| What it does | The governance layer for AI agents
| Persistent, verifiable memory for AI agents that evolves, reasons and verifies itself
|
|---|
| Stage | MVP
| Not given
|
|---|
| Founded | 2026
| Not given
|
|---|
| Based in | CH
| Not given
|
|---|
| Pricing model | Not given
| Freemium
|
|---|
| Pricing | Agent Hook for Claude Code (public beta, available now), Community Edition (public beta, early September 2026, free), Enterprise Edition (Q4 2026)
| 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
|
|---|
| Key features | - Policy-based rule definition for agent actions
- Checkpoint enforcement before every action
- Tamper-evident signed audit ledger
- Vendor-neutral across models and harnesses
- Deterministic decision-making without LLMs
- Offline enforcement without network connectivity
- Budget caps and cost control
- Data tokenization and secret placeholder support
- One-click installation for Claude Code
| - 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
|
|---|
| What makes it different | - Neutral layer enforcing policies across any agent, model, or harness
- Self-hosted on your hardware with no telemetry or cloud dependency
- Cryptographically verified audit trail you can check offline
| - 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
|
|---|
| 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) | 5 ▲ +5 (up) since last check | Not checked yet ● no change since last check |
| Trust Flow (Majestic) | 9 | 0 |
| Citation Flow (Majestic) | 24 | 11 |
| Referring domains (Majestic) | 64 | 1 |