Ghost — the database for agents

Source: original

Postgres for developers and their agents

Give every agent its own database.

Ghost is hosted Postgres you spin up, fork, and throw away. One per task, production stays untouched, no blast radius.

curl -fsSL https://install.ghost.build | sh

Weekly digest

curl -fsSL https://install.ghost.build | sh

Subscribe to the weekly digest →

Send

Unlimited databases·Unlimited forks·100 hrs/mo free·1 TB storage free

ghost — database for agents

The manifesto

  1. Agents need to explore.Coding agents need to be able to test various ideas and see what works.→Letting agents experiment unlocks their full potential.
  2. Experimentation needs to be safe.You can't mess up a production system because an agent did something stupid.→Agents can't touch your production database.
  3. Experiments need to work on real data.Otherwise you never know if the results are valid.→Ghost forking lets you duplicate your database quickly, at any size.
  4. Humans need to get out of the way.During experimentation, an agent that needs human approval for every operation moves too slow.→Isolated environments are the only solution.
  5. Most experiments will fail.They need to be cheap to run and cheap to throw away.→Both code and databases need to be disposable.
  6. Humans need to review the final result.For correctness, style, and taste.→Ghost lets you introspect the database and share it with others for review.

Create, fork, or delete a ghost

Give every agent its own Postgres environment.

01≈ 0.4s

Create databases in seconds for new tasks and experiments

02copy-on-write

Fork existing databases instantly before changes or testing

03one command

Discard environments freely when work is complete

04MCP ready

Use CLI and MCP from day one for agent-native workflows

05no surprises

Set hard spending caps to avoid surprise usage

Use cases

Built for real agent workflows.

Safe schema experimentation

Fork a database before your agent touches migrations, data transformations, or structural changes. Test freely without risking prod.

Database per task

Give each agent task its own isolated Postgres environment instead of sharing one fragile staging database.

Persistent memory for agents

Use real Postgres as long-lived memory for agent systems that need state, retrieval, history, and structure.

Rapid product prototyping

Spin up disposable databases for prototypes, internal tools, and experiments without infrastructure overhead.

Pricing

Auto-pause for experiments. Always-on for production.

On-demand

Freeto start

billed by query time

Charged only when something actively queries the database, in 15-minute chunks. Spin one up for a task, throw it away when done — built for agent runs and experimentation.

Spin up free →

Dedicated

$10/ month

always-on

Reserved Postgres for production workloads. Never pauses. Same platform as your on-demand forks — fork production into disposable copies without leaving the system.

Spin up dedicated →

Early builders

People using it already.

“We had three agents fighting for one staging database. Now each one gets its own, spun up in the time it takes the first tool call to return. The whole category of 'agent stepped on another agent's work' just disappeared.”

Engineer, AI Research Platform

“We fork main before every migration. If it works on the fork, we swap. If it doesn't, we delete the fork. We haven't had a migration roll back in production since we moved to Ghost.”

Staff Engineer, Fintech Platform

“Databases used to be expensive enough that you reused them for everything. Now I create one for a single afternoon of work and throw it away at the end. It feels wasteful. It's not.”

Engineering Lead, Agent Infra Team

“I stopped writing cleanup scripts. That alone paid for it.”

Founder, DevTools Startup

The roadmap

What's landed and what's in flight

shipped

MCP server

First-class tool surface for Claude Code, Cursor, Windsurf, Codex, Gemini CLI, VS Code, and more. One command to install: ghost mcp install.

shipped

Schema introspection

ghost schema displays your database structure in a format optimized for agents. Tables, views, constraints, indexes, all formatted so Claude can write accurate queries without guessing.

shipped

MCP prompts

Reusable guidance packages agents can pull on demand. Eight shipped so far, covering pgvector semantic search, hybrid text search, TimescaleDB setup, and Postgres schema design.

shipped

Read-only mode

A read_only config option prevents destructive operations like delete, pause, and sql writes. Give agents access to your databases without worrying about accidental data loss.

shipped

Drop into psql

ghost psql opens an interactive psql session connected to your database. No more copying connection strings.

shipped

Headless login

ghost login --headless uses OAuth device flow for environments without a browser. Sandboxes, VMs, containers, remote servers. Enter a code on any device and you're in.

shipping next

pgvector + pg_textsearch baked in

No extensions to install. Forks of a vector-heavy db stay consistent. Agents can search on day one.

shipping next

Scheduled deletes

Auto-delete a database after N minutes. For agents that forget to clean up after themselves.

Get started

Your first Ghost database in minutes.

/01

Install Ghost

Get set up with the CLI and connect your workflow.

$ curl -fsSL https://install.ghost.build | sh

✓ install script complete · CLI ready

$ ghost login

✓ authenticated as you@team.com

/02

Create or fork a database

Start fresh or clone an existing environment for safe experimentation.

$ ghost create --name my-agent-task

✓ ready in 0.41s · postgres 16.1

$ ghost fork my-agent-task --name exp-a

✓ fork ready in 0.28s · CoW

/03

Use it with your agent

Connect through MCP or CLI and let your agent build against real Postgres.

$ ghost mcp install claude-code

✓ MCP configured · claude-code ready

$ ghost connect exp-a

postgresql://•••@exp-a.ghost.build/postgres

The wrap

Infrastructure for agent-native software starts here.

Ghost is the database layer built for how agents actually work: fast, parallel, disposable, and stateful.

Create your first database → See how Ghost works →

curl -fsSL https://install.ghost.build | sh