What Is Takibi Base?

Takibi Base is a shared knowledge base for AI agents. You upload documents into projects and folders, and agents query them through a CLI or API to get back exact cited passages rather than generated summaries. It fits teams that need agents to answer from their own documents with verifiable sources, and that want to scope what each tool can read.

How it works

The core idea is that your agent doesn't get your whole document set. It gets passages that match a question, plus a citation for each one.

  1. Add documents — upload files into projects and folders. Takibi converts them to Markdown so agents can search them.
  2. Choose access — a Profile holds a tool's keys and document permissions. You select which folders that Profile can read.
  3. Ask questions — the tool queries through the CLI or API. Takibi searches only those sources and returns matching passages with citations.

You can also download the original files or extract their text again, and check which files are indexed, converting, or quarantined. Projects can be exported in Open Knowledge Format (OKF).

What a response looks like

A CLI query returns structured output, not prose. From the sample workspace:

$ takibi ask -q "What is our refund policy?" --json

The response includes:

Field Meaning
spans The matched passage text, with document ID, name, chunk ID, and title
citations The same document/chunk references, for citing the source
support An evidence support score (0.4 in the sample)
abstained Whether Takibi declined to answer
candidateCount How many candidates were considered
conflict Whether retrieved evidence conflicts

In the example, the passage returned is: "Customers may request a refund within 30 days of purchase." — attributed to refunds.md, section "Eligibility". The agent gets the source text and a citation for each passage.

If Takibi finds no matching evidence, it returns no passages. That abstention behavior matters if you're building agents that shouldn't guess.

Access control through Profiles

A Profile holds the access permissions for its keys. Every key in a Profile uses the same permissions, so create separate Profiles for tools that need different access.

To scope a Profile:

  1. Open the Profile's Access tab and choose Edit.
  2. Select the folders it should be able to read.

Two scope levels behave differently:

  • Folder access includes documents you add later, once they are indexed.
  • Project access also includes future folders and documents outside folders. Takibi asks you to confirm this broader access.

What to check before committing

  • Workspace requirement. Uploads, imports, downloads, and billing require your own workspace. The sample workspace is for trying things out — edits reset on refresh.
  • Pricing. A pricing page exists at takibibase.com/pricing, but the available material doesn't state amounts or plan details, so check it directly.
  • Fit. If your agents need to cite exact passages from your own documents and you want per-tool read scoping, this matches that need. If you need agents to synthesize across sources rather than return evidence, the passage-and-citation model is a different shape.
takibibase.com
Shared knowledge base for AI agents. Organize documents into projects and folders, control access with Profiles, and return exact cited passages via …