The Base for Agents

Turn agent output into data, docs, skills, and apps you can actually use.

Open Cloud DashboardOpen Source
Works with
Claude Code
We launch the oat latte Thursday — draft this week's posts.

Nine posts across Instagram, X, and LinkedIn, visuals included. Opened one change request for your review.

busabase · change-requestSENT
content.posts
9 posts · 3 platforms
Do anything
Busabase
ReviewsThis week's posts

This week's posts

Claude Code · Content · Posts · just now

In review9 operations in Content: draft posts from the launch plan.

What will change

9. Create
InstagramRosetta season. The winter blend pours like silk.Mon 09:00
InstagramThe Oat Latte lands Thursday — $4.50 all week.$4.50$6.50Product base says $6.50Mon 20:00
InstagramCorner seat, 3pm light. Some afternoons write themselves.Tue 20:00
XSlow pour, no filter. Just the winter blend.Wed 12:00
XRoast drop day — 14 minutes, first crack at 9:40.Wed 20:00
X7:58am. The queue that forms before we open.Thu 09:00
LinkedInWhere the winter blend starts: 1,800m, Huila, Colombia.Thu 12:00
LinkedInSix years ago today: four seats and one grinder.Fri 10:00
LinkedInThe new roastery opens next month. Here's the space.Fri 20:00
Waiting for your reviewRequest changesApprove
USE CASES

Many agents. One workspace they all build in.

Blog Posts base table
Agent submits post as a Change Request
Reviewer checks body and metadata
Approved post becomes a canonical record

More workflows

Unify the databases your agents touch — then make them trustworthy.

See use cases
Team MemoryNotes, sources, decisions, and agent-readable context, verified before reuse.
MarketingCampaign records, social posts, newsletters, and assets become approved content data.
OperationsProjects, tasks, vendors, and ownership updates become reliable ops data.
Routine WorkRecurring work logs become reviewable institutional memory.
ComplianceAccess reviews, vendor checks, and evidence lists keep an audit trail.
ResearchMarket signals and monitored sources become analyst-verified knowledge.
Content FactoryIdeas, briefs, drafts, and creative assets pass through one trusted pipeline.
ConfigService configs and policy data are reviewed before automation uses them.
SupportHelp articles, saved replies, and product facts are approved before customers see them.
Product catalogListings, specs, pricing, and relations become a trusted commercial database.
LocalizationAgent translations become locale-specific records reviewed by native speakers.
HiringCandidate notes, evaluations, and interview signals stay reviewable.

How it works

Turn every agent output into data, docs, skills, and apps you can use.

Agents write through change requests — every change carries a message, a diff, and a history, and you can hold anything back for review. What lands becomes reusable memory for agents and apps. Start locally, then add Cloud when you need collaboration.

01

Agents write changes

Claude Code, n8n, custom agents, or any producer submits structured records, enrichment, labels, and updates over API.

02

Every change is accounted for

Each one carries a message, field diffs, an author, and a full history — and waits in the Inbox for review whenever you want it to.

03

Revise with evidence

Ask agents to revise, add sources, or explain decisions while comments, commits, and reviews stay attached.

04

It adds up into intelligence

What lands becomes canonical data that CRM, CMS, dashboards, and agent memory can all reuse.

Features

Turn agent writes into intelligence you can trust.

Approve, request changes, merge — and every downstream record is one a human verified. Busabase turns the AI firehose into a personal, traceable, reusable intelligent database.

  • Change Request review

    Each submission is a field-level diff — inspect it before it enters the database.

  • Fact verification

    Reviewers check source context and impact before hallucinations become business facts.

  • Canonical knowledge

    Approved work becomes the source of truth, with commit history and relationship context.

  • Audit trail

    Every submit, approval, and merge is logged — who, when, and why.

