Starred repositories
🪢 Open source LLM engineering platform: LLM Observability, metrics, evals, prompt management, playground, datasets. Integrates with OpenTelemetry, Langchain, OpenAI SDK, LiteLLM, and more. 🍊YC W23
An local, offline (after initial setup), portable OCR software that can process images and PDF files, using DeepSeek-OCR AI (running directly on your machine).
A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.
PostTrainBench measures how well CLI agents like Claude Code or Codex CLI can post-train base LLMs on a single H100 GPU in 10 hours
Dr. Zero Self-Evolving Search Agents without Training Data
Elixir hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools
HTTP Proxy that allows you to define the IP address at connect time
Some utility functions to help myself (and perhaps others) go faster with ML/AI work
GDPR, WCAG 2.2 AA, and EAA compliant, self-hosted CAPTCHA alternative with PoW mechanism.
A course on aligning smol models.
Bridge is a multi-level proxy that supports clients and servers with multiple protocols. SSHProxy, HTTPProxy, Socks4, Socks5, Shadowsocks.
Socks5/Socks5h server and client. Full TCP/Bind/UDP and IPv4/IPv6 support
A curated list of awesome computer vision resources
Free course that takes you from zero to Reinforcement Learning PRO 🦸🏻🦸🏽
A lightweight, event-driven TCP/UDP load balancer and proxy built for high-concurrency and mass port binding.
Implementing scalable LLMs in pure JAX (no third-party libraries)
Tutorials about tinygrad, an end-to-end deep learning stack
The Incredible PyTorch: a curated list of tutorials, papers, projects, communities and more relating to PyTorch.