Product updates, research, and ideas for building better agents.
We built Knowhere as a memory layer between complex, messy documents and AI agents. Rather than stopping at text extraction, it converts documents into structured memory that can be updated and reused.
Instead of aggressively converting every document into stripped-down text chunks, keep the original visual pages intact so the AI agent can inspect the actual layout, check figures against the source, and provide verifiable evidence.
Knowhere Notebook and MCP let agents in Cursor, Claude, and Codex search a shared cloud document Brain.
Marker v2, MarkItDown, MinerU 4.0 and Knowhere compared for agentic RAG: structure, tables, citations, MCP access, self-hosting, license and price.
Instead of extracting text, VISION-MAP understands, organizes, and annotates pages. The agent sees the original page, not a lossy stand-in.
This release does two things. VISION-MAP and text parsing now run together as dual-track parsing, so more of those messy files can land in an agent’s knowledge base. Retrieval also changed: the agent decides where to look, and what to read next.
