| What it does | The data layer for AI agents
| Open-source memory platform for AI agents
|
|---|
| Stage | Startup
| Not given
|
|---|
| Founded | 2026
| Not given
|
|---|
| Based in | US
| DE
|
|---|
| Pricing model | Paid
| Not given
|
|---|
| Pricing | Base: $50/mo for 50,000 points per month. Core: $100/mo for 100,000 points per month. Pro: $250/mo for 250,000 points per month. Ultima: $500/mo for 500,000 points per month. Enterprise: $1000/mo for 1,000,000 points per month. Custom option available for higher volumes. Search costs 5 points per ca
| 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.
|
|---|
| Key features | - AI research for structured, cited answers across sources
- AI extraction converts pages to clean JSON without selectors
- 250+ data sources including company registries and business intelligence
- MCP server integration with Claude, OpenAI, and other clients
- REST API for custom agent code
- Web search capability for AI agents
- Points-based pricing model with no per-source fees
- AI research depth tiers from quick lookups to exhaustive investigations
| - 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
|
|---|
| What makes it different | - Unified API and MCP access to 250+ data sources without stitching scrapers
- Structured, cited answers synthesized from comprehensive source catalog
- No HTML parsing or selector maintenance required for extraction
- One request format for all company intelligence and registry sources
- Points reset monthly with no per-source pricing complexity
| - 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
|
|---|
| 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) | 4 ▲ +3 (up) since last check | 70 ● no change since last check |
|---|
| Trust Flow (Majestic) | 1 | 14 |
|---|
| Citation Flow (Majestic) | 27 | 43 |
|---|
| Referring domains (Majestic) | 61 | 1089 |
|---|
NeuralVerge