Tencent/WeKnora
WeKnora is an LLM-powered modular framework for deep document understanding, semantic retrieval, and context-aware question answering using the Retrieval-Augmented Generation paradigm.
Awesome AI Agents › Document Analytics Platforms
StarTrail-org/PixelRAG
PixelRAG is the official codebase for a paper from Berkeley SkyLab, BAIR and Berkeley NLP arguing that retrieving over rendered screenshots beats parsing documents into text. Instead of converting a web page or PDF into text chunks, the pipeline renders it into screenshot tiles and retrieves directly over the images, so tables, charts, infographics and layout that HTML parsing discards remain available to the reader model. Two components make this work: a renderer, and a Qwen3-VL embedding model fine-tuned with LoRA on screenshot data that places page images in a space where visual content is retrievable. The project is installed from PyPI and splits into a standalone pixelshot command that turns a document, page or PDF into image tiles using Playwright and the Chrome DevTools Protocol, and a pixelrag umbrella command whose stages chunk tiles, embed them, build a FAISS index, orchestrate the full ingest pipeline, and serve a FastAPI search API on CPU or GPU. Optional extras are installed per stage, and the training code is a separate project with its own pinned PyTorch and Transformers environment. A hosted endpoint serves a prebuilt index of 8.28 million Wikipedia pages without setup or an API key, accepts text or image queries, and is also reachable from a browser demo and a Colab notebook. The renderer additionally ships as a Claude Code plugin called pixelbrowse, installed from a plugin marketplace, which lets the agent screenshot a page and read the image instead of fetching raw HTML; the skill calls the local pixelshot binary directly, with no MCP server or backend involved. The project targets researchers and engineers building retrieval augmented generation over visually rich documents, and anyone who wants an agent that reads pages the way a person sees them.
https://github.com/StarTrail-org/PixelRAG
Also in Document Analytics Platforms
georgia-tech-db/evadb
EvaDB is an open-source database system that empowers developers to build AI-powered applications by integrating advanced AI models and optimizations within a SQL-based querying framework for both structured and unstructured data.
loggie-io/loggie
Loggie is a lightweight, cloud-native data transfer agent and aggregator designed for scalable, high-performance log collection, processing, and monitoring in Kubernetes environments.
johnsonhk88/AI-Bank-Statement-Document-Automation-By-LLM-And-Personal-Finanical-Analysis-Prediction
A full-stack pipeline that parses bank statement PDFs with layout detection, OCR and LLMs, then runs CrewAI, LangChain Deep Agents and Hermes agent harnesses over the extracted data for categorisation, analysis and RAG querying.
netboxlabs/pktvisor
pktvisor is a dynamic network observability agent that analyzes high volume network traffic and generates opentelemetry metrics for real-time and centralized monitoring.
genomoncology/FuzzTypes
FuzzTypes is a Pydantic extension that provides autocorrecting annotation types for enhanced data validation and normalization, enabling automatic correction and structured data composition in Python applications.