Zouroboros Memory

Production-grade persistent memory for AI agents. Hybrid SQLite + vector search, decay classes, episodic memory, cognitive profiles, and MCP server.

This skill appears to implement what it claims: a local hybrid SQLite + vector memory with CLI and an MCP server. Before installing, consider: - If you enable vector search or reranking, the skill will send text to external services (OLLAMA_URL or OpenAI). Only set these env vars if you trust the destination (prefer a local Ollama instance). - The package writes a database by default to ~/.zouroboros/memory.db — pick and review the DB path if you don't want persistent data in your home directory. - The npm package depends on better-sqlite3 (native addon) which compiles on install — review/build in a controlled environment if you have supply-chain concerns. - Registry metadata did not declare env vars or the config path; this is likely an oversight. Verify the upstream repository and package integrity (check GitHub releases, package contents, and package checksum) before installing into a production agent. - For minimal risk, run the package in a sandboxed environment, avoid setting OPENAI_API_KEY or OLLAMA_URL to public endpoints, and audit network activity the first time the skill runs.

Type: OpenClaw Skill Name: zouroboros-memory Version: 3.0.0 The zouroboros-memory skill bundle is a legitimate implementation of a persistent memory system for AI agents, providing hybrid keyword and vector search capabilities. It uses SQLite (via better-sqlite3) for local storage and integrates with Ollama or OpenAI for embeddings and reranking. The code follows standard patterns for MCP (Model Context Protocol) servers, including secure parameter binding for SQL queries and standard JSON-RPC communication over stdio. No evidence of data exfiltration, malicious execution, or prompt injection was found across the source files (e.g., src/database.ts, src/mcp-server.ts) or documentation.