| What it does | Open-source memory platform for AI agents
| A marketplace to discover, run, and publish AI agents
|
|---|
| Stage | Not given
| Not given
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | DE
| TR
|
|---|
| 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.
| Starter Credits Pack: $5 one-time payment (100 credits, approximately 50 agent runs). Middle Credits Pack: $15 one-time payment (300 credits, approximately 150 agent runs). High Credits Pack: $45 one-time payment (900 credits, approximately 450 agent runs). New accounts receive 50 free credits.
|
|---|
| 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
| - Browse and discover AI agents from a curated marketplace
- Run agents without coding or technical setup
- Create and publish agents using a visual interface
- One-time credit purchases with no monthly subscriptions
- Free agent publishing with fees only on actual usage
- Agents for marketing, development, research, and productivity tasks
- Sandboxed environment for secure data handling
|
|---|
| 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
| - Single marketplace eliminates hunting across multiple sites for AI agents
- One-time purchases instead of subscriptions reduce friction and simplify access
- Transparent and predictable fee structure designed for creator profitability
- Agents that take actions and complete multi-step tasks, not just chat
- Supports both non-developers and developers with flexible interface options
|
|---|
| 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 | 2 ● no change since last check |
|---|
| Trust Flow (Majestic) | 14 | 8 |
|---|
| Citation Flow (Majestic) | 43 | 24 |
|---|
| Referring domains (Majestic) | 1089 | 15 |
|---|
caywork