Python

DeepInfer: High-performance, large-scale inference framework for DeepSeek models

Why your local LLM feels dumber than it is

GitHub - roboflow/supervision: We create your reusable computer vision tools. 💜

GitHub - chiennv2000/orthrus: Fast, lossless LLM inference via dual-view diffusion...

GitHub - openai/privacy-filter: OpenAI Privacy Filter

GitHub - arman-bd/guppylm: A ~9M parameter LLM that talks like a small fish.

GitHub - microsoft/VibeVoice: Open-Source Voice AI

GitHub - karpathy/autoresearch: AI agents automatically conducting research on single-GPU nanochat training

GitHub - Pinperepette/snakebite: Detect malicious PyPI packages using heuristic analysis and LLM-powered filtering to uncover credentials

GitHub - 666ghj/MiroFish: A Simple and Universal Swarm Intelligence Engine, Predicting Anything. A concise and universal swarm intelligence engine, predicting everything.

GitHub - jundot/omlx: LLM inference server with continuous batching and SSD caching for Apple Silicon — managed from the Mac

GitHub - NousResearch/hermes-agent: The agent that grows with you

GitHub - bytedance/deer-flow: An open-source SuperAgent framework that researches, codes, and creates. With the help of sandboxes,

GitHub - z-lab/paroquant: [ICLR 2026] ParoQuant: Pairwise Rotation Quantization for Efficient Reasoning in Large Language Model Inference

GitHub - zai-org/GLM-OCR: GLM-OCR: Accurate × Fast × Comprehensive

GitHub - alexziskind1/llama-throughput-lab: Interactive launcher and benchmarking framework for llama.cpp server throughput, featuring tests, sweeps, and round-robin load tools.

GitHub - aiming-lab/SimpleMem: SimpleMem: Efficient Lifelong Memory for LLM Agents

GitHub - virattt/ai-hedge-fund: An AI Hedge Fund Team

GitHub - google/langextract: A Python library for extracting structured information from unstructured text using large language models (LLMs) with precision.

GitHub - microsoft/VibeVoice: Open-Source Voice AI

GitHub - GVCLab/PersonaLive: PersonaLive! : Expressive Portrait Image Animation for Live Streaming

GitHub - NevaMind-AI/memU: Memory infrastructure for large language models and AI agents

GitHub - yichuan-w/LEANN: RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal device.

GitHub - Tencent-Hunyuan/HunyuanOCR

GitHub - pixeltable/pixeltable: Pixeltable — Data Infrastructure providing a declarative, incremental approach for multimodal AI workloads

GitHub - GibsonAI/Memori: Open-Source Memory Engine for LLMs, AI Agents & Multi-Agent Systems

GitHub - rbalestr-lab/lejepa

Context Retrieval for AI Agents across Apps & Databases

DeepSeek-OCR

Airbyte: The Leading Data Integration Platform for ETL/ELT Pipelines

Enterprise Deep Research

Make Any App Searchable for AI Agents

Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting

nanochat

ROMA: Recursive Open Meta-Agents

NeuTTS Air

Cua: Open-source infrastructure for Computer-Use Agents

RAG-Anything: All-in-One RAG Framework

RAGLight

Turns Codebase into Easy Tutorial with AI

AI-Researcher: Autonomous Scientific Innovation

AgenticSeek: Private, Local Manus Alternative

Qwen-Image

Introducing Tongyi Deep Research

💾🎉 copyparty

MemoRAG: Moving Towards Next-Gen RAG Via Memory-Inspired Knowledge Discovery

Enable AI to control your browser 🤖

dots.ocr: Multilingual Document Layout Parsing in a Single Vision-Language Model

PaddleOCR

SurfSense

LoRAX: Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs

The LLM Red Teaming Framework

Memvid

Elysia: Agentic Framework Powered by Decision Trees

LangExtract

Litestar is worth a look

SymbolicAI: A neuro-symbolic perspective on LLMs

Agent Development Kit (ADK)

Show HN: My LLM CLI tool can run tools now, from Python code or plugins