A settled choice the team has committed to.
Assistants that remember how your team works.
kumbuka is an open-source team memory system for AI assistants. It gives your team one durable, shared place for the decisions, conventions, and constraints an assistant should carry across every session — served to Claude and any MCP-capable client over a single endpoint.
Every session starts from zero.
AI assistants are stateless between conversations. So teams re-explain the same context forever — and when it comes back inconsistently, the work drifts.
“We use Postgres as the system of record.”
“Money is integer minor units, never floats.”
“Service names are kebab-case.”
Read at the start. Written back through one endpoint.
kumbuka serves work-steering knowledge — rules and decisions, not a copy of your docs or source. The assistant reads it; the team curates it.
Recall
At session start, the assistant loads your team’s steering knowledge for the scopes it’s working in.
Apply
It works against your decisions and constraints as it goes — no one has to re-explain them.
Curate
New decisions are written back, then reviewed and refined by the team in the admin console.
↻ One loop, one endpoint — memory_remembermemory_recallmemory_forgetmemory_scopesmemory_load_context
One member decides. The whole team remembers.
Watch how a decision made in one chat reaches a teammate in another — without anyone re-explaining a thing.
Shared, typed, team-owned.
Six kinds of knowledge.
Every entry is typed, so the assistant and the team always know what they’re looking at.
A shared default way of doing things.
A hard boundary that must not be crossed.
Unresolved — needs an owner and an answer.
A term defined so everyone means the same thing.
The current state of something in motion.
Three scopes. One boundary that holds.
Memory is organised into scopes, so the right knowledge reaches the right people — and nothing else does.
A per-user space, owned by you and reachable only by you. Your working notes never leak into the team’s view.
Owner-onlyShared spaces a team curates together — the decisions and conventions for a service, product, or area of work. Perfect for Projects in Claude and ChatGPT.
Team-sharedOne org-wide baseline everyone inherits — the conventions and constraints that hold across every project.
One, org-widePrivate means private. Enforced, not configured.
A member’s private scope is owned by them and reachable only by them — only through the MCP surface, under their own session.
No admin, no console screen, and no team-facing API can read it.
It’s enforced at the data-access layer — not by a configuration toggle that could be flipped. Disabling a user leaves their private memory untouched and theirs.
Self-hosted. Open source. One Compose stack.
A single Docker Compose stack you run yourself. No accounts to create, no data leaving your control.
https://mcp.kumbuka.ai/mcp
Works with claude.ai and any MCP-capable client.
Curate it together.
The admin console is where the team reviews, edits, and organises shared memory — the human side of the same endpoint the assistant reads.
Memory for teams that keep control of their decisions.
Join the public beta and help shape how kumbuka evolves. We’re looking for early adopters who care about governance, durability, and team ownership.
- We’re in beta — and listening.
- Shape the roadmap with us.
- A partnership, not a sign-up — come build with us.
Thank you.
We’ll review your request and reach out within 3 business days.
Give your assistants a memory your team owns.
Self-host kumbuka, point your assistant at the endpoint, and stop re-explaining your team.