Starred repositories
A theoretical reconstruction of the Claude Mythos architecture, built from first principles using the available research literature.
VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning
Optimize prompts, code, and more with AI-powered Reflective Optimization
An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.
Hundreds of models & providers. One command to find what runs on your hardware.
Running a big model on a small laptop
OpenClaw-RL: Train any agent simply by talking
A reinforcement learning agent built from scratch in C++, trained on the cart-pole environment.
Dermatology ddx dataset, Jax implementations of Monte Carlo conformal prediction, plausibility regions and statistical annotation aggregation from our recent work on uncertain ground truth (TMLR'23…
Synthetic Dialog Generation and Analysis with LLMs
official implementation for our paper Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning (NeurIPS 2023)
Making open safety AI models accessible and beneficial to the safety community
Scalable toolkit for efficient model reinforcement
OpenCE (Open Context Engineering): A community toolkit to implement, evaluate, and combine LLM context strategies (RAG, ACE, Compression). Evolved from the `ACE-open` reproduction.
An interface library for RL post training with environments.
Open-source repository for Semantic Modeling Language (SML)
Procedural data generators for verifiable reasoning, synthetic pretraining, post-training, evaluation, and RL.
A high-throughput and memory-efficient inference and serving engine for LLMs
A framework for few-shot evaluation of language models.
Official code release for "SuperBPE: Space Travel for Language Models"
A scalable asynchronous reinforcement learning implementation with in-flight weight updates.