🌱 A little course on Reinforcement Learning Environments for evaluating and training Language Models

SGLang is a high-performance serving framework for large language models and multimodal models.

A Paper collection for LLM based Patient Simulators

Democratizing Reinforcement Learning for LLMs

PaperBanana: Automating Academic Illustration For AI Scientists

[ICLR 2025] ACES: Automatic Cohort Extraction System for Event-Streams

Schema definitions and Python types for Medical Event Data Standard, a standard for medical event data such as EHR and claims data

A paper list of Awesome Latent Space.

A machine learning primer built from first principles. For engineers who want to reason about ML systems the way they reason about software systems.

Turn paper/text/topic into editable research figures, technical route diagrams, and presentation slides.

Native web workspace for Hermes Agent — chat, terminal, memory, skills, inspector.

AI Browser

AI agent toolkit: coding agent CLI, unified LLM API, TUI & web UI libraries, Slack bot, vLLM pods

Memory library for building stateful agents

Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM

Meta-Reinforcement Learning with Self-Reflection

Agent skills for Obsidian. Teach your agent to use Markdown, Bases, JSON Canvas, and use the CLI.

Hypernetworks that update LLMs to remember factual information

Hundreds of models & providers. One command to find what runs on your hardware.

"CLI-Anything: Making ALL Software Agent-Native" -- CLI-Hub: https://clianything.cc/

The largest open-source medical AI skills library for OpenClaw🦞.

🦞 Just talk to your agent — it learns and EVOLVES 🧬.

Personal AI, On Personal Devices

The AI-Q NVIDIA Blueprint is an open reference example for building intelligent AI agents that connect to your enterprise data, reason using state-of-the-art models, and deliver trusted business in…

🦖 ClawBio — The first bioinformatics-native AI agent skill library. Local-first. Reproducible. Built on OpenClaw.

Semantic grep powered by Jina embeddings v5 (MLX on Apple Silicon)

Apple Silicon (MLX) port of Karpathy's autoresearch — autonomous AI research loops on Mac, no PyTorch required.