Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

A super fast Graph Database uses GraphBLAS under the hood for its sparse adjacency matrix graph representation. Our goal is to provide the best Knowledge Graph for LLM (GraphRAG).

A universal sandbox platform for AI application scenarios, providing multi-language SDKs, unified sandbox protocols, and sandbox runtimes for LLM-related capabilities.

Implement a reasoning LLM in PyTorch from scratch, step by step

Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models

A Claude Code plugin that automatically captures everything Claude does during your coding sessions, compresses it with AI (using Claude's agent-sdk), and injects relevant context back into future …

EAFT(Entropy-Adaptive Fine-Tuning: Resolving Confident Conflicts to Mitigate Forgetting) official repo

📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG

🕷️ An undetectable, powerful, flexible, high-performance Python library to make Web Scraping Easy and Effortless as it should be!

All parts of Claude Code's system prompt, 20 builtin tool descriptions, sub agent prompts (Plan/Explore/Task), utility prompts (CLAUDE.md, compact, statusline, magic docs, WebFetch, Bash cmd, secur…

"DeepCode: Open Agentic Coding (Paper2Code & Text2Web & Text2Backend)"

mcp-use is the easiest way to interact with mcp servers with custom agents

"DeepTutor: AI-Powered Personalized Learning Assistant"

Get your documents ready for gen AI

The terminal agent that unites all model providers for developers.

Get 10X more out of Claude Code, Codex or any coding agent

A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.

Multilingual Document Layout Parsing in a Single Vision-Language Model

Open-source framework for conversational voice AI agents

The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SAM 3), links for downloading the trained model checkpoints, and example notebooks that sho…

SWE-bench: Can Language Models Resolve Real-world Github Issues?

AI 基础知识 - GPU 架构、CUDA 编程、大模型基础及AI Agent 相关知识

The official repo for “Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting”, ACL, 2025.

SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2024]