| What it does | Persistent, verifiable memory for AI agents that evolves, reasons and verifies itself
| Shared context platform for human-agent teams
|
|---|
| Stage | Not given
| Startup
|
|---|
| Founded | Not given
| 2026
|
|---|
| Based in | Not given
| US
|
|---|
| Pricing model | Freemium
| Freemium
|
|---|
| Pricing | Free: $0/month (100k stored tokens, 5k queries/month, 100MB ingest); Builder: $29/month (1.5M stored tokens, 25k queries/month, 1GB ingest); Pro: $99/month (6M stored tokens, 150k queries/month, 5GB ingest); Scale: $299/month (25M stored tokens, 1M queries/month, 20GB ingest). Payment via Dodo card
| Starter: Free (all features and integrations). Advanced: Bespoke pricing (includes onboarding, training, custom integrations). Enterprise: Bespoke pricing (includes rollout plan, configurable data retention, security controls).
|
|---|
| Key features | - Hybrid retrieval combining vector search and full-text search via Reciprocal Rank Fusion
- Multi-hop reasoning graph to answer questions across agent history
- Automatic contradiction detection with update relations
- Agent-owned Ed25519 cryptographic identity
- Source-available self-hosting option for non-commercial use
- MCP server integration with Claude, Cursor, Zed and other MCP clients
- Autonomous x402 USDC micropayment protocol for agents
- Memory consolidation that evolves over time
- Temporal ledger for deterministic calendar arithmetic
| - Real-time context capture from conversations and decisions
- Agent priming with team context
- Team status and live activity visibility
- Search and retrieval across team knowledge
- Meeting capture and decision recording
- Coordination signals (murmurs) between team members
- Human-agent handoffs without re-briefing
- Ox Plans for architectural documentation
- Integration with multiple AI coding tools
- iPhone and Apple Watch app for capturing thinking
|
|---|
| What makes it different | - Memory evolves and consolidates over time rather than just growing larger
- Contradiction detection prevents stale facts from poisoning prompts
- Agent-owned identity and full data export prevent lock-in
- Native MCP integration requires no code changes for Claude, Cursor and other tools
- Autonomous agents can pay programmatically via USDC without human intermediaries
| - Persistent context that moves with work instead of starting from scratch
- Context layer independent of any single tool or ecosystem
- Prevents drift and duplication across human-agent teams
- Free for small teams with all features included
- Data portability: context can be exported and kept as git repos
|
|---|
| 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) | Not checked yet ● no change since last check | 17 ● no change since last check |
| Trust Flow (Majestic) | 0 | 15 |
| Citation Flow (Majestic) | 11 | 19 |
| Referring domains (Majestic) | 1 | 140 |