Starred repositories
AI agents running research on single-GPU nanochat training automatically
Beads - A memory upgrade for your coding agent
Fabric is an open-source framework for augmenting humans using AI. It provides a modular system for solving specific problems using a crowdsourced set of AI prompts that can be used anywhere.
A high-performance distributed file system designed to address the challenges of AI training and inference workloads.
[Chumsky has moved to Codeberg!] Write expressive, high-performance parsers with ease.
An extremely fast Python package and project manager, written in Rust.
Two conversational AI agents switching from English to sound-level protocol after confirming they are both AI agents
Distributed LLM inference. Connect home devices into a powerful cluster to accelerate LLM inference. More devices means faster inference.
A free and strong UCI chess engine
Redfish is an open-source chess engine written in C++.
PyTheus, a highly-efficient discovery framework for quantum optical experiments
A lil' TOML writer (counterpart to https://github.com/hukkin/tomli)
OpenHealth, AI Health Assistant | Powered by Your Data
An AI-powered research assistant that performs iterative, deep research on any topic by combining search engines, web scraping, and large language models. The goal of this repo is to provide the si…
⭐️ Companies that don't have a broken hiring process
ollama modelfiles for deepseek and goose
an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM
DeepSeek Coder: Let the Code Write Itself
Fully open reproduction of DeepSeek-R1
A Self-adaptation Framework🐙 that adapts LLMs for unseen tasks in real-time!
Build, Evaluate, and Optimize AI Systems. Includes evals, RAG, agents, fine-tuning, synthetic data generation, dataset management, MCP, and more.
Open-source vector similarity search for Postgres
Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"