Starred repositories
DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm
Vite+ is the unified toolchain and entry point for web development. It manages your runtime, package manager, and frontend toolchain in one place.
AI agents running research on single-GPU nanochat training automatically
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
Modern Python client for Apache Solr with type safety and async support, built with httpx and Pydantic
agent-sandbox enables easy management of isolated, stateful, singleton workloads, ideal for use cases like AI agent runtimes.
Financial Services Interest Group
vlrosa-dev / hextra
Forked from imfing/hextra🔯 Modern, batteries-included Hugo theme for creating beautiful doc, blog and static websites
gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI
Extremely fast Query Engine for DataFrames, written in Rust
OCaml implementation of word embedding algorithms with minimal dependencies
TinyGo drivers for sensors, displays, wireless adaptors, and other devices that use I2C, SPI, GPIO, ADC, and UART interfaces.
Specification and documentation for the Model Context Protocol
A lightweight, powerful framework for multi-agent workflows
Minimal reproduction of DeepSeek R1-Zero
[AAAI 2026] Global Compression Commander: Plug-and-Play Inference Acceleration for High-Resolution Large Vision-Language Models
An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.
👻 Ghostty is a fast, feature-rich, and cross-platform terminal emulator that uses platform-native UI and GPU acceleration.
AI Agent Framework, the Pydantic way
Visualise your CSV files in seconds without sending your data anywhere
wazero: the zero dependency WebAssembly runtime for Go developers