Agent Hook for Claude Code (public beta, available now), Community Edition (public beta, early September 2026, free), Enterprise Edition (Q4 2026)
Free: Personal memory up to 1,000 records with no time limit. Pro: $5 per month or $50 per year for unlimited personal memory. Team: $10 per month plus $5 per member per month for shared memory and collaboration.
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
Personal and team memory
MCP server with OAuth 2.1 or token authentication
Search by words and by meaning
Record provenance and version history
Conflict detection and resolution
JSON export and import
Project-based organization with hierarchical grouping
Urgent inbox for team notifications
Role-based access control for teams
Works with Claude, ChatGPT, ZCode, Grok and other MCP clients
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
One memory accessible from any AI assistant without re-explanation or chat copying
Separate personal and team memory layers with no automatic sharing
Records show full history and cannot be silently erased or replaced
Search by meaning finds relevant records even with different wording
Isonapse
GAIM