| What it does | Open-source memory platform for AI agents
| MCP server connecting AI agents to Google Search Console, Bing Webmaster Tools and GA4
|
|---|
| Stage | Not given
| Not given
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | DE
| PL
|
|---|
| Pricing model | Not given
| Freemium
|
|---|
| Pricing | Free: $0/month with 1M tokens and 1 workspace (no card required). Standard: $1.00 per 1M tokens plus $5 per additional workspace. Enterprise: contact for pricing with bring-your-own-cloud deployment. Open-source engine available free to self-host.
| Free: $0/month (1 site, 200 requests/month, 14 days history). Pro: $19/month or $182/year (10 sites, unlimited requests, 16 months history). Agency: $34/month or $340/year (25 sites, 5 seats, 16 months history).
|
|---|
| Key features | - Unified vector search, knowledge graphs, and relational storage
- Automatic knowledge graph generation from data sources
- Multi-tenant support with isolated workspaces
- Data source integrations (Slack, Notion, Google Drive, GitHub, etc.)
- Self-improving memory that learns from use
- Multiple deployment options (cloud, self-hosted, air-gapped)
- Agent framework integrations (LangGraph, CrewAI, OpenAI SDK, MCP)
- Support for multiple vector and graph databases
- GDPR compliance and encryption at rest and in transit
- Built-in graph visualization of company brain
| - Google Search Console data access (clicks, impressions, CTR, position by query, page, country, device)
- SEO reports including quick wins, traffic drops, content decay and cannibalization
- Bing Webmaster Tools integration and IndexNow submissions
- Google Analytics 4 reports and AI assistant referral traffic tracking
- URL inspection and sitemap status
- Email alerts and weekly digest
- Read-only and write access controls
- Works with Claude, ChatGPT, Cursor, Windsurf, VS Code and any MCP client
- OAuth sign-in with no API keys or Google Cloud project required
|
|---|
| What makes it different | - Combines vectors with graph relationships and generated data models for connected context retrieval
- State of the art performance on BEAM benchmark (79% vs 73.4% at 100k tokens)
- Keeps memory costs flat as data grows compared to baseline LLM approaches
- Fully open-source with no database lock-in
- Updates memory as source data changes, not just static snapshots
| - Hosted MCP server with no Google Cloud project or API keys needed
- All three sources (Google Search Console, Bing, GA4) in one connector
- Server-side analysis returning finished numbers instead of raw data exports
- Works on claude.ai and ChatGPT web without desktop-only setup
|
|---|
| Free plan | Not given
| Not given
|
|---|
| Open source | Not given
| Not given
|
|---|
| Platforms | Not given
| Not given
|
|---|
| Public API | Not given
| Not given
|
|---|
| Community votes | 0 | 0 |
|---|
| DR (Domain Rating by Ahrefs) | 70 ● no change since last check | 17 ▼ −1 (down) since last check |
|---|
| Trust Flow (Majestic) | 14 | 0 |
|---|
| Citation Flow (Majestic) | 43 | 24 |
|---|
| Referring domains (Majestic) | 1089 | 13 |
|---|
GSC Magic