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
netboxlabs/pktvisor
pktvisor is a dynamic network observability agent designed to analyze high volume and information-dense network data streams. It extracts actionable insights directly from the network edge and integrates seamlessly with modern observability stacks such as Prometheus and Grafana. The agent is resource-efficient, modular, and can be dynamically controlled in real-time through API and YAML policies. It supports dynamic loading of input and analyzer modules at runtime, allowing flexible and adaptive network monitoring. The input stream system of pktvisor supports various data taps including packet capture, dnstap, sFlow, Netflow, and IPFIX, with plans to support additional taps like envoy taps and eBPF. The stream analyzer system performs full application layer analysis and efficiently summarizes data into counters, histograms, quantiles, timers, rates, heavy hitters, set cardinality, and GeoIP/ASN information. pktvisor originated from the need to observe critical internet infrastructure for purposes such as DDoS protection, traffic engineering, and ongoing network operations. It provides both localized, hyper real-time visualization through a command line UI and centralized visualization through integration with industry-standard observability tools. The project offers multiple deployment options including Docker containers, Linux static binaries, and AppImage for easy installation and use. It supports running without root privileges by setting appropriate capabilities on the binary. The project is actively maintained with build status, code scanning, and code coverage badges indicating a focus on quality and security. Overall, pktvisor is a powerful and flexible tool for network observability, providing detailed insights and metrics from network traffic to support network management and security operations.
https://github.com/netboxlabs/pktvisor
Also in Document Analytics Platforms
StarTrail-org/PixelRAG
Visual retrieval-augmented generation pipeline that renders web pages, PDFs and images to screenshot tiles and retrieves over them with a LoRA-tuned Qwen3-VL embedding model.
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.
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.