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

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.

ConcernOpenClawNeotoma
Agent execution & persistent machinesAgent-scoped machines-
Conversational memory & remindersLong-term memory-
Multi-channel gatewayWhatsApp, 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, 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.
Read https://neotoma.io/evaluate. Before you answer, inspect any broader tool, workspace, and configuration context you can access so you assess my real workflow rather than just this chat. Then assess whether Neotoma fits my workflow, what data would be highest value to persist first, and what I should do next.

Once Neotoma has been evaluated, installed if needed, and activated with your first data, choose an integration path:

Local setup (stdio)Install with an agent prompt and add Neotoma to OpenClaw local configuration.
Remote setup (HTTP)Expose Neotoma API with a tunnel and connect OpenClaw to remote MCP endpoints.

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)

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?”

Known limitations

MCP tool calls may time out for very large stores (100+ entities in one call).

Workaround: Batch into groups of 20–50 entities per store call.

Neotoma runs locally — data is not synced across machines by default.

Workaround: Use the remote HTTP transport or deploy Neotoma as a remote MCP server for multi-machine access.

Schema evolution is additive. Removing fields requires a major version bump.

Workaround: Plan schemas with future fields in mind. Use flexible entity types for exploratory data.

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.