Scanopy vs txtai

Scanopy discovers and documents network hosts, services, and topology from scans. It produces Physical (L2), Logical (L3), Workloads, and Applications views, then refreshes documentation on a schedule rather than continuously polling. Discovery uses a single daemon on the network, with no agents required on individual endpoints. Listed integrations include Docker, Podman, Instant On, UniFi Controller, gNMI, and SNMP; Instant On and gNMI are marked beta. Depending on the plan, diagrams and data can be exported or shared in formats including PNG, SVG, HTML, PDF, Mermaid, Confluence, and CSV. API access is listed for paid plans, and the API has a limit of 300 requests per minute. The self-hosted, open-source Community Edition has no time restriction and is limited to one network and one seat. Paid plans start at $11.99 a month billed yearly. Scanopy documents assets and connections, but is not a replacement for monitoring device health, bandwidth, or alerts.

txtai is an open-source framework for semantic search, language-model orchestration, and language-model workflows. Its embeddings database brings together sparse and dense vector indexes, graph networks, and relational databases. It supports vector search with SQL, object storage, topic modeling, graph analysis, and multimodal indexing, and can create embeddings from text, documents, audio, images, and video. Pipelines cover prompts, question answering, labeling, transcription, translation, and summarization; workflows combine pipelines with business logic, while agents can coordinate embeddings, pipelines, workflows, and other agents. Web and Model Context Protocol APIs are available, alongside JavaScript, Java, Rust, and Go bindings. txtai can run locally or be deployed on a server, cluster, or serverless environment. Install with pip or use Docker; Python 3.11 or later is supported. The software is free under the Apache 2.0 license. The API is open over HTTP by default, with HTTPS and token authorization options documented.