Skip to main content
The knowledge base is a wiki-style brain for each workspace. It holds interlinked pages auto-generated from your repositories, so your AI team always answers with real context about your code, not guesses. Everything is built and searched on your machine. No cloud, no telemetry.

Wiki pages

Structured pages describing modules, flows, and decisions in your workspace.

Wikilinks + graph

Pages link to each other, forming a navigable graph of your project.

Local RAG

BM25 lexical search plus on-device embeddings retrieve the right page.

Agents that learn

Agents read the KB before acting and write learnings back to it.

​
What the knowledge base is

Each workspace gets its own knowledge base, a private wiki that lives next to your repositories in ~/.orkestral. It captures what your codebase is and how it works, in plain language, so that both you and the agents can reason about the project quickly. Think of it as institutional memory: instead of re-reading every file on every request, the team consults a curated set of pages that summarize architecture, conventions, and past decisions. A knowledge base is made of pages. Each page covers one idea, a module, a service, a data flow, a convention, or a decision.
1

Pages

Every page has a title and a body. Pages describe a concrete part of your workspace and stay focused on a single topic.
2

Wikilinks

Pages reference each other with wikilinks. When one concept depends on another, a link connects them so you can follow the thread.
3

Graph view

The graph view renders every page as a node and every wikilink as an edge. Use it to see clusters, find orphaned topics, and understand how your project hangs together.
Follow wikilinks the way you would in any wiki. Start from a high-level page and drill down into the modules it mentions.

​
How it is built from your repos

The knowledge base is generated from the repositories in your workspace, then made searchable with a hybrid retrieval engine, all running locally.
On-device embeddings capture meaning, not just keywords. They retrieve pages that are conceptually related even when the wording differs. Combined with BM25, this is retrieval-augmented generation (RAG) running entirely on your hardware.
Indexing and search happen on your machine. Your code never leaves your device to populate or query the knowledge base.
The hybrid approach matters: BM25 nails exact identifiers, while embeddings catch the “what is the thing that does X?” questions. Together they surface the most relevant page for each query.

​
How the agents use it

The knowledge base is wired into the team’s workflow, not a side feature.

Consult before answering

Before an agent plans or writes code, it retrieves the most relevant pages so its answer is grounded in your actual project.

Write learnings back

As the team works through issues and reviews, new understanding gets written back to the KB, so the brain keeps improving.
This creates a loop: the more your team works in a workspace, the richer its knowledge base becomes, and the better grounded every future answer is.
Knowledge bases are per workspace. Switching workspaces switches the brain, pages and graph from one workspace do not bleed into another.

​
Next steps

Agent team

See how the CEO and specialists delegate work and consult the KB.

Workspaces

Learn how repositories map to a workspace and its knowledge base.