<!--
Full-page Markdown export (rendered HTML → GFM).
Source: https://neotoma.io/neotoma-with-openclaw
Generated: 2026-04-26T19:10:03.258Z
-->
# Neotoma with OpenClaw
OpenClaw gives agents their own machine, long-term memory, and persistent execution. Neotoma adds user-owned, structured state that any agent can query across platforms, sessions, and tools.
## What OpenClaw provides
- →[Agent-scoped machines](https://docs.openclaw.ai/cli/agents) with persistent execution, isolated sessions, and multi-agent routing
- →[Long-term conversational memory and reminders](https://docs.openclaw.ai/index)
- →[Multi-channel gateway](https://docs.openclaw.ai/index) (WhatsApp, Telegram, Discord, iMessage via a single process)
- →[Skills system](https://docs.openclaw.ai/skills) with ClawHub registry and [first-class agent tools](https://openclaw-ai.com/en/docs/tools/index) (browser, canvas, cron)
* * *
## What OpenClaw doesn't handle
- ×Cross-platform memory; data stays inside one agent instance
- ×Structured entity resolution across tools and data sources
- ×User-owned state with provenance, versioning, and audit trail
* * *
## Deterministic guarantees Neotoma provides
- →User-owned structured memory accessible from any tool or agent
- →Deterministic entity resolution: contacts, tasks, and relationships unified by canonical IDs
- →Versioned state with full provenance: every fact traces to its source
- →Cross-tool continuity: data stored from OpenClaw is available in Cursor, Claude, and Codex
* * *
## Using them together
OpenClaw is the execution layer: it gives the agent a machine and the ability to act. Neotoma is the state layer: it holds the user's structured memory that any agent can read and write. The two are complementary with no conflict.
| Concern | OpenClaw | Neotoma |
| --- | --- | --- |
| Agent execution & persistent machines | Agent-scoped machines | \- |
| Conversational memory & reminders | Long-term memory | \- |
| Multi-channel gateway | WhatsApp, Telegram, etc. | \- |
| Structured entities across tools | \- | Store via MCP |
| Cross-platform state | \- | Shared memory graph |
| Versioned history & audit trail | \- | Observation history |
* * *
## Getting started
Copy this prompt into an AI coding agent such as Claude Code, Cursor, or Codex to have it read the [evaluation page](/neotoma-with-openclaw/evaluate), inspect your tool, workspace, and configuration context, then judge whether Neotoma fits your real workflow and what to persist first.
Evaluation prompt
Reads the page, then evaluates fit against your real workflow.
Copy
``Read https://neotoma.io/evaluate. Use any tool, workspace, and chat context already available in this session to assess my real workflow. Avoid ad-hoc shell introspection just to profile me; if Neotoma is already installed, use `neotoma doctor --json` for status instead. Then tell me whether Neotoma fits my workflow, what data would be highest value to persist first, and what I should do next.``Copy prompt
The evaluation flow handles install, activation, and OpenClaw connection (including the native plugin path) automatically. If you prefer to configure the connection yourself, use one of these options:
Native plugin
Neotoma is published on [ClawHub](https://clawhub.ai) as a native OpenClaw plugin with `kind: "memory"`. All 30+ MCP tools are registered as agent tools with zero extra configuration.
ClawHub install
Register Neotoma from ClawHub on the machine where OpenClaw runs.
```
openclaw plugins install clawhub:neotoma
```
Memory slot
Assign the plugin to the memory slot in your OpenClaw configuration.
```
plugins:
slots:
memory: neotoma
entries:
neotoma:
enabled: true
config:
dataDir: ~/.local/share/neotoma
environment: production
```
Verify with `openclaw plugins inspect neotoma` to confirm `Format: native` and `Kind: memory`.
Or use manual MCP configuration:
[Local setup (stdio)Install Neotoma and add it to OpenClaw local configuration.](/neotoma-with-openclaw/neotoma-with-openclaw-connect-local-stdio)
[Remote setup (HTTP)Expose Neotoma API with a tunnel and connect OpenClaw to remote MCP endpoints.](/neotoma-with-openclaw/neotoma-with-openclaw-connect-remote-http)
* * *
## OpenClaw documentation
- →[Overview](https://docs.openclaw.ai/index) (self-hosted agent gateway)
- →[Configuration](https://www.getopenclaw.ai/docs/configuration) (setup wizard and settings reference)
- →[Tools](https://openclaw-ai.com/en/docs/tools/index) (browser, canvas, cron, and access control)
- →[Skills](https://docs.openclaw.ai/skills) (extensible skill folders and ClawHub registry)
- →[ClawHub](https://docs.openclaw.ai/tools/clawhub) (plugin and skill registry where Neotoma is published)
* * *
## Before and after: OpenClaw with Neotoma
“Continue where we left off yesterday.”
Without Neotoma
Resuming based on thread from two weeks ago.
With Neotoma
Resuming yesterday’s thread on the migration plan. 3 open tasks remaining.
“What did I commit to with Sarah last week?”
Without Neotoma
No commitments found.
With Neotoma
You committed to sending the architecture doc by Friday. Sarah’s email updated Mar 28.
“How much did we spend on cloud hosting last month?”
Without Neotoma
No hosting expenses found.
With Neotoma
$847 across AWS and Vercel, up 12% from February.
* * *
## After you connect
Once Neotoma is running, try these starter commands in OpenClaw to see cross-session memory in action:
Store a contact
“Remember that Sarah Chen's email is sarah@newstartup.io — she's the CTO at NewStartup.”
Store a task
“I need to send the architecture doc to Sarah by Friday.”
Recall across sessions
“What do I know about Sarah? What did I commit to doing for her?”
Start with [evaluation](/neotoma-with-openclaw/evaluate), see the [install guide](/neotoma-with-openclaw/install) for more options, [MCP reference](/neotoma-with-openclaw/mcp) for full setup, [CLI reference](/neotoma-with-openclaw/cli) for terminal usage, and [agent instructions](/neotoma-with-openclaw/agent-instructions) for behavioral details.