HYSEN LABS 專案目錄

開源專案目錄

以精準分類、人工校驗資料與實用脈絡整理值得關注的開源專案。

19173 個精選開源專案

huggingface

aisheets

★ 1,646

Build, enrich, and transform datasets using AI models with no code

TypeScript139 個 Fork

ymcui

Chinese-XLNet

★ 1,645

Pre-Trained Chinese XLNet（中文XLNet预训练模型）

Python278 個 Fork

symforce-org

symforce

★ 1,643

Fast symbolic computation, code generation, and nonlinear optimization for robotics

C++178 個 Fork

iwe-org

iwe

★ 1,642

此專案圍繞「Markdown knowledge graph, LSP for your editor, CLI + MCP memory for your AI agents.」建置，聚焦實際場景的開源實作，提供可重用的工具鏈與整合方式。

RustAI 與機器學習75 個 Fork

Rust AI 與機器學習可自託管桌面端

DataTalksClub

ai-dev-tools-zoomcamp

★ 1,642

A free, hands-on course on using AI developer tools to build, test, deploy, extend, and audit software without losing engineering discipline. The 2026 cohort starts August 31.

Python270 個 Fork

lucasastorian

llmwiki

★ 1,641

Open Source Implementation of Karpathy's LLM Wiki. Upload documents, connect your Claude account via MCP, and have it write your wiki !

Python235 個 Fork

fetchai

uAgents

★ 1,640

A fast and lightweight framework for creating decentralized agents with ease.

Python358 個 Fork

InterDigitalInc

CompressAI

★ 1,640

A PyTorch library and evaluation platform for end-to-end compression research

Python279 個 Fork

nasa-jpl

rosa

★ 1,640

ROSA 🤖 is an AI Agent designed to interact with ROS1- and ROS2-based robotics systems using natural language queries. ROSA helps robot developers inspect, diagnose, understand, and operate robots.

Python181 個 Fork

mediar-ai

terminator

★ 1,640

playwright for windows computer use

Rust217 個 Fork

spec-kitty

★ 1,639

Spec-Driven Development for serious software developers. Spec Coding with with Claude, Cursor, Gemini, Codex. Kanban dashboard, git worktrees, auto-merge and more.

Python170 個 Fork

Jeffser

Alpaca

★ 1,638

🦙 Local and online AI hub

Python144 個 Fork

HumanSignal

Adala

★ 1,637

Adala: Autonomous DAta (Labeling) Agent framework

Python160 個 Fork

gomlx

★ 1,637

GoMLX: An Accelerated Machine Learning Framework For Go

Go83 個 Fork

syv-ai

Qwen3.8-27B on a single RTX 3090 with vLLM: ~1,000 tok/s at 64 concurrent (int8 tensor-core GEMMs, fp16 DeltaNet state), ~114 tok/s single-user at default sampling / ~124 greedy (MTP drafts, own-output draft vocab, calibrated int4 lm_head, split-KV verify attention), 150k-262k context; patches, requant scripts, benchmarks

Python230 個 Fork