Highlights
- Pro
Stars
Manages Unified Access to Generative AI Services built on Envoy Gateway
Fast, daily-updated skill and CLI for arXiv, PubMed, PMC, and policy retrieval
A platform for reproducible world model research and evaluation
Zig INferenCe Engine — Local LLM inference on AMD GPUs and Apple Silicon
From isolated agents to shared work
Sutskever 30 implementations inspired by https://papercode.vercel.app/ | For Agents, use https://github.com/pageman/Sutskever-Agent | Polyglot / Multi-Backed version at https://github.com/pageman/s…
Run frontier LLMs and VLMs locally on Qualcomm devices across NPU, GPU, and CPU with a few lines of code
Actively maintained open-source game remakes.
SURF - Advanced Go HTTP client with Chrome/Firefox browser impersonation, HTTP/3 with QUIC fingerprinting, JA3/JA4 TLS emulation, and anti-bot bypass for web automation and scraping.
An open-source application for building, observing, and collaborating with teams of AI agents.
Just another reasonably minimal repo for class-conditional training of pixel-space diffusion transformers.
This repository `II-Commons` contains tools for managing text and image datasets, including loading, fetching, and embedding large datasets.
A fast approximate nearest neighbor search library for Go
The repo has been moved to https://github.com/VectorDB-NTU/RaBitQ-Library. [SIGMOD 2025] Practical and Asymptotically Optimal Quantization of High-Dimensional Vectors in Euclidean Space for Approxi…
Go library for embedded vector search and semantic embeddings using llama.cpp
Lightpanda: the headless browser designed for AI and automation
🧠 Train a 64M-parameter LLM from scratch in just 2h!
[NeurIPS 2024] Code release for "Segment Anything without Supervision"
Any model. Any hardware. Zero compromise. Built with @ziglang / @openxla / MLIR / @bazelbuild
Capturing SSL/TLS plaintext without a CA certificate using eBPF. Supported on Linux/Android kernels for amd64/arm64.
llama3 implementation one matrix multiplication at a time