Kumbuka
Serves team-ratified decisions, conventions and constraints to AI assistants over a single MCP endpoint, with human curation.
not read yet
Use
- For
- Teams using Claude or MCP-capable assistants who want ratified decisions and conventions applied consistently.
- Price
- Price not read
- App
- iPhone & iPad · 0★ from 0 ratingscurrent version 2026-10-07 ↗
- Activity
- Actively maintainedrelease 7 days ago
- Company
- Domain since 2026domain registered
- Runs as
- Self-hosted
- Keep AI assistants aligned with team decisions across chats
- Curate shared decisions and conventions in an admin console
- Avoid re-explaining settled choices at the start of each session
- Domain since2026domain registered
- MCP serverai.kumbuka/kumbuka-serververified in the MCP registry
- Stateanswers, requires sign-inchecked 2026-10-13
- Address to connectmcp.kumbuka.ai/mcp
Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.
Figure and bar: visits/mo, estimate · year: online since
- #1
GBrain
Shared workspace where teams prompt multiple AI assistants together with persistent memory and tool integrations.
283ActiveFrom $199/mo - #2
Byterover
Stores and syncs project context across AI agents and team members with access control and source attribution.
137not readFrom $15/mo - #3
Pactto
Persistent shared workspace for creative teams to present, review, and approve assets with AI-assisted live editing and decision tracking.
102ActiveFrom $19/mo - #4
MemoryRouterMCP · open
Stores your preferences and project context and passes it between ChatGPT, Claude and other AI tools via an MCP connector.
14ActiveFrom $20/mo2026 - #5
BaseThreadMCP · sign-in
Syncs a team's decisions, tasks and project context between each member's local AI tools through a cloud graph that every tool reads and writes.
5ActiveFrom $5/user/mo - #6
ContextForge Memory
Stores and retrieves project context across Claude, Cursor, Copilot via MCP server with semantic search.
1ActiveFrom $9/mo
What is Kumbuka?
Serves team-ratified decisions, conventions and constraints to AI assistants over a single MCP endpoint, with human curation. It is listed in the Atlas under Productivity.
Who is Kumbuka for?
Teams using Claude or MCP-capable assistants who want ratified decisions and conventions applied consistently.
Do people use Kumbuka?
Little sign of use.
Is Kumbuka still maintained?
Actively maintained: release 7 days ago.
Does Kumbuka have an iPhone app?
Yes: “Kumbuka - Card Scanner” on the App Store, rated 0 from 0 ratings; current version released 2026-10-07.
What are alternatives to Kumbuka?
In Productivity, by use: GBrain, Byterover, Pactto, MemoryRouter, BaseThread, ContextForge Memory.
Not quite it? Describe the job
betaFive tools from the Atlas that fit it, each judged against what you wrote.
How we read a tool
No votes, no reviews, no vendor claims. Every week a crawler reads each tool's own site and a few public registries, and the words on the card are bands over what it read.
- Use: visits to the site (estimated), installs from npm and PyPI, presence in Chrome's usage report.
- Activity: the newest release on GitHub, npm or PyPI; the newest dated page on the site; open roles on a public jobs board.
- Price: the vendor's own pricing page, read with the date. A figure is printed only when it is on that page.
- The line and the use cases are written by us from the homepage, one tool at a time, and refused when they repeat the vendor's marketing.
How AI assistants read each site — the reading vendors ask us about — is on each tool's own visibility page.