi:

transitive-bullshit:

1st1:

luiscape:

Created 1 year ago

Updated 17 hours ago

hud-python by hud-evals

AI agent development and evaluation toolkit

didierrlopes:

ekzhu:

Created 1 year ago

Updated 1 day ago

RL by NVIDIA-NeMo

Scalable toolkit for efficient model reinforcement learning

vincentweisser:

hammer:

wangshangsam:

pcmoritz:

Created 1 year ago

Updated 3 hours ago

openagents by OpenAgentsInc

Command Claude Code

hugs:

AntonOsika:

Created 2 years ago

Updated 2 days ago

arbor by Ziems

Framework for optimizing DSPy programs with RL

jeffchuber:

okhat:

Created 1 year ago

Updated 8 months ago

ao by pytorch

PyTorch library for quantization and sparsity in training/inference

danielhanchen:

shimmyshimmer:

parano:

alexchen4ai:

Created 2 years ago

Updated 17 hours ago

ReCall by Agent-RL

RL framework for LLM tool use

bryanhelmig:

casper-hansen:

Created 1 year ago

Updated 1 year ago

opencode by opencode-ai

CLI tool for terminal-based AI coding assistance

tobi:

didierrlopes:

jrk:

soumith:

Created 1 year ago

Updated 11 months ago

ART by OpenPipe

RL library for training LLM agents via GRPO

swyxio:

rotemweiss57:

lewtun:

luiscape:

Created 1 year ago

Updated 1 day ago

MisguidedAttention by cpldcpu

LLM reasoning benchmark for evaluating responses to misleading prompts

victortaelin:

winglian:

Created 2 years ago

Updated 1 year ago

DeepSeekRL-Extended by brendanhogan

GRPO implementation for scaled RL research

winglian:

Created 1 year ago

Updated 1 year ago

modded-nanogpt by KellerJordan

Language model training speedrun on 8x H100 GPUs

geohot:

karpathy:

jn2clark:

lewtun:

Created 2 years ago

Updated 1 month ago

codemcp by ezyang

Coding assistant for Claude Desktop, enabling code edits and testing

soumith:

Created 1 year ago

Updated 8 months ago

instructor by 567-labs

SDK for structured LLM outputs using Pydantic models

cournape:

gregpr07:

jxnl:

marcklingen:

Created 3 years ago

Updated 7 hours ago

verdict by haizelabs

Framework for LLM-as-a-judge systems, scaling evaluation

didierrlopes:

thomwolf:

natolambert:

hammer:

Created 1 year ago

Updated 10 months ago

demystify-long-cot by eddycmu

Research code for long chain-of-thought reasoning in LLMs

hiyouga:

hammer:

Created 1 year ago

Updated 1 year ago

TextArena by TextArena

LLM evaluation and training framework

logankilpatrick:

Created 1 year ago

Updated 3 weeks ago

reasoning-gym by open-thought

Procedural dataset generator for reasoning models

pgarbacki:

natolambert:

shizhediao:

ekzhu:

Created 1 year ago

Updated 4 months ago

avante.nvim by avante-corp

Neovim plugin emulating Cursor AI IDE for AI-driven code assistance

sxyu:

KyleAMathews:

patrickvonplaten:

jrk:

Created 2 years ago

Updated 1 day ago

shortest by antiwork

AI-powered framework for natural language end-to-end testing

transitive-bullshit:

cbh123:

Created 2 years ago

Updated 1 month ago

genesis-world by Genesis-Embodied-AI

Physics platform for robotics & embodied AI learning

alexchen4ai:

chiphuyen:

omarsar:

ashtom:

Created 2 years ago

Updated 1 day ago

OpenRLHF by OpenRLHF

RLHF framework for scalable training of large language models

beyang:

parano:

vincentweisser:

binarybana:

Created 3 years ago

Updated 20 hours ago

priompt by anysphere

JSX-based prompting library for context window management

truell20:

kentcdodds:

compuives:

bryanhelmig:

Created 3 years ago

Updated 11 months ago

markitdown by microsoft

Python tool for converting files to Markdown for LLM text analysis

mojombo:

chiphuyen:

omarsar:

handotdev:

Created 1 year ago

Updated 1 day ago

aider by Aider-AI

AI pair programming in your terminal

bcherny:

nat:

hammer:

ekzhu:

Created 3 years ago

Updated 3 months ago

crewAI by crewAIInc

Framework for autonomous AI agent orchestration via role-playing and collaboration

tobi:

hammer:

smthomas:

zjasper666:

Created 2 years ago

Updated 23 hours ago

cohere-toolkit by cohere-ai

RAG toolkit for LLM application development and deployment

chiphuyen:

jph00:

pgarbacki:

transitive-bullshit:

Created 2 years ago

Updated 5 months ago

open-instruct by allenai

Training codebase for instruction-following language models

hammer:

zhyncs:

vincentweisser:

RJT1990:

