| What it does | The governance layer for AI agents
| Open-source memory platform for AI agents
|
|---|
| Stage | MVP
| Not given
|
|---|
| Founded | 2026
| Not given
|
|---|
| Based in | CH
| DE
|
|---|
| Pricing model | Not given
| Not given
|
|---|
| 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 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 | - 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
| - 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 | - 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
| - 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) | 5 ▲ +5 (up) since last check | 70 ● no change since last check |
|---|
| Trust Flow (Majestic) | 9 | 14 |
|---|
| Citation Flow (Majestic) | 24 | 43 |
|---|
| Referring domains (Majestic) | 64 | 1089 |
|---|
Isonapse