deep-swe
Measuring frontier coding agents on original, long-horizon engineering tasks
HYSEN LABS DIRECTORY
Language tag · curated repositories and deep analysis.
Measuring frontier coding agents on original, long-horizon engineering tasks
GPT-SoVITS ONNX Inference Engine & Model Converter
Playing the game of snake with AI.
Minimal AI coding agent (~1,000 lines of Python) inspired by Claude Code. Works with any LLM. Think NanoGPT for coding agents. Formerly NanoCoder.
TurboQuant: Near-optimal KV cache quantization for LLM inference (3-bit keys, 2-bit values) with Triton kernels + vLLM integration
AI + Finance (quant): 1. An open-source tutorial for a multi-factor stock quant framework; 2. A collection of classic academic and industry materials; 3. AI + finance related work, including LLMs, agents, and benchmarks (evaluation), etc.
A mental-health LLM (LLM x Mental Health) covering pre- and post-training, dataset, evaluation, deployment and RAG, with InternLM, Qwen, Baichuan, DeepSeek, Mixtral, LLaMA and GLM series models.
An AI motion-comic production app that generates scripts, storyboards and composited video with one click, letting you quickly make motion comics on your phone.
📄 🤖 AI for medical and scientific papers
Everything for pentest. A penetration-testing knowledge base, with security methodology captured in a format executable by AI agents.
Reference implementations of MLPerf® training benchmarks
A neurosymbolic perspective on LLMs
AI Legal Assistant skill for Claude Code. Contract review, risk analysis, NDA generation, compliance auditing, negotiation strategy, and PDF reports — 14 skills, 5 parallel agents. If you want to learn how to sell this to real businesses, check out the Skool community
Bailing is a GPT-4o-like voice chat robot built on ASR + LLM + TTS, integrating excellent models like DeepSeek R1 and connecting to OpenClaw. A true personal voice assistant with latency as low as 800ms, able to run on low-spec machines like Mac, and supports interruption.
FireRedTTS3: Multilingual and Multi-Dialect Voice Cloning with Instruction-Guided Voice Design and Speech Editing
MLE-bench is a benchmark for measuring how well AI agents perform at machine learning engineering
Research and applications of NLP, knowledge graphs, dialogue systems, LLMs and related technologies.
A Codex Skill for generating dense, editable, consulting-style PowerPoint decks, supporting SCR narrative structure, style confirmation, and PPTX quality checks.
FSL-Mate: A collection of resources for few-shot learning (FSL).
Python AutoML for Trading Systems and Sports Betting