Discover

Every project in the index. Underrated first: good projects that haven’t been noticed yet.

11 projects

TokenSpeed
LLM serving engine tuned for agentic workloads on datacenter GPUs
AI models and runtimes Servers and infrastructure
2.7k
forge
Reliability layer that makes local LLM tool calls succeed more often
Agent frameworks and tools AI models and runtimes
Antoine2.3k
RLM
Inference library letting language models recursively call themselves via a REPL
Agent frameworks and tools AI models and runtimes
az5.7k
DFlash
Block diffusion draft models for faster LLM speculative decoding
AI models and runtimes
6.2k
MLX-VLM
Run and fine-tune vision language models locally on Apple silicon
AI models and runtimes
Prince Canuma5.6k
whichllm
Command-line tool that ranks local LLMs that will run on your hardware
AI models and runtimes Developer tools
andy6.8k
tinygrad
Small, readable deep learning framework with its own kernel compiler
AI models and runtimes Languages and frameworks
33.8k
nanochat
Minimal codebase for training a small chat LLM end to end on one GPU node
AI models and runtimes Education
Andrej58.8k
PersonaPlex
Full-duplex speech-to-speech model with prompt-set roles and voices
AI models and runtimes AI media
11.2k
DeepSeek-V3
Open-weight 671B Mixture-of-Experts language model with 128K context
AI models and runtimes
105k
VibeVoice
Open speech recognition and text-to-speech models from Microsoft
AI media AI models and runtimes
54.9k