Skip to main content
Knowledge Stack
Build production-ready AI agents in under 1 hour. Knowledge Stack turns a pile of documents into an AI-ready knowledge base — drop in PDFs, DOCX, PPTX, Markdown, or plaintext and get back a hierarchical, multi-tenant, permission-aware corpus with semantic search, streaming chat, and workflow-driven ingestion behind a single REST API.

Knowledge Stack in 90 seconds — ingest, search, chat, cite.

Watch the tour

Five short videos — ingestion, agents, citations, RBAC.

Book a demo

30 minutes on your own corpus with a founding engineer.

Quickstart

First ingest + search call in under five minutes.

Pick your client

Install the CLI

uv tool install kscli — ingest, search, watch workflows from the terminal.

Python & TypeScript SDKs

pip install ksapi · npm install @knowledge-stack/ksapi — fully typed.

MCP server

Drop into LangGraph, Claude Desktop, Cursor, or any MCP-compatible host.

Cookbook

Runnable recipes — RAG, citations, bulk ingest, evals, agent workflows.

API Reference

Every endpoint, request, and response — generated from openapi.yaml.

Architecture

How ingestion, search, threads, and Temporal fit together.

Install in 30 seconds

Your first call

Ingest a document and run a semantic search. Pick your tool — every example targets the same endpoints.

What you can build

See it in action

Knowledge Stack ships a reference workspace UI so your team (and your customers) can ingest, search, and chat without writing a single line of frontend code.
Knowledge Stack workspace home with sidebar of chats and files

The Knowledge Stack workspace — chat history, project file tree, search, and a single composer for ingest + chat.

Knowledge Stack chat showing inline citations on each fact in a SCADA report summary

Every assistant response carries grounded numeric citations that link back to the exact source chunk and page.

Built-in citations are a core primitive — not a bolt-on. See the Citations guide for the SSE event shape, how to render badges, and how to resolve a citation back to its bounding box on the PDF.

How the system fits together

Read the full picture in Architecture. Key concepts: the path system (everything is a node in a Unix-style tree), authentication (cookie or API key), and authorization (path-level grants).

Where to next

Quickstart

First ingest + search

Architecture

System overview

Path system

How content is organized

Ingestion pipeline

Conversion, chunking, embedding

Semantic search

Dense, full-text, hybrid

Threads & streaming

Chat with citations

Talk to us

Book a demo

Walk through Knowledge Stack on your own data with a founding engineer.

Contact sales

Pricing, enterprise SSO, on-prem, and procurement questions.