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 with persistent execution, isolated sessions, and multi-agent routing
- Long-term conversational memory and reminders
- Multi-channel gateway (WhatsApp, Telegram, Discord, iMessage via a single process)
- Skills system with ClawHub registry and first-class agent tools (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.
Getting started
Copy this prompt into an AI coding agent such as Claude Code, Cursor, or Codex to have it read the evaluation page, inspect your tool, workspace, and configuration context, then judge whether Neotoma fits your real workflow and what to persist first.
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.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 as a native OpenClaw plugin with kind: "memory". All 30+ MCP tools are registered as agent tools with zero extra configuration.
openclaw plugins install clawhub:neotomaplugins:
slots:
memory: neotoma
entries:
neotoma:
enabled: true
config:
dataDir: ~/.local/share/neotoma
environment: productionVerify with openclaw plugins inspect neotoma to confirm Format: native and Kind: memory.
Or use manual MCP configuration:
OpenClaw documentation
- Overview (self-hosted agent gateway)
- Configuration (setup wizard and settings reference)
- Tools (browser, canvas, cron, and access control)
- Skills (extensible skill folders and ClawHub registry)
- ClawHub (plugin and skill registry where Neotoma is published)
Before and after: OpenClaw with Neotoma
“Continue where we left off yesterday.”
Resuming based on thread from two weeks ago.
Resuming yesterday’s thread on the migration plan. 3 open tasks remaining.
“What did I commit to with Sarah last week?”
No commitments found.
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?”
No hosting expenses found.
$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, see the install guide for more options, MCP reference for full setup, CLI reference for terminal usage, and agent instructions for behavioral details.