HYSEN LABS DIRECTORY

#Large Language Models

Capability tag · curated repositories and deep analysis.

6,244 curated open-source projects
★ 669

Keep Markdown, Jupyter notebooks, and image text translated as your repository changes.

Python112 forks9 min read
bitwize-music-studio

claude-ai-music-skills

★ 668

Human + AI music production workflow for Suno - skills, templates, and tools

Python149 forks6 min read
retrage

gpt-macro

★ 668

ChatGPT powered Rust proc macro that generates code at compile-time.

Rust8 forks6 min read
★ 668

The project integrates the RAG and FAQ dual mechanisms, introduces intent recognition, dynamic adaptive retrieval, and the RAGAS automated evaluation system, achieving a transformation from empirical optimization to data-driven optimization.

Python30 forks7 min read
leonickson1

Swiftlet

★ 668

Swiftlet is a Swift and Metal runtime that runs large Qwen Mixture-of-Experts models locally on Apple devices by streaming expert weights from storage, enabling 35B and 80B models to run with low RAM, including on iPhone.

Swift41 forks6 min read
gargpratyush

jev-router

★ 668

Route to the cheapest model in claude code for your task using jev-router

JavaScript102 forks7 min read
joelhooks

pdf-brain

★ 668

🧠 Local PDF knowledge base with vector search using libsql w/vectors

TypeScript59 forks8 min read
★ 668

LiveKit browser client SDK (javascript)

TypeScript321 forks8 min read
Tura-AI

tura

★ 667

Across 348 long-horizon benchmark sessions, Tura used up to 83.1% fewer turns on the rewrite benchmark and improved the DeepSWE pass rate by up to 16.7 percentage points compared with Codex CLI.

RustAI & Machine Learning36 forks8 min read
machinewrapped

llm-subtrans

★ 667

Open Source project using LLMs to translate subtitles (SRT, SSA/ASS, VTT)

Python69 forks7 min read
ServiceNow

AgentLab

★ 667

AgentLab: An open-source framework for developing, testing, and benchmarking web agents on diverse tasks, designed for scalability and reproducibility.

Python141 forks8 min read
★ 667

A.S.E (AICGSecEval) is a repository-level AI-generated code security evaluation benchmark developed by Tencent Wukong Code Security Team.

Python113 forks4 min read
jamesrochabrun

SwiftOpenAI

★ 666

The most complete open-source Swift package for interacting with OpenAI's public API.

Swift129 forks7 min read
NadirRouter

NadirClaw

★ 666

Open-source LLM router & AI cost optimizer. Routes simple prompts to cheap/local models, complex ones to premium — automatically. Drop-in OpenAI-compatible proxy for Claude Code, Codex, Cursor, OpenClaw. Saves 40-70% on AI API costs. Self-hosted, no middleman.

Python80 forks6 min read
Agent-Field

pr-af

★ 666

#1 open-source code reviewer on Code-Review-Bench

Go75 forks7 min read
PKU-YuanGroup

OpenAI4S

★ 665

Replicate Claude Science using the 9.9-yuan Doubao API

Python81 forks6 min read
joaoh82

rustunnel

★ 665

Self-hosted, secure tunnel server in Rust. Expose local HTTP/HTTPS/TCP/UDP services to the public internet via TLS-encrypted WebSocket. Open-source, pay-as-you-go managed option, MCP server for AI agents.

Rust49 forks8 min read
DiskCryptor

DiskCryptor

★ 665

DiskCryptor Open Source full disk encryption tool

C121 forks6 min read
★ 664

On-device AI for Flutter — Gemma and other LLMs, multimodal, function calling, embeddings, RAG and speech on Android, iOS, Web, macOS, Windows and Linux.

Dart180 forks7 min read
helicalinsight

open-data-pipeline

★ 664

Open Data Pipeline is an AI powered data migration and data transformation tool

Python637 forks6 min read