Lists (1)
Stars
Memory Sparse Attention - A scalable, end-to-end trainable latent-memory framework for 100M-token contexts.
Autonomous Agents (LLMs) research papers. Updated Daily.
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
A next.js web application that integrates AI capabilities with draw.io diagrams. This app allows you to create, modify, and enhance diagrams through natural language commands and AI-assisted visual…
Completed research on semantic retrieval augmented generation through novel semantic similarity graph traversal algorithms.
Mirage Persistent Kernel: Compiling LLMs into a MegaKernel
Open Lakehouse Format for Multimodal AI. Convert from Parquet in 2 lines of code for 100x faster random access, vector index, and data versioning. Compatible with Pandas, DuckDB, Polars, Pyarrow, a…
Context7 Platform -- Up-to-date code documentation for LLMs and AI code editors
Modeling, training, eval, and inference code for OLMo
Official code repo for the O'Reilly Book - "Hands-On Large Language Models"
Fast block-level file diffs (e.g. for VM disk images) using CoW filesystem metadata
LMCache: Supercharge Your LLM with the Fastest KV Cache Layer
AI-Native Risk Intelligence Systems, OpenDeRisk——Your application system risk intelligent manager provides 7* 24-hour comprehensive and in-depth protection.
[AAAI 2025] Open-source, End-to-end, Medical Image Segmentation model by Task allociation.
Official Core Services for MemFuse - the lightning-fast open-source memory layer that gives LLMs persistent, queryable memory across conversations and sessions.
Repository hosting code for "Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations" (https://arxiv.org/abs/2402.17152).
This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. Each technique has a detailed notebook tutorial.
Qwen2.5-Omni is an end-to-end multimodal model by Qwen team at Alibaba Cloud, capable of understanding text, audio, vision, video, and performing real-time speech generation.
Official Implementation of "KBLaM: Knowledge Base augmented Language Model"
Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.
Eko (Eko Keeps Operating) - Build Production-ready Agentic Workflow with Natural Language - eko.fellou.ai
[ICML 2024] LLMCompiler: An LLM Compiler for Parallel Function Calling
Apache GeaFlow: A Streaming Graph Computing Engine.
Qwen GRPO Graph Extraction RL Finetune
Cost-efficient and pluggable Infrastructure components for GenAI inference
The RL Bridge for LLM-based Agent Applications. Made Simple & Flexible.
Lyric: A Rust-powered secure runtime for AI-Agent.
Chat2Graph: Graph Native Agentic System.