Docmost

Knowledge graph-powered RAG framework from HKU

LightRAG is a research-backed RAG framework from Hong Kong University that combines knowledge graph structures with vector search for more contextual retrieval. Published at EMNLP 2025, it extracts entities and relationships from documents to build a structured knowledge graph, then uses dual-level retrieval across both graph and vector representations with five query modes: naive, local, global, hybrid, and mix.

Mozilla-backed browser infrastructure for AI agents

Tabstack is Mozilla's browser infrastructure service for AI agents, providing clean markdown extraction, structured JSON data, and automated browser actions through a fast API. With two-tier fetch escalation that achieves sub-600ms latency for static pages, robots.txt compliance, and ephemeral data handling, it offers an ethical alternative to aggressive web scraping tools — complete with an MCP server for Claude and Cursor integration.

Browser automation framework turning websites into action APIs

Notte is a browser automation framework for AI agents that converts any website into a structured action API. Instead of scraping pages for text, Notte lets agents interact with sites — clicking buttons, filling forms, and navigating flows. Built with hybrid AI-plus-deterministic scripting, it includes digital personas, CAPTCHA solving, and proxy management for reliable automation at scale.

Heterogeneous CPU-GPU inference and SFT for large MoE models

Open-source framework for running and fine-tuning large Mixture-of-Experts models with heterogeneous CPU-GPU execution, optimized kernels, limited VRAM and SGLang or LLaMA-Factory integrations.

Official Kubernetes and Helm reference stack built on the vLLM inference engine

Official vLLM reference implementation for scaling the existing inference engine on Kubernetes with Helm, request routing, KV-cache offload, autoscaling and Prometheus/Grafana observability.

Distributed inference orchestration above vLLM, SGLang and TensorRT-LLM

Open-source, datacenter-scale orchestration layer that coordinates vLLM, SGLang and TensorRT-LLM across nodes with disaggregated serving, KV-aware routing, multi-tier cache management and automatic scaling.

Open-source GPU control plane for scalable AI model serving

Open-source GPU cluster manager that configures vLLM, SGLang, TensorRT-LLM or custom engines, serves models through compatible APIs, and provisions SSH-accessible GPU instances across on-premises, Kubernetes and cloud environments.

Disaggregated KV cache storage and transfer for LLM serving

Open-source infrastructure for disaggregated LLM serving that pools KV caches across prefill and decode workers, with high-performance transfer, distributed storage and integrations for vLLM and SGLang.

Reusable KV cache infrastructure for scalable LLM inference

Open-source KV cache management layer that persists, offloads and reuses model key-value caches across requests and serving engines to reduce repeated prefill work and improve inference throughput.