Skip to content

Editions

The open edition and Enterprise.

What each one includes, the control plane, and the questions a decision-maker asks.

Editions

Open to try and use. Enterprise for production.

Open

Free · Apache-2.0

To evaluate, develop with and use the whole ecosystem.

  • All seven extensions, open source
  • Public image with PostgreSQL 19 RC2 (preview)
  • Installable from PGXN on your own PostgreSQL 18 or 19
  • Support through GitHub issues

Enterprise

No public pricing yet

To run the gate and its guards in production on a supported base.

  • PostgreSQL 18 on Red Hat's PostgreSQL image (RHEL 9), with user and password
  • ygg-pg Enterprise 0.3.1 image (pg_agent_gate 0.4.3), not certified
  • One tested image with four extensions: pg_agent_gate, pg_living_assertions, pg_promise_guard and pg_grammar_guard
  • Support and deployment guidance

LatamFlows is a Red Hat partner; container certification is the next step.

The piece that makes MCP unnecessary

ygg-agent

v0.2.0 Python package · not an extension

The agent loop on pg_agent_gate, with no MCP: the model writes SQL and the database decides.

It connects a model to PostgreSQL over the database’s own protocol, through the gate. It works with pg_agent_gate 0.4.0 or later. If your client only speaks MCP, the same gate can be used over MCP; ygg-agent is the path without that intermediary.

pip install ygg-agent

PyPI → GitHub Apache-2.0

Enterprise · ygg Control · in development

Your whole fleet of databases, one record nobody can alter without it showing.

ygg Control is the control plane of the Enterprise edition. It gathers what every AI agent proposed, what the database kept and what it stopped, across all your databases, in a hash-chained record. If anyone edits or deletes a row, the verifier gives it away. The console only reads: neither it nor its API can write.

ygg Control · fleet audit verifying…
sample data · computed in your browser
assistant prod-orders
proposed
0
kept
0
aborted
0
refused
0
reporter staging-billing
proposed
0
kept
0
aborted
0
refused
0
# Database Agent Action Outcome Rows Chained hash
01 prod-orders assistant proposes · DROP TABLE orders refused — …
02 prod-orders assistant proposes · DELETE FROM orders passed — …
03 prod-orders assistant executes · DELETE FROM orders aborted 8 …
04 prod-orders assistant executes · UPDATE orders SET total = 999 WHERE id = 1 kept 1 …
05 staging-billing reporter executes · UPDATE invoices SET status = 'sent' WHERE id = 418 kept 1 …
06 staging-billing reporter proposes · ALTER TABLE invoices DROP COLUMN tax refused — …

What it includes

01

Central store

Its own PostgreSQL with an append-only record: every event carries the SHA-256 hash of the previous one, per database, and a trigger rejects any UPDATE or DELETE. verify_chain() walks the chain and says exactly where it broke.

02

Fleet connector

Reads the proposals and executions pg_agent_gate already records in each database, by watermark, and pours them into the record without duplicates. In production it connects with a read-only role.

03

Read-only console and API

The console shows the fleet, every agent and every act. Its API enters the database with a role that can only read: trying to write answers 401. Only the console faces the world; the API stays internal.

Roadmap

  1. Phase 1 Built and tested

    Audit and compliance: the record, the connector and the console.

  2. Phase 2 In design

    Human in the loop: approve or reject before anything is kept, on top of the gate's propose / commit.

  3. Phase 3 Planned

    Central fleet policy, SSO and roles.

Early access

Live trials open by sign-up.

Request early access with your company email. We will contact you to set up a session on a trial environment, with the console and the gate running.

No public price yet. What you see above is a reproduction in your browser of the same algorithm the product uses, on sample data; it is not a real database or customer data.

Questions from the people who decide

What gets asked before connecting an AI to the database.

Short answers, each with a link to where the detail lives. If your question is not here, write to us.

Contact
Can the AI bypass the gate?

Not through any client path: it is enforced by hooks inside the server, and in a session registered as an agent nothing executes except the gate’s seven verbs. Who can switch it off is a superuser, or whoever edits postgresql.conf; that is why the gate refuses to register a superuser role as an agent.

Threat model →
Does it work with my AI vendor or my framework?

With any of them. The AI only needs to produce SQL: it arrives through psql, a driver, or an MCP shim with no power of its own. There is no SDK to integrate and no service to run in front of the database.

What about performance?

Writing one statement and letting the database decide took a median of 6 s per task. With the same gate behind both, the agent without MCP used 5x fewer prompt tokens than through MCP (24k vs 126k for 13 tasks) and finished each task 13x faster: a median of 14 s against 185 s, on a CPU-only CI runner anyone can re-run. Measured with pg_agent_gate 0.4.0.

See the run →
Do I have to change my application?

No. The application keeps connecting as it always has. Only the sessions of the roles you register as agents go through the gate; for the rest of the database nothing changes.

What does it guarantee, and what not?

It bounds what the agent names (the statement and the rows it changes) and the row count. It does not judge intent: a mass UPDATE the role is entitled to make is kept, confined by row-level security. What it does not cover is written down, before you find out yourself.

What it does not cover →
Is it safe for production?

The code is open, with adversarial tests and fuzzing on every push. The public image is a preview (PostgreSQL 19 release candidate) and must not be exposed to the internet. For production there is the Enterprise edition, on PostgreSQL 18 and Red Hat’s PostgreSQL image, with support.

And if the AI gets it wrong anyway?

If the effect exceeds the agent’s limit or breaks an assertion, it is undone and the reason is recorded. If it is within bounds, it is kept with the before and after of up to 50 rows. The record cannot be edited or deleted; it survives pg_dump.

What data leaves my company?

Through the gate, none: everything runs inside your PostgreSQL and talks to no external service. The AI model is whichever you choose, local or not; the vector memory of pg_phasevec (a 0.x preview) lives in your database too.

Which PostgreSQL version do I need?

pg_agent_gate needs PostgreSQL 18 or later (dry_run uses RETURNING old/new). Each of the other extensions states its own requirement in its README; the public image 0.3.6 ships six (all but pg_recall_guard) on 19 and the Enterprise edition runs on 18.

How much does it cost?

The seven extensions are free, under Apache-2.0, forever. The Enterprise edition and the services are quoted per case; there is no public price yet, and when there is you will read it here.

Contact

Write to us. We will get back to you.

Enterprise edition, security audit or agent-to-database integration: one email with two lines about your case is enough. We answer in English and Spanish.

Email

manu@latamflows.com

A person reads the email. If you would rather write directly, the address is above.

Or tell us here

We only use this to reply to you. No lists, no newsletters.

Who is behind this

Manuel Reyes Bravo

The seven extensions, the image and the contributions to PostgreSQL core are signed by Manuel Reyes Bravo, from Chile. To talk code, repositories or the PostgreSQL lists, his personal email:

Personal email

manuelreyesbravo@gmail.com

Also through GitHub issues: pg_agent_gate/issues

Try it Talk