Inbox · review queueMarketing4 pending
Cclaude-codeNvidia
industry → Semiconductors · AI
RejectApprove
Nn8nLaunch announcement
queued
ZzapierJensen Huang
queued
Cclaude-codeQ3 renewal
queued
Approved work enters intelligence1,247 trusted records

Agent-first API

Claude Code, n8n, Zapier, or your own agents submit structured changes through Agent Skills, MCP, or OpenAPI.

Spaces & permissions

Separate personal projects, clients, or business lines by Space; owner, admin, and reviewer roles.

Open source, local-first

Busabase core runs locally on PGlite. Cloud adds collaboration, hosted APIs, and permission governance.

Inside Busabase

From one change to data your agents can build on.

The whole review loop — pending changes, field-level diffs, audit history, canonical records, and the graph behind your business data.

Busabase inbox — pending change requests from agents

Inbox: pending changes

Every agent submission lands in one fact-verification queue.

Graph view of seeded data

Graph view

See how customers, content, assets, and business objects connect.

Agent-proposed diff awaiting human review

Field-level fact review

Inspect sources and diffs field by field, then approve or request changes.

Base table — canonical approved records

Canonical records table

Approved changes become trusted records in your intelligent database.

Base records grid view

Records grid view

Browse, filter, and maintain verified records like a database.

Record detail with full audit trail

Full audit trail

Who submitted, approved, and merged — traced.

Why agent work keeps evaporating

Output that disappears vs. a workspace it adds up in

Without Busabase
With Busabase
The work ends up in a chat log or a scratch file nobody finds again.
It lands in typed Bases, Docs, Skills, and Apps you can open tomorrow.
Every session starts from zero and re-derives what the last one knew.
The next agent reads what the last one wrote.
Each agent invents its own schema and its own place to put things.
One typed data contract every agent reads and writes through.
You find out what an agent changed by diffing production.
Every change carries a message, a diff, and an undo — hold any of it for review.
You still have to build the app that makes the data usable.
The same data renders back as AirApps, views, and dashboards.

Pricing that scales with your team

Open source, free forever. Cloud starts free and grows per seat.

Free
For one person putting agent output under review.
$0
  • 1 space you own
  • 3 seats per space
  • 5,000 records per space
  • 1 GB attachment storage
  • 1 self-hosted connection online
Get Started
Plus
For a small team reviewing agent-written records together.
$10/seat/mo
Billed $120/seat annually
  • $10 per seat, billed yearly (2 months free)
  • 3 spaces you own
  • 10 seats per space
  • 20 GB attachment storage
  • OpenAPI, webhooks and MCP
Get Plus
Most Popular
Pro
For growing workspaces that need room to scale and open APIs everywhere.
$20/seat/mo
Billed $240/seat annually
  • $20 per seat, billed yearly (2 months free)
  • Unlimited spaces you own
  • Unlimited seats
  • 100 GB attachment storage
  • Priority support (WhatsApp / WeChat / Email)
Get Pro
See full pricing

FAQ

Questions, answered

Is Busabase open source?

Yes. The local engine is open source — run it yourself, no SaaS required.

Can I self-host, or is it cloud-only?

Both. Run the open-source desktop / local engine, or use Busabase Cloud — it is the same engine and the same change model either way.

Which agents does it work with?

Any agent that can call a REST API — Claude Code, Codex, Gemini CLI, n8n, Zapier, LangChain, or your own. Paste the SKILL.md and go.

How does Busabase help me build an intelligent database?

Start with the bases your agents already touch — CRM, content, research, support, finance, datasets. Agents write through change requests, so every change carries a message, a diff, and a full history — and you can hold anything back for review when it matters. What lands becomes reusable memory for you, agents, and apps.

What happens to rejected changes?

Rejected work never enters your canonical data. Every decision — approve, request changes, reject — stays attached so the record remains explainable later.

Is my data private?

Yes. With the local engine your data never leaves your machine; on Cloud it stays in your own space. You stay in control.

Give your agents a workspace worth building in.

Every change keeps its source, its diff, and its full history — and waits for you whenever you want it to.

Open Cloud DashboardOpen Source