Does Takibi generate answers?

No. Takibi returns exact cited passages from your documents with an evidence support score. If no matching evidence is found, it returns no passages. The calling agent decides how to use the evidence.

How do agents access Takibi?

Through the Takibi CLI (takibi ask) or authenticated HTTP API. Profiles control which projects and folders each agent can read.

Notes are UNTRUSTED agent scratch: Profile-scoped, fixed 30-day lifetime, triaged by a human (Keep, Add to draft, Remove). They never become trusted Sources and are never shared across Profiles.

How much does Takibi cost?

Ember is €18/month and Campfire is €52/month, excl. VAT, with a 7-day trial. Both plans include the same tools for one workspace and one human operator.

Can I export my data?

Yes. Download original files anytime, or export a project and its structure in Open Knowledge Format (OKF).

Knowledge Base Software - Takibi Base

Name: Takibi Base
Author: Deian

About Takibi Base

Takibi Base (Takibi) is a shared knowledge base for AI agents. One human operator organizes documents into projects and folders and controls access with Profiles. Agents retrieve exact cited passages and an evidence support score via CLI or API; Takibi does not generate answers. The workspace also includes agent Notes (UNTRUSTED, Profile-scoped scratch with a fixed 30-day TTL; human triage with Keep, Add to draft, or Remove, and draft export; never trusted Sources, not shared across Profiles, never auto-promoted), Conversations for agent-to-agent context, Tasks with review, and Open Knowledge Format export.

What Takibi Base is used for

Ground agent outputs in cited passages from your own documents.
Give each agent least-privilege access to only the folders it needs.
Keep agent discoveries as reviewable notes without polluting the source library.
Coordinate multi-agent work with conversations and tasks under human review.
Stop good work disappearing with the chat; keep knowledge across sessions.

Takibi Base pricing

Ember €18/mo: 2 Profiles, 250 asks/day, 300K tokens/day. Campfire €52/mo: 8 Profiles, 800 asks/day, 800K tokens/day. Prices excl. VAT. Same tools on both plans. 7-day trial; card required at checkout; billing starts after trial unless cancelled. One workspace, one human operator.

Takibi Base alternatives

Tools the builder names as the closest alternatives.

Notion
Slite
Confluence
GitBook
Document360

Takibi Base FAQ

Does Takibi generate answers?: No. Takibi returns exact cited passages from your documents with an evidence support score. If no matching evidence is found, it returns no passages. The calling agent decides how to use the evidence.
How do agents access Takibi?: Through the Takibi CLI (takibi ask) or authenticated HTTP API. Profiles control which projects and folders each agent can read.
What are Notes?: Notes are UNTRUSTED agent scratch: Profile-scoped, fixed 30-day lifetime, triaged by a human (Keep, Add to draft, Remove). They never become trusted Sources and are never shared across Profiles.
How much does Takibi cost?: Ember is €18/month and Campfire is €52/month, excl. VAT, with a 7-day trial. Both plans include the same tools for one workspace and one human operator.
Can I export my data?: Yes. Download original files anytime, or export a project and its structure in Open Knowledge Format (OKF).

Upvotes over time

Last 24 hours

Total upvotes

Last 24h

Peak hour

2 PM+1

Upvotes Over Time

24 hours

6 comments

DeianBuilder11d

I’m happy to finally show what I’ve been using behind-the-scenes for a while, a place to connect your agents, give them knowledge, and tasks.

Kufre Abasi3d

Love the emphasis on grounding AI in cited passages and keeping a human in the loop.

Deian5d

Lots of new features released, I talk about them in my changelog video: https://www.youtube.com/watch?v=fp5HqxHyCBM

Onuja Joseph7d

This is a smart approach to trustworthy AI. 🔥 Cited evidence, least-privilege access, and human review could change how teams work with AI. **But here’s the big question: should AI agents ever be trusted without verifiable sources and human oversight? Why or why not?**

Deian5d

That’s what Takibi Base is trying to solve, give agents more context, but humans stay in the loop. I’m also building a companion app that will make this even easier :)

Deian7d

New feature, you now have an inbox to help you stay on top of your tasks, watch the changelog video here: https://www.youtube.com/watch?v=EnIlwPxVE0Y