HYSEN LABS DIRECTORY

#Python

Language tag · curated repositories and deep analysis.

5,218 curated open-source projects

helallao

perplexity-ai

★ 1,957

Unofficial API Wrapper for Perplexity.ai + Account Generator with Web Interface

Python343 forks

photonixapp

A modern, web-based photo management server. Run it on your home server and it will let you find the right photo from your collection on any device. Smart filtering is made possible by object recognition, face recognition, location awareness, color analysis and other ML algorithms.

Python136 forks

jd-opensource

JoyAI-VL-Interaction

★ 1,948

JoyAI-VL-Interaction: An Open Real-time Video-Language Interaction System

Python196 forks

microsoft

Magma

★ 1,947

[CVPR 2025] Magma: A Foundation Model for Multimodal AI Agents

Python165 forks

AI4Finance-Foundation

FinRL-Meta

★ 1,947

FinRL®-Meta: Dynamic datasets and market environments for FinRL.

Python750 forks

nosarthur

gita

★ 1,947

Manage many git repos with sanity.

Python93 forks

kyegomez

BitNet

★ 1,947

Implementation of "BitNet: Scaling 1-bit Transformers for Large Language Models" in pytorch

Python174 forks

tum-pbs

PhiFlow

★ 1,945

A differentiable PDE solving framework for machine learning

Python235 forks

databricks-solutions

ai-dev-kit

★ 1,942

Databricks Toolkit for Coding Agents provided by Field Engineering

Python428 forks

HKUDS

VideoAgent

★ 1,937

[EMNLP2026] "VideoAgent: All-in-One Agentic Framework for Video Understanding and Editing, and Remaking"

Python243 forks

vstorm-co

full-stack-ai-agent-template

★ 1,937

Full-stack AI app generator — FastAPI + Next.js with AI Agents, RAG, streaming, auth, and 20+ integrations out of the box.

Python388 forks

aipoch

medical-research-skills

★ 1,935

Hundreds of agent skills for medical research, including protocol design, data analysis, evidence insights, and academic writing.

Python186 forks

AlexxIT

YandexStation

★ 1,933

Управление Яндекс.Станцией и другими устройствами умного дома с Алисой из Home Assistant

Python182 forks

syv-ai

qwen38-27b-rtx3090

★ 1,933

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

Python266 forks