Postgram MCP server

Postgram

A self-hosted productivity and knowledge backend for humans and AI agents.

Website · Quick start · MCP guide · REST API · Demo

Postgram keeps the data you and your agents work from in one inspectable place: notes, documents, tasks, people, projects, interactions, decisions, and agent memory. Humans use the browser UI and CLI; agents use the same corpus over MCP, REST, or the CLI.

It is more than an agent-memory layer. Postgram preserves typed source objects, supports GTD-style task management and Markdown folder sync, combines full-text and vector retrieval with a knowledge graph, and separates short-lived agent working context from durable memory.

Watch the demo Search across memories, documents, people, projects, and tasks

Why Postgram

to the same data without tying it to one editor or hosted memory provider.

• One private corpus across tools. Give different agents and devices access

summaries, then search, edit, link, archive, or delete them yourself.

• Inspectable source data. Store typed entities instead of opaque chat

edge summaries tell an agent when related graph context is worth following.

• Search before graph expansion. Hybrid retrieval finds relevant entities;

and lifecycle; grooming can archive it or distill selected context into durable memory.

• Working context is not durable memory. Session context has its own scope

extraction providers are allowed, who receives API keys, and what is kept.

• Operator control. Choose where PostgreSQL runs, which embedding and

Postgram is built for one person or a small trusted team running a local or single-VM deployment. It is not a hosted service or a multi-tenant SaaS platform. Knowledge extraction is optional, and the provided Docker Compose setup binds the raw API and UI ports to loopback by default.

Quick Start (Docker Compose)

You need Git, Docker, and Docker Compose. Node.js 22+ is needed only for local development or for installing the pgm CLI; gpg is needed only for encrypted CLI backups.

1. Clone Postgram:

git clone https://github.com/ivo-toby/postgram.git
   cd postgram

install and start Ollama on the Docker host, then pull Postgram's default embedding model:

1. Choose an embedding path before the first start. For the local default,

ollama pull bge-m3

For hosted OpenAI embeddings instead, create a .env file containing a real key before starting Compose:

OPENAI_API_KEY=<your-openai-key>

1. Start the stack:

docker compose up -d --build

The first run creates persistent Docker volumes for PostgreSQL and installation secrets. No .env file is required for the default Compose path.

1. Read the one-time bootstrap token:

docker compose logs mcp-server \
     | grep 'Bootstrap token:' \
     | tail -n 1

The plaintext appears only in the original first-start logs. Capture it before recreating the API container or discarding those logs.

Shortened. The full README is on GitHub.