| What it does | Open-source memory platform for AI agents
| Cloud hosting for AI agents running 24/7 with no setup
|
|---|
| Stage | Not given
| Not given
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | DE
| EE
|
|---|
| Pricing model | Not given
| Paid
|
|---|
| 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.
| Base $19/mo with $5 AI credits, 4 vCPU, 8GB RAM, 80GB storage. Pro $39/mo with $10 AI credits, 8 vCPU, 16GB RAM, 160GB storage. Max $79/mo with $20 AI credits, 16-64 vCPU, 32-128GB RAM, 320-1280GB storage.
|
|---|
| 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
| - Run multiple open-source AI agents including OpenClaw, Hermes, Codex, DeepSeek Harness, NanoClaw and OpenCode
- Gmail management: clear threads, draft replies, send follow-ups
- Calendar autopilot: schedule meetings, move events, set reminders
- Document and PDF summarization with action items extraction
- Browser control to click, fill forms and submit web tasks
- File organizer: find, rename and sort downloads
- Scheduled and recurring tasks with monitoring
- Connect to 1000+ skills and integrated apps
- Choose from 100+ AI models from top providers
- MCP integrations for external tools and APIs
|
|---|
| 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
| - No setup required - launch in one click without managing servers or infrastructure
- 24/7 uptime guaranteed - agents keep running even when your computer is off
- Switch between 100+ AI models with one click
|
|---|
| 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 | 30 ● no change since last check |
|---|
| Trust Flow (Majestic) | 14 | 12 |
|---|
| Citation Flow (Majestic) | 43 | 29 |
|---|
| Referring domains (Majestic) | 1089 | 255 |
|---|
Atomic Bot