Neotoma with Cursor
Cursor provides project-scoped context and session memory. Neotoma adds persistent, cross-project memory with entity resolution and versioned state. They complement each other without conflict.
What Cursor provides
- Project-scoped context from open files, workspace, and Notepads
- Session memory within the current conversation
- Persistent instructions via .cursor/rules/ (always-apply, glob-scoped, or agent-invoked rule files)
- Native MCP integration (30+ built-in servers and support for custom stdio, SSE, and HTTP servers)
What Cursor doesn't handle
- Memory that persists across projects or after session ends. Rules carry forward instructions, not data
- Entity resolution across different conversations and data sources
- Versioned state with audit trail and provenance
Deterministic guarantees Neotoma provides
- Persistent memory across all projects, sessions, and tools
- 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 Cursor is available in Claude and Codex
Using them together
Keep rules and notepads for what they do well: project instructions and reusable context snippets. Neotoma handles structured data that persists across projects and tools. Both are active simultaneously with no conflict.
Neotoma Cursor hooks (optional)
The Neotoma Cursor hooks package installs into .cursor/hooks.json and runs alongside the MCP server. MCP remains the path for agent-driven structured writes; hooks guarantee capture of each prompt, tool call, and assistant reply, and inject retrieved Neotoma context into the prompt via additionalContext.
Install with npx @neotoma/cursor-hooks install. Hooks share idempotency keys with MCP, so combined use produces one entity per logical turn, not duplicates.
Getting started
Copy this prompt into a Cursor agent chat 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.If you are ready to proceed, paste this prompt into a Cursor agent chat. The agent handles evaluation, installation if needed, activation, and local MCP configuration.
Read https://neotoma.io/install and carry me through the install-first Neotoma flow.
Use `neotoma` commands for status and setup. If Neotoma is already installed, start with `neotoma doctor --json`; otherwise install it and run `neotoma setup --tool <my_tool> --yes`.
Avoid ad-hoc shell introspection or arbitrary repo scripts. Then activate Neotoma with my data and configure my current tool for robust ongoing use.This is a local integration. Neotoma runs on the same machine via stdio. No API server or remote access is required. The agent writes to .cursor/mcp.json (project-level) or ~/.cursor/mcp.json (global) and restarts MCP automatically.
After activation, offer to configure additional remote access points if the user also wants Neotoma available in hosted tools.
Before and after: Cursor 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 Cursor 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?”
Cursor documentation
- MCP integrations (connecting external tools via MCP)
- Rules (persistent AI instructions via .cursor/rules/)
- Notepads (reusable context shared across sessions)
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.