Skip to main content
Glama
byte5ai

palaia

Official
by byte5ai
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Your AI tools finally share one memory.

License: MIT Release v3 CI Container image

Get started · What it does · Docs · How it works · Coming from v2?

palaia is a hub you run yourself: on a server in your office, in your own cloud account, or on a machine at home. Every AI tool you use connects to it once: Claude, ChatGPT, Codex, Gemini, and any other tool that speaks MCP, the open standard AI tools use to reach outside data and tools. From then on they share one memory and one set of tools, and they can hand work to each other. Your data stays in plain files on hardware you control.

Think Home Assistant, for your AI tools.

NOTE

palaia v3 is a release candidate (3.0.0-rc1). Everything below works and is tested, but it has not had an outside security review yet. Try it, keep backups, and tell us what breaks. If you are running palaia v2 today, it stays supported.

What it does for you

  • Your AI tools remember, together. Tell one assistant about a decision and the others know it too. Your memory is a folder of plain Markdown notes you can open in any editor (Obsidian opens it as-is), search, and back up like any other files.

  • Set up a tool once, use it everywhere. Install an add-on in palaia and every connected AI can use it. No more pasting the same configuration into five apps.

  • Your agents can work as a team. An AI session on your laptop can hand a task to one on your server, with the context attached, and find out who is already working on what.

  • Runs where you decide. A server in your office, a machine in your cloud account, a NAS, or a Raspberry Pi. No account with us, no subscription, no data leaving your infrastructure unless you say so.

  • Safe by default. Sign in with GitHub or Google, pick in the setup wizard how far your hub should reach (just this machine, your private network, or the internet), and back everything up with one click.

Related MCP server: AgentBase

Get started in 60 seconds

You need Docker. That is the whole prerequisite list.

docker run -d --name palaia-hub \
  -p 8420:8420 \
  -v palaia_home:/data \
  --restart unless-stopped \
  --security-opt no-new-privileges:true --cap-drop ALL \
  --read-only --tmpfs /tmp --tmpfs /run \
  ghcr.io/byte5ai/palaia-hub:beta

Then open http://<your-machine>:8420 in a browser (on many home networks http://palaia.local works too). A short setup wizard takes it from there: sign in, save your first memory, connect your first AI tool. No config files, no second command.

Once 3.0.0 is final, use :stable instead of :beta. Updating later is one click in the dashboard.

Other ways to install

You have…

Do this

A Synology NAS

Paste one file into Container Manager, no terminal: step-by-step guide

A Raspberry Pi

The command above works on 64-bit Raspberry Pi OS with Docker. A ready-to-flash card image is in progress

A rented server (Hetzner, DigitalOcean, AWS, …)

Paste cloud-init.yaml into your provider's user-data field. It installs everything and keeps the hub off the open internet

Umbrel, CasaOS, Runtipi, TrueNAS SCALE

Packages are ready; until they are in the official catalogs, use the command above

Docker Compose or Portainer

docker-compose.yml

Release candidate: the files and packages in this table pin ghcr.io/byte5ai/palaia-hub:stable, which does not exist until 3.0.0 is final. Until then, change :stable to :beta in whatever you use.

Stuck? See Your first shared memory for a walkthrough with screenshots, or troubleshooting.

Works with

Claude Code · Claude Desktop · claude.ai · ChatGPT · Codex · Gemini CLI · Grok · LM Studio · any other MCP-compatible tool

Each one has a short connect guide. Claude Desktop gets a one-click bundle: download, click, connected.

Learn more

Already using palaia v2?

palaia v2 is the Python package at the root of this repository. It stays installable and supported with critical fixes; its documentation is unchanged. Nobody is being pushed off it. When you are ready, one command imports your v2 knowledge into v3, and the migration guide covers what changes and how to roll back.

Community & support

License

MIT · © 2026 byte5 GmbH

This server cannot be deployed

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Maintenance

ActivityMaintained
ResponsivenessSlow

Resources

Related MCP Connectors

Related MCP Servers

  • BuildAutomata Memory MCP

    brucepro
    F
    license
    Not graded
    quality
    D
    maintenance
    Provides AI agents with persistent, searchable memory that survives across conversations using semantic search, temporal versioning, and smart organization. Enables long-term context retention and cross-session continuity for AI assistants.
    14
    -

  • AgentBase

    revmischa
    A
    license
    Not graded
    quality
    C
    maintenance
    Hosted shared knowledge base for AI agents. Store, search, and retrieve structured knowledge using semantic search. Agents contribute to a growing collective intelligence that compounds over time. No install — just a URL.
    1
    MIT
  • Memsolus MCP Server by memsolus

    Memsolus MCP Serverofficial

    memsolus
    A
    license
    A
    quality
    D
    maintenance
    Provides persistent long-term memory for AI agents through semantic search and automated knowledge graph extraction. It enables agents to store, recall, and reason over facts, preferences, and relationships across multiple conversations and sessions.
    14
    12 npm
    MIT