$ loading_
Provide tamper-evident audit and embedded memory storage for AI agents.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "ai.sovantica/engrava" MCP server from askskill: Run: claude mcp add 'ai-sovantica-engrava' -- npx -y engrava-mcp
Developers building AI agents can use it to store long-term memory, action records, and contextual data. This makes it easier to trace why an agent made a specific decision.
When agents need stronger traceability, this tool can record critical operations. It is suitable for agent systems that care about auditing, compliance, or security.
When you need to filter actions and memories from agent history, you can use MindQL for querying. This helps locate past context and operational steps.
It is an embedded memory database for AI agents, focused on tamper-evident audit, MindQL querying, and Action Records. It can store agent memory and operational history.
Based on the description, it is both: it provides an embedded memory database and emphasizes tamper-evident auditing and action records. For implementation details, see the source repository.
The provided material does not include installation steps, runtime requirements, or key requirements. Please see the source repository for prerequisites.
Provide Git-backed Markdown memory and clean search for AI agents.
Create tamper-evident audit trails and observability records for AI agents.
Provide fully offline, encrypted vector memory storage for AI agents.
Provide a local memory layer for coding agents to capture and recall facts.
Provide evidence-grounded agent memory with mandatory provenance tracking and flexible storage.
Give AI agents durable memory, observable retrieval, and governed context assembly.