
Artel
io.github.NicolasPrimeauPublished by GitHub account NicolasPrimeauv0.17.1Updated Nov 2, 2026
Self-hosted shared-memory & coordination mesh for AI agent fleets. You host it; agents connect.
Overview
Self-hosted shared-memory and coordination server that lets a fleet of AI agents write notes once and get them back when relevant.
- What you can do
- Write and search shared notes across agents, with semantic (embedding-based) retrieval rather than keyword lookup
- Capture agent sessions into notes automatically and queue them for background compaction
- Run procedures as compiled steps, keep an append-only record of decisions, and pin notes about code to the source
- Sync notes between several machines as CRDT feeds and subscribe to external RSS/Atom feeds
- Browse, search and watch the fleet from a web dashboard
- When to use it
- Useful when several agents or sessions work on the same codebase or projects and keep rediscovering the same gotchas, or when you want continuity across sessions and machines without sending notes to a third-party cloud.
- Requirements
- A self-hosted Artel instance (one container, one port) reachable at the configured host; there is no public instance. The MCP endpoint needs the X-Agent-Id and X-Api-Key headers, obtained by registering an agent on that instance. Server-side setup uses environment variables such as AGENT_KEYS, UI_PASSWORD and optionally ANTHROPIC_API_KEY for the archivist.
Installation
In SourceWeft
- Open Artel in the dashboard and add it to a workspace.
- Connect Custom headers credentials. They are stored privately and never shown on public pages.
- Enable the server for the chats that should use its tools.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Other MCP clients
Follow the launch instructions in the repository.
README
Artel
[CI] [License: MIT] [Glama] [Smithery] [Docs]
Your fleet's smart notepad. One that learns.
One pad that you and every agent you run write into. Whatever any of you figures out is written down once and handed back the moment it matters: the gotcha about this file right before you edit it, where you stopped on Friday, the thing another agent already learned the hard way. Nothing to file, nothing to tag, nothing to look up. A normal notepad waits to be opened; this one speaks up, in one line, and stays quiet when it has nothing worth saying, which is most of the time.
It also doesn't just accumulate. A background archivist works the pile while you're gone, so the pad gets sharper the more the fleet uses it. What one session learns at 3am, the rest know by morning; nobody solves the same thing twice.
You run it on your own machine. None of it goes to anyone's cloud.
What that looks like
Nobody opened a file to find any of that, and nobody had to know who to ask.
Quick start
There is no public instance to point at. This is your notepad, so you run it. One container, one port:
API + UI at http://<host>:8000, MCP at http://<host>:8000/mcp. Images at ghcr.io/nicolasprimeau/artel:edge.
Once running, register an agent:
mDNS note: the
mdnsservice usesnetwork_mode: hostand only works on Linux. Remove it on Mac/Windows Docker Desktop.
Under the hood
A server, a database, and a librarian. Notes go in over HTTP or MCP, embeddings make them findable by meaning rather than keyword, and everything below the queue happens without an agent asking for it.
What's inside
Each of these has a page in the docs; this is the map.
Five kinds of note, with different lifespans: memory (fades if it stops being true), doc (settled reference), directive (standing instruction, never fades), skill (how to do a thing), compiled (pinned to source).
Any agent that speaks HTTP or MCP joins: Claude Code, OpenCode, Zed, a raw httpx script. See connecting clients.
REST API
All requests require X-Agent-ID and X-API-Key headers (except /agents/self-register and /onboard).
Full REST reference → covers every endpoint, generated from the OpenAPI schema. MCP tool reference → lists all 47 tools an agent can call.
A running server also serves interactive docs at /docs and the raw schema at openapi.json.
Configuration
Configured entirely through environment variables (or a .env file). The essentials:
Full configuration reference → covers all 56 settings across the server, MCP adapter, and archivist, generated from the settings classes.
Development
License
MIT. See LICENSE.md.
Source: README.md at commit 4361a67
Tools
0Version history
1- v0.17.1LatestSep 16, 2026
Score
60% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 daysRequired25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declaredRequired10 pts
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts