Skip to main content

Zero-config embedded Unforget server — PostgreSQL 17 + pgvector 0.8 + memory API, no setup required

Project description

unforget-embed

Zero-config embedded Unforget memory server. PostgreSQL + pgvector + Unforget API — no Docker, no setup, one command.

Install

pip install unforget-embed

Usage

# Start the server (background daemon)
unforget-embed start

# Check status
unforget-embed status

# Stop
unforget-embed stop

Server runs on http://127.0.0.1:9077 with the full Unforget API.

Data persists in ~/.unforget/data/.

How It Works

  1. Starts an embedded PostgreSQL instance via pgserver (no Docker needed)
  2. Enables the pgvector extension
  3. Runs the Unforget FastAPI server on localhost
  4. All data stored locally in ~/.unforget/data/

No API keys. No external services. No configuration.

Options

unforget-embed start --port 9077        # custom port
unforget-embed start --data-dir /path   # custom data directory
unforget-embed start --foreground       # run in foreground (don't daemonize)

API

Once running, the full Unforget REST API is available:

# Write a memory
curl -X POST http://localhost:9077/v1/memory/write \
  -H "Content-Type: application/json" \
  -d '{"content": "User prefers dark mode", "org_id": "demo", "agent_id": "bot"}'

# Recall memories
curl -X POST http://localhost:9077/v1/memory/recall \
  -H "Content-Type: application/json" \
  -d '{"query": "user preferences", "org_id": "demo", "agent_id": "bot"}'

License

Apache 2.0

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

unforget_embed-0.2.0.tar.gz (4.0 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

unforget_embed-0.2.0-py3-none-any.whl (5.2 kB view details)

Uploaded Python 3

File details

Details for the file unforget_embed-0.2.0.tar.gz.

File metadata

  • Download URL: unforget_embed-0.2.0.tar.gz
  • Upload date:
  • Size: 4.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for unforget_embed-0.2.0.tar.gz
Algorithm Hash digest
SHA256 fb83152025a4d5b29bfd61eba77d12eb07e678d0c3f2d7b402ed547e7dedef44
MD5 ee498daa90ef40659e94ae82279b8309
BLAKE2b-256 7563d2a77bfccd429e066a20de7e5c97022bb9d271372ed89034fa41cf2d8e8f

See more details on using hashes here.

Provenance

The following attestation bundles were made for unforget_embed-0.2.0.tar.gz:

Publisher: publish.yml on unforget-ai/unforget-embed

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file unforget_embed-0.2.0-py3-none-any.whl.

File metadata

  • Download URL: unforget_embed-0.2.0-py3-none-any.whl
  • Upload date:
  • Size: 5.2 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for unforget_embed-0.2.0-py3-none-any.whl
Algorithm Hash digest
SHA256 75cd914f48a3f2bd886fdc2bfd4be656d2ac5429358c954d1a6b720eed1db0b4
MD5 24ab02028e94f2fb05e40a7befb2bec7
BLAKE2b-256 31127094ee4fd8e391df5cfd1eecd9b1829a03b5d08bc2d72ad538834c0f9948

See more details on using hashes here.

Provenance

The following attestation bundles were made for unforget_embed-0.2.0-py3-none-any.whl:

Publisher: publish.yml on unforget-ai/unforget-embed

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page