| What it does | Open-source memory platform for AI agents
| Managed Apache Iceberg tables and hosted agents for AI to work with data
|
|---|
| Stage | Not given
| Startup
|
|---|
| Founded | Not given
| 2026
|
|---|
| Based in | DE
| ES
|
|---|
| 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.
| Storage €0.10 per GB-month (5 GB free monthly), Compute €0.12 per CPU-hour (10 CPU-hours free monthly), AI tokens €2.50 per million (5 million free monthly). No request, ingress or egress fees.
|
|---|
| 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
| - Managed Apache Iceberg tables with automatic maintenance and backups
- Multiple data ingestion methods including files, APIs, webhooks, and scheduled URLs
- Query with DuckDB, Spark, Trino, Polars, or PyIceberg
- Public data catalogs served over a CDN
- Automatic spatial clustering for geometry tables
- FTP, FTPS and SFTP support for file uploads from cameras and devices
- Corporate sign-in and granular access control for organizations
- Audit trail and activity log for organizational use
|
|---|
| 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
| - Open table format: Apache Iceberg ensures your data remains portable and readable by any compatible engine
- Agents keep what they observe, decide and do as persistent tables for learning across runs
- Operated in Europe with data storage in Frankfurt and model inference in Paris
- Pay only for what you use with no request, ingress or egress fees
- Serverless platform with no servers or clusters to manage
|
|---|
| 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 | Not checked yet ● no change since last check |
|---|
| Trust Flow (Majestic) | 14 | 2 |
|---|
| Citation Flow (Majestic) | 43 | 26 |
|---|
| Referring domains (Majestic) | 1089 | 32 |
|---|
LakehouseBox