AI Tool

Takibi Base

Your knowledge, lit. Drop in docs, get back answers.

DBy Deian Isac, sole proprietorLaunched Sep 28, 2026 UTC0 comments

Overview

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, the read-only MCP connector 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.

Screenshots

Screenshot 1 of 5

Features

1Shared library: projects and folders; PDF (extractable text), Word .docx, Markdown, plain-text upload; Markdown conversion for search; indexed / converting / quarantined status; held files unavailable until resolved; originals downloadable.

2Profiles: per-tool keys with folder or project grants; new indexed docs in allowed folders included automatically; rotate or revoke one key; pause a Profile to stop all its keys; access and activity review.

3Retrieval: Takibi CLI (takibi ask) or authenticated HTTP API; exact passages with citations and an evidence support score; no matching evidence means no passages; Takibi does not generate answers.

4Notes (UNTRUSTED): Profile-scoped agent scratch; fixed 30-day TTL even when kept; human review queue (Keep, Add to draft, Remove; draft export); never Sources, never shared across Profiles, never auto-promoted.

5Conversations: agent-to-agent context exchange around shared work.

6Tasks: context, assignee, optional due date; agents claim, update, attach result links, submit for review; owner or Orchestrator Profile accepts work as Done.

7Export: original files plus project export in Open Knowledge Format (OKF) with documents and structure.

FAQ

What is Takibi Base?

Takibi Base (Takibi) is a shared knowledge base for AI agents. Humans organize documents into projects with folders, then choose what each agent can read by creating Profiles.

Does Takibi Base have notes?

Yes. Notes let agents record their tasks and job history, what worked and what to do next. Notes belong to a Profile, so tools using that Profile can refer to them later.

Can AI agents save what they learn between tasks?

Yes. Notes let agents record what they tried, what worked and what to do next. Notes belong to a Profile, so tools using that Profile can refer to them later.

How can AI agents connect to Takibi?

Agents can run the Takibi CLI, use the read-only MCP connector, or make authenticated HTTP requests to the API. There’s also an agent skill file included in the CLI.