livingbrain.wiki

How it works

Listen. Write. Evolve.

Living Brain reads your team's conversations, writes what it learns as a Markdown wiki with sources, and keeps that wiki true. All of it is planned; the examples are sample data.

Speaks up

It answers before anyone has to dig.

Living Brain listens in the team chat channels you invite it to, in Slack or Discord. When a question already has an answer, it replies in the thread and links to the exact message the answer came from.

# eng Slack shown · Illustration
Dev Patel09:51

Rolling back #412. The 502s on /api/routes come from the new pool config.

12 more messages
Sam Ito10:04

is prod down? Northwind says routes won't load

Living BrainAPP10:04unprompted

Not down. routes-api returned 502s from 09:38 to 09:52 after deploy #412. Dev rolled it back at 09:51 and error rates have been normal since.

↩ #eng · Dev Patel · 09:51 [[Route Optimizer]]

Three steps, end to end.

01Listen

It reads the channels it's invited to and picks out the people, projects, decisions and customers in them.

02Write

Conversations become Markdown pages with [[backlinks]]. Every fact cites the message it came from.

03Evolve

On its own schedule it merges duplicates, flags contradictions, retires stale facts and rewrites summaries.

LISTEN WRITE EVOLVE #eng #sales #support living brain billing.md billing-v2 billing-v2
Illustration · the pipeline, end to end

A wiki that keeps itself true.

Every night the brain revisits what it knows.

BILLING-V2.MD · OWNER
Dev Patel · since Jan 08
Lina Haas · since Mar 12 [^1]
[1] #product · Tomás Reyes · Mar 12 · 11:20
Observe Summarize Reconcile Learn EVERY NIGHT

One night in the brain.

While the team is offline it reads what happened, tidies what it knows and hands work to agents. It also scans new research papers, news and releases about your stack, and notes how they could apply to your projects. By morning there's a digest waiting.

Sample data
  1. 22:40
    Read 214 new messages

    across 9 channels

  2. 23:15
    Merged 4 duplicate pages

    billing.md folded into billing-v2.md, and 3 more

  3. 01:30
    Resolved 3 contradictions

    Billing v2 ship date, PG16 window, Bluepeak contact

  4. 03:05
    An agent opened PR #218

    "Set routes-api pool size back to 20", waiting for Dev's review

  5. 07:00
    Wrote the morning digest

    emailed to 12 people, each in the format they prefer

See how it thinks

Explore a sample brain.

This is Kestrel Freight, a fictional 20-person logistics company. Drag to orbit, scroll or pinch to zoom, and click any node to open its page.

Maya OkaforDev PatelLina HaasTomás ReyesSam ItoBilling v2Route OptimizerPostgres 16 migrationDriver appNo deploys on FridaysMove to Postgres 16Sunset v1 APINorthwind GrocersAlder & FinchBluepeak Logistics Illustration · Sample data

Static view · click a node or use the list below

Jump to a page

It acts, and it learns.

Planned

Acts in your tools

Opens the issue, reads the PR, sends the email digest, and hands bigger jobs to a sandboxed agent that returns a pull request. How that works

Learns your way

The learning layer notices how each person likes answers, short or detailed, in threads or DMs, and adapts week by week, so its answers improve every week. It learns from agent sessions too

You own it

Your brain is a folder of Markdown.

Read it, edit it, version it, move it. Your knowledge isn't locked in a black-box vector store. Planned: keep it in your own git repo, where the Living Brain GitHub App proposes every change as a pull request and edits you merge flow back in.

brain/projects/billing-v2.mdMarkdown
---
type: project
owner: [[Lina Haas]]
ships: 2026-04-30
updated: 2026-03-13 by living-brain
---
# Billing v2
Usage-based invoices for fleet customers.
Owned by [[Lina Haas]] since Mar 12. [^1]
## Waiting on it
- [[Alder & Finch]]
- [[Northwind Grocers]]
[^1]: #product · Tomás Reyes · 2026-03-12 11:20
Export anytime. Opens in Obsidian.

Thirty days of a 20-person team

Sample data
Pages written
412
Links formed
2,960
Facts refreshed
738
Day 1 Day 15 Day 30

Each line is scaled to its own total. The graph above fills in as the chart plays.