Répertoire open source

NVlabs

Fast-dLLM

★ 1 090

Official implementation of "Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding"

matlab

matlab-agentic-toolkit

★ 1 090

The MATLAB Agentic Toolkit brings trusted MATLAB capabilities to AI agents, making engineering and scientific workflows agent-ready.

dtsola

xiaoyaosearch

★ 1 090

小遥搜索，听懂你的话、看懂你的图，用AI找到本地任何文件。让搜索像聊天一样简单。XiaoyaoSearch: Understands your words, reads your images, finds any local file with AI. Making search as easy as chatting.

Rishabh-creator601

Books

★ 1 089

Books / PDFS / EPUBS for different fields of programming . READ GROW AND ENJOY 😊😊😊😊

0xGG

crossnote-app

★ 1 088

📝 Local-first markdown notebook - notes live in your browser or local folders as plain markdown files, synced with in-browser git. No server, no account, works offline.

andrepimenta

claude-code-chat

★ 1 087

Beautiful Claude Code Chat Interface for VS Code

zhengkid

Dream-RSI

★ 1 087

The offical repo for "Dream-RSI: Recursive Self-Improvement through Evolving Worlds"

will-moss

isaiah

★ 1 086

Self-hostable clone of lazydocker for the web. Manage your Docker fleet with ease

brufdev

many-notes

★ 1 086

Markdown note-taking web application designed for simplicity

aiptimizer

TurboOCR

★ 1 085

TurboOCR, >200 img/s OmnidocBench. TensorRT FP16, PP-OCRv6, HTTP + gRPC

cognizant-ai-lab

neuro-san-studio

★ 1 084

A playground for neuro-san

sunblaze-ucb

exploitgym

★ 1 084

ExploitGym is a large-scale, realistic benchmark built from real-world vulnerabilities designed to evaluate AI agents' ability to develop exploits.

Farama-Foundation

Stable-Retro

★ 1 083

A fork of gym-retro with additional games, emulators and supported platforms

jla524

fromthetensor

★ 1 083

From the Tensor to Stable Diffusion, a rough outline for a 10 week course.

tigicion

dao-code

★ 1 083

Open-source TypeScript terminal coding agent for DeepSeek-V4 — builds on DeepSeek's strong price-performance and ultra-cheap cache pricing, engineering byte-stable prefixes and cache-reusing forks so cross-session memory and a continuous self-correction layer add almost no token cost; 1M context, Skills/MCP/Hooks, Claude Code config compatible.

nevalang

neva

★ 1 082

Dataflow programming language where you write a program as a message-passing graph and everything runs in parallel by default. It has strong static types, compiles to machine code, interoperates with Go, and supports visual programming with a node editor. Extremely LLM-friendly too.

LucasAlegre

sumo-rl

★ 1 081

Reinforcement Learning environments for Traffic Signal Control with SUMO. Compatible with Gymnasium, PettingZoo, and popular RL libraries.

RUC-NLPIR

Arbor

★ 1 080

A generalist autonomous research agent — runs experiments, researches, and iteratively optimizes, autonomously.

flopperam

unreal-engine-mcp

★ 1 079

This MCP is now owned by Aura! Please try out the most intelligent AI agent for Unreal Engine at https://www.tryaura.dev/?utm_source=youtube&utm_medium=video&utm_campaign=flop

mlr-org

mlr3

★ 1 079

mlr3: Machine Learning in R - next generation