Alex Cheema

Cofounder of EXO Labs

Starred Projects (30)

autonomous-computer by autonomous-ai

Build your own private AI computer for local model inference

Created 10 months ago

Updated 1 day ago

openhuman by tinyhumansai

Personal AI agent for deep desktop integration and local intelligence

Created 4 months ago

Updated 18 hours ago

inferrs by ericcurtin

LLM inference server optimized for resource efficiency and broad API compatibility

Created 3 months ago

Updated 2 days ago

LifeOS by danielmiessler

Personal AI infrastructure for human augmentation

Created 10 months ago

Updated 1 day ago

recurrent-pretraining by seal-rg

Pretraining code for depth-recurrent language model research

winglian:

chiphuyen:

lucidrains:

Created 1 year ago

Updated 6 months ago

Anemll by Anemll

Framework for porting LLMs to Apple Neural Engine (ANE)

ngaut:

alexchen4ai:

luiscape:

Created 1 year ago

Updated 4 months ago

Vane by ItzCrazyKns

AI-powered search engine alternative

karpathy:

assafelovic:

taranjeet:

jmorganca:

Created 2 years ago

Updated 3 months ago

mcp-reasoner by Jacck

Advanced reasoning engine for complex problem-solving

Created 1 year ago

Updated 1 year ago

omi by BasedHardware

AI wearable for real-time audio capture and intelligent processing

rodrigosnader:

ogabrielluiz:

aksh-at:

omarsar:

Created 2 years ago

Updated 12 hours ago

sidecar by codestoryai

AI brains for the Aide editor, running locally

omarsar:

Created 2 years ago

Updated 1 year ago

modular by modular

AI toolchain unifying fragmented AI deployment workflows

lattner:

tobi:

parano:

zhyncs:

Created 3 years ago

Updated 1 day ago

BitNet by microsoft

Inference framework for 1-bit LLMs

luiscape:

omarsar:

k06a:

parano:

Created 1 year ago

Updated 4 months ago

mlx by ml-explore

Array framework for machine learning on Apple silicon

geohot:

karpathy:

ekzhang:

lysandrejik:

Created 2 years ago

Updated 21 hours ago

vllm by vllm-project

LLM serving engine for high-throughput, memory-efficient inference

karpathy:

clmnt:

tobi:

adamdotdevin:

Created 3 years ago

Updated 12 hours ago

infinity by infiniflow

AI-native database for LLM applications

Created 4 years ago

Updated 1 day ago

exo by exo-explore

AI cluster for running models on diverse devices

hammer:

k06a:

chiphuyen:

omarsar:

Created 2 years ago

Updated 2 weeks ago

tinygrad by tinygrad

Minimalist deep learning framework for education and exploration

geohot:

ebursztein:

millionintegrals:

k06a:

Created 5 years ago

Updated 13 hours ago

llama3-from-scratch by naklecha

Llama3 implementation from scratch, one matrix multiplication at a time

torantulino:

simon-mo:

vincentweisser:

omarsar:

Created 2 years ago

Updated 2 years ago

Dot by alexpinel

Local RAG app for document interaction using local LLMs

omarsar:

joewalnes:

ggerganov:

Created 2 years ago

Updated 1 year ago

Awesome-Multimodal-Large-Language-Models by BradyFU

MLLM resource list, covering papers, datasets, and benchmarks

hugs:

vincentweisser:

jinze1994:

jn2clark:

Created 3 years ago

Updated 1 week ago

MobileAgent by X-PLUG

Mobile device operation assistant research paper

zhiyuan8:

chiphuyen:

omarsar:

Created 2 years ago

Updated 4 days ago

executorch by pytorch

On-device AI framework for PyTorch inference and training

patrickvonplaten:

ebursztein:

danielhanchen:

shimmyshimmer:

Created 4 years ago

Updated 17 hours ago

mlx-bitnet by exo-explore

Efficient LLM inference on Apple Silicon

osanseviero:

winglian:

Created 2 years ago

Updated 2 years ago

JetMoE by myshell-ai

Open-sourced LLM reaching LLaMA2 performance with limited resources

chiphuyen:

jiamings:

thomwolf:

jwyang:

Created 2 years ago

Updated 1 year ago

Triton-Puzzles by gpu-mode

Interactive puzzles for learning Triton

winglian:

sebastiandero:

borzunov:

hammer:

Created 2 years ago

Updated 3 months ago

BitNet by kyegomez

PyTorch implementation of BitNet research paper

winglian:

victortaelin:

gakonst:

Created 2 years ago

Updated 5 days ago

unilm by microsoft

Foundation models for language, vision, speech, and multimodal tasks

jph00:

chiphuyen:

osanseviero:

parano:

Created 7 years ago

Updated 5 months ago

tract by sonos

Tiny, self-contained inference engine for diverse hardware and modalities

gakonst:

lantiga:

binarybana:

kerollmops:

Created 9 years ago

Updated 15 hours ago

graph-of-thoughts by spcl

Graph-of-Thoughts: LLM framework for complex problem-solving

yiranwu0:

ngaut:

chiphuyen:

vincentweisser:

Created 2 years ago

Updated 3 months ago

novel by steven-tey

Open-source editor with AI-powered autocompletions

tobi:

syrusakbary:

rodrigosnader:

ogabrielluiz:

Created 3 years ago

Updated 1 year ago

Feedback? Help us improve.