Lists (3)
Sort Name ascending (A-Z)
Stars
Complete logs of the experiments in the blog post 'LLMs can understand and write neural network weights'
The open-source app everyone uses to manage agents at work
AgentOS: Serve agents over API, MCP, and chat interfaces like Slack
Neural Networks: Zero to Hero
Experience-Driven Black-Box Cost Control for Coding Agents
A curated list of papers, tools, and resources on Multi-Token Prediction (MTP) and related techniques in Large Language Models (LLMs), Speech-Language Models (SLMs), and more.
Soft-MTP: Multi-Token Prediction Done Right. KL gradient recovery for faster speculative decoding and better language model training.
Open-source Grok Bot alternative with a virtual machine that bots can use
A complete transformer engine in C — inference, training, chat, vision.
A small llm model I made for a youtube video, isn't the best, nor the worst.
A zero-dependency ML framework in C with a modern Python API for full control over execution and memory.
Deep Learning in Javascript. Train Convolutional Neural Networks (or ordinary ones) in your browser.
Our library for RL environments + evals
Code samples for my book "Neural Networks and Deep Learning"
A Claude Code / Codex plugin that helps you learn how to build while AI writes the code.
Visualizer for neural network, deep learning and machine learning models
A high-throughput and memory-efficient inference and serving engine for LLMs
open-source canvas for thoughtful software design
A small, fast WebKit browser for macOS, by Office Commun.
Non-autoregressive System 1 decision engine. Typed choice, score and yes/no decisions over any text in a single forward pass, in 100+ languages, with a router that picks the right checkpoint per re…
Python SDK for ProgramAsWeights — compile natural language specs into neural programs that run locally
Secure, fast, efficient, battle-tested at Alibaba's scale. Hybrid architecture code review tool: deterministic pipelines + LLM Agent, precise line-level comments, built-in multi-language ruleset (N…
A curated List of Coding Questions Asked in FAANG Interviews
Per-commit evidence records for agent-written code. Captures what the agent tried, what verified it, and what nobody reviewed