Documentation

API reference, authentication, and integration guides.

Last updated May 21, 2026 (UTC)

Overview

Reflect Memory gives your AI tools shared memory. Store something in one tool and every connected tool can access it: ChatGPT, Claude, Cursor, Gemini, and more. All data is scoped to your account and privacy-first.

Base URL: https://api.reflectmemory.com

Authentication

All requests require a Bearer token in the Authorization header:

Authorization: Bearer <your-api-key>

User key: Full access. Used for direct API calls, scripts, and the dashboard. Get this from your account settings.

Agent keys: Scoped per vendor (e.g., chatgpt, claude). Used by AI integrations. Each agent only sees memories where allowed_vendors includes"*" or their vendor name.

API Endpoints

Agent endpoints (used by AI integrations):

  • GET /agent/memories/latest Most recent memory. Optional ?tag= filter.
  • GET /agent/memories/{id} Full memory by UUID.
  • POST /agent/memories Create a memory.
  • POST /agent/memories/browse List summaries (no content).
  • POST /agent/memories/by-tag Full memories by tags.
  • POST /query AI query with memory context.
  • GET /whoami Resolve identity from key.

POST /agent/memories: Request body

  • title, content (required)
  • tags (optional array of strings)
  • memory_type (optional). Values: "semantic", "episodic", "procedural" (default: "semantic"). Memory classification: semantic = facts and knowledge, episodic = events and decisions, procedural = workflows and patterns.

User endpoints (dashboard, scripts): POST /memories,PUT /memories/:id,DELETE /memories/:id,POST /memories/list.

MCP Server

Reflect Memory exposes a Model Context Protocol (MCP) server for Claude and other MCP-compatible hosts. Connect to:

https://api.reflectmemory.com/mcp

Transport: Streamable HTTP. MCP clients must use streamable-http (or streamableHttp in Cursor settings). The legacy SSE transport is not supported.

Auth: OAuth 2.1 (for Claude native connector) or Bearer token (for Cursor, xAI API, n8n, and other MCP clients). Claude handles OAuth automatically when you add the connector URL.

Cursor config

Create .cursor/mcp.json in your project root:

{
  "mcpServers": {
    "reflect-memory": {
      "type": "streamable-http",
      "url": "https://api.reflectmemory.com/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_AGENT_KEY"
      }
    }
  }
}

Get your agent key from your dashboard (API Keys section). Restart Cursor after saving.

Tools (11)

  • read_memories - recent memories (full content)
  • get_memory_by_id - full memory by UUID
  • get_latest_memory - most recent memory, optional tag filter
  • browse_memories - lightweight summaries
  • search_memories - search by keyword
  • get_memories_by_tag - filter by tags
  • write_memory - create a new memory
  • update_memory - edit an existing memory (title, content, tags)
  • delete_memory - soft-delete a memory (recoverable from trash)
  • read_team_memories - get memories shared with your team
  • share_memory - share a personal memory with your team

All tools are scoped to the authenticated user. Team tools require the user to belong to a team (see Team Memories).

Integrations

  • ChatGPT Custom GPT (per-user OAuth): Use our ready-made Reflect Memory GPT. Each user authenticates individually via OAuth 2.1 - no shared API keys. 14 OpenAPI operations covering read, write, update, delete, search, browse, tag, latest, team, and share.
  • Claude (native connector): Go to Claude.ai Settings, Connectors, click +, paste https://api.reflectmemory.com/mcp as the URL, and click Add. Claude discovers all 11 memory tools automatically via OAuth. No extension or downloads needed.
  • Cursor (remote MCP): Add a .cursor/mcp.json file to your project with the MCP URL and your agent key as a Bearer token header. Cursor discovers all 11 memory tools automatically. No npm install or local server needed.
  • Grok: Install the Reflect Memory Chrome Extension and paste your agent key. The extension automatically injects your memory context into Grok conversations and saves important decisions. Developers can also use the xAI API's native remote MCP support.
  • Gemini: Install the Reflect Memory Chrome Extension and paste your agent key. The extension automatically injects your memory context into Gemini conversations. Works with Gemini's built-in memory seamlessly.
  • Perplexity: The Chrome Extension captures conversation context from Perplexity and saves it to your shared memory. Note: Perplexity is search-first, so memory context injection has limited effect on search results.

Setup guides: /integrations

Team Memories

Team Memories let multiple users share context through a shared memory pool. Any team member can share a personal memory with the team, and all members can read team-shared memories from any connected AI tool.

How it works

  1. Create a team -POST /teams with a team name. The creator becomes the team owner.
  2. Invite members -POST /teams/:id/invite with the invitee's email. They join automatically when they sign in.
  3. Share memories - use the share_memory MCP tool (or POST /memories/:id/share) to share any of your memories with the team.
  4. Read team memories - use the read_team_memories MCP tool (or GET /memories/team) to pull shared context from your teammates.

Team tools appear automatically in Claude, Cursor, and all other MCP-connected clients once the user belongs to a team.

Self-Hosted / Private Deploy

Run Reflect Memory on your own infrastructure so data stays on your machine or private network. Hosted, isolated-hosted, and self-host options are available — see deployment architecture.

Private deploy packages, install guides, and networking recipes are delivered under NDA for active evaluations — not via a public GitHub clone. Contact vm@reflectmemory.com or start from Enterprise.

Data Model

Each memory has:

  • id: UUID
  • title: Short descriptor
  • content: Full text
  • tags: Array of strings
  • memory_type: "semantic", "episodic", or "procedural"
  • origin: Which AI/service wrote it (chatgpt, claude, cursor, etc.)
  • allowed_vendors: Who can see it (["*"] = all)
  • created_at, updated_at: ISO 8601 timestamps
  • version: Integer, auto-incremented on every edit (version history)

Version History

Every edit creates a new version. The dashboard shows a full diff history for each memory, and you can restore any prior version. Versions are also accessible via the REST API at GET /memories/:id/versions.

Memory Types

Memories can be classified into three types to improve retrieval and context:

  • semantic: Facts, knowledge, and general information (default)
  • episodic: Events, experiences, and decisions tied to specific moments
  • procedural: Workflows, patterns, and how-to knowledge

Support

Documentation: this page. Privacy: /privacy. Terms: /terms. Support: vm@reflectmemory.com.

Documentation | Valaria