Design principles for agent ergonomics. Higher accuracy with lower token cost than both MCP and regular CLI.

The best-benchmarked open-source AI memory system. And it's free.

Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflo…

The repo is finally unlocked. enjoy the party! The fastest repo in history to surpass 100K stars ⭐. Join Discord: https://discord.gg/5TUQKqFWd Built in Rust using oh-my-codex.

Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/

From-scratch PyTorch implementation of Google's TurboQuant (ICLR 2026) for LLM KV cache compression. 5x compression at 3-bit with 99.5% attention fidelity.

Muon is an optimizer for hidden layers in neural networks

AI agents running research on single-GPU nanochat training automatically

A lightweight inference engine supporting speculative speculative decoding (SSD).

Symphony turns project work into isolated, autonomous implementation runs, allowing teams to manage work instead of supervising coding agents.

VSCode theme based off the easemate IDE and Jetbrains islands theme

Algorithm powering the For You feed on X

The open source coding agent.

A powerful MCP toolkit for coding, providing semantic retrieval and editing capabilities - the IDE for your agent

Memray is a memory profiler for Python

The personal finance app for everyone. NOT affiliated with or endorsed by Maybe Finance Inc.

Google 💚 MCP

CUDA-L2: Surpassing cuBLAS Performance for Matrix Multiplication through Reinforcement Learning

Tile primitives for speedy kernels

KernelBench: Can LLMs Write GPU Kernels? - Benchmark + Toolkit with Torch -> CUDA (+ more DSLs)

CUDA-L1: Improving CUDA Optimization via Contrastive Reinforcement Learning

An interface library for RL post training with environments.

The absolute trainer to light up AI agents.

A Python-embedded DSL that makes it easy to write fast, scalable ML kernels with minimal boilerplate.

Beads - A memory upgrade for your coding agent

nanobind: tiny and efficient C++/Python bindings

Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

tasks from university courses

The best ChatGPT that $100 can buy.