HYSEN LABS DIRECTORY

#Apache 2.0

License tag · curated repositories and deep analysis.

4,603 curated open-source projects
kyky2347

ALTA

★ 1,098

Autonomous LLM Trading Asterism — a research-only multi-agent trading platform with evidence-first research, an auditable console, Shadow simulation and explicitly authorized broker execution.

Python130 forks
bubblelabai

BubbleLab

★ 1,097

Open-core workflow engine powering Bubble Lab — and fully runnable, hostable, and extensible on its own.

TypeScript183 forks
RUC-NLPIR

Arbor

★ 1,096

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

Python128 forks
NVlabs

Fast-dLLM

★ 1,095

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

Python145 forks
chrisbanes

skills

★ 1,095

Skills for Kotlin, Jetpack Compose, and Android development

Python53 forks
spring-ai-alibaba

Lynxe

★ 1,095

A high-determinism, code-free 'Prompt Programming' studio built with Java.

Java248 forks
agents-io

PokeClaw

★ 1,090

PokeClaw (PocketClaw) — first on-device AI that controls your Android phone. Gemma 4, no cloud, no API key. Poke is short for Pocket.

Kotlin155 forks
capitalone

VulnHunter

★ 1,090

Agentic AI security tool that applies proactive, attacker-first analysis directly to source code.

Python159 forks
cisco-ai-defense

mcp-scanner

★ 1,089

Scan MCP servers for potential threats & security findings.

Python140 forks
ix-infrastructure

Ix

★ 1,088

Understand any codebase instantly. System intelligence for codebases, built for humans and AI.

TypeScript82 forks
shinkuan

Akagi

★ 1,088

Supports Majsoul, Tenhou, Riichi City, and Amatsuki, with the ability to use custom AI models to analyze games in real time and provide suggestions. Comes with Mortal AI as a built-in example.

Rust137 forks

The definitive vLLM runtime for dual RTX 2080 Ti 22GB + NVLink, delivering Qwen 27B local inference with maximum 100+ tok/s single-request decode with support of FP8 weight ( Join Discord :https://discord.gg/VFqVVySdMS )

Python148 forks
LycheeMem

LycheeMem

★ 1,082

Lightweight Long-Term Memory for LLM Agents.

Python18 forks
beltromatti

get-it

★ 1,082

Read it. See it. Get it. Built at GDG AI Hack Milan 2026 for "Learn Different" track.

JavaScript122 forks
THU-BPM

MarkLLM

★ 1,082

[EMNLP 2024 Demo] MarkLLM: An Open-Source Toolkit for LLM Watermarking

Python96 forks
apache

ranger

★ 1,080

Apache Ranger - Centralized, fine-grained authorization and auditing across data and AI platforms

Java1,091 forks
arcee-ai

DistillKit

★ 1,079

An Open Source Toolkit For LLM Distillation

Python143 forks
★ 1,078

Model Zoo For OpenCV DNN and Benchmarks.

Python312 forks
★ 1,078

Official remote MCP server for Atlassian. Securely connect Jira, Confluence, Jira Service Management, Bitbucket, and Compass to Claude, ChatGPT, Cursor, VS Code, and other AI tools using OAuth 2.1 or API tokens.

JavaScript139 forks
FlashML-org

FreeVideo

★ 1,077

Make videos on the computer you already own. FreeVideo runs MiniMax H3 in as little as 8 GB of VRAM and 16 GB of RAM, and adapts its acceleration path to your hardware.

Python100 forks