Created 3 years ago

Updated 7 hours ago

tensorzero by tensorzero

LLMOps framework for optimizing LLM applications via production data feedback

hammer:

kerollmops:

chiphuyen:

ebursztein:

Created 2 years ago

Updated 3 months ago

letta by letta-ai

Agent framework for stateful agents with memory, reasoning, and context management

hammer:

gregpr07:

hiyouga:

xiezhq-hermann:

Created 2 years ago

Updated 17 hours ago

LLM-Training-Puzzles by srush

Hands-on puzzles for large language model training

Jiayi-Pan:

albertfgu:

hiyouga:

patrickvonplaten:

Created 3 years ago

Updated 2 years ago

SuperPrompt by NeoVertex1

Prompt engineering research for AI agent understanding

pgarbacki:

alexchen4ai:

bryanhelmig:

Created 2 years ago

Updated 4 months ago

claude-quickstarts by anthropics

Quickstarts for Anthropic API application development

dguido:

omarsar:

Edward-Sun:

chiphuyen:

Created 2 years ago

Updated 6 days ago

unstructured by Unstructured-IO

ETL solution for structuring unstructured data for language models

zhiyuan8:

pgarbacki:

handotdev:

pirroh:

Created 4 years ago

Updated 1 day ago

infinity by michaelfeil

REST API for high-throughput, low-latency embedding and reranking

luiscape:

ishaan-jaff:

ankane:

zhyncs:

Created 2 years ago

Updated 5 months ago

mito by mito-ds

Jupyter extensions for faster Python coding

calebpeffer:

joewalnes:

Created 4 years ago

Updated 1 month ago

flash-linear-attention by fla-org

Efficient Torch/Triton implementations for linear attention models

didierrlopes:

hiyouga:

xiezhq-hermann:

zhyncs:

Created 2 years ago

Updated 1 day ago

lectures by gpu-mode

Lecture series for GPU-accelerated computing

cournape:

stas00:

danielhanchen:

xiezhq-hermann:

Created 2 years ago

Updated 2 days ago

trl by huggingface

Library for transformer RL

jeffchuber:

vincentweisser:

tjbck:

alexchen4ai:

Created 6 years ago

Updated 17 hours ago

Open-Reasoning-Tasks by NousResearch

Reasoning tasks collection for LLMs

zjasper666:

winglian:

JohannesHa:

philschmid:

Created 2 years ago

Updated 1 year ago

SiLLM by armbues

Toolkit for training/running LLMs on Apple Silicon using MLX

tjbck:

Created 2 years ago

Updated 1 year ago

phi by JosefAlbers

Apple Silicon framework for language and vision models

gakonst:

Created 2 years ago

Updated 1 month ago

thread-notebook by alishobeiri

AI-powered Jupyter Notebook alternative with local AI copilot

marcklingen:

joewalnes:

Created 2 years ago

Updated 3 months ago

LlamaGym by KhoomeiK

SDK for fine-tuning LLM agents with online reinforcement learning

winglian:

vincentweisser:

osanseviero:

chiphuyen:

Created 2 years ago

Updated 2 years ago

atomic-agents by Eigenwise

Agentic AI framework for building modular, predictable AI pipelines

sxyu:

Created 2 years ago

Updated 2 weeks ago

AgentBoard by hkust-nlp

Analytical evaluation board for multi-turn LLM agents

pgarbacki:

Created 2 years ago

Updated 2 years ago

AgentGym by WooooDyy

Agent framework for LLM-based agent development and evaluation

Created 2 years ago

Updated 3 months ago

repeng by vgel

Python library for representation engineering control vectors

jph00:

winglian:

tgaddair:

Created 2 years ago

Updated 11 months ago

mlx-examples by ml-explore

Examples using the MLX framework

hammer:

didierrlopes:

awni:

JustinLin610:

Created 2 years ago

Updated 5 months ago

llm-course by mlabonne

LLM course with roadmaps and notebooks

mlabonne:

shizhediao:

shimmyshimmer:

zhiyuan8:

Created 3 years ago

Updated 7 months ago

maestro by Doriandarko

Framework for Claude Opus to orchestrate subagents

omarsar:

winglian:

Created 2 years ago

Updated 2 years ago

loom by socketteer

Tree-based writing interface for human-AI collaboration

bryanhelmig:

JohannesHa:

vincentweisser:

omarsar:

Created 5 years ago

Updated 2 years ago

ml-engineering by stas00

Open book for LLM/VLM training engineers

tobi:

stas00:

WoosukKwon:

ppwwyyxx:

Created 6 years ago

Updated 1 day ago

llm.c by karpathy

LLM training in pure C/CUDA, no PyTorch needed

norvig:

alexey-milovidov:

didierrlopes:

hiyouga:

Created 2 years ago

Updated 1 year ago

openui by wandb

UI prototyping tool using LLMs

ishaan-jaff:

doriandarko:

willingc:

lukas:

Created 2 years ago

Updated 1 day ago

Feedback? Help us improve.