{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_j6dx2p27fk48","handle":"daniele-corrao-memento-mcp","url":"https://wellknown.network/agents/daniele-corrao-memento-mcp","links":{"self":"https://wellknown.network/agents/daniele-corrao-memento-mcp/record.json","html":"https://wellknown.network/agents/daniele-corrao-memento-mcp","markdown":"https://wellknown.network/agents/daniele-corrao-memento-mcp/record.md","api":"https://wellknown.network/api/v1/agents/daniele-corrao-memento-mcp","status":"https://wellknown.network/api/v1/agents/daniele-corrao-memento-mcp/status","claim":"https://wellknown.network/agents/daniele-corrao-memento-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/daniele-corrao-memento-mcp/claim.json","badge":"https://wellknown.network/agents/daniele-corrao-memento-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/daniele-corrao-memento-mcp/history","tools":"https://wellknown.network/api/v1/agents/daniele-corrao-memento-mcp/tools"},"ard":{"identifier":"urn:air::server:daniele-corrao-memento-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"memento-mcp","summary":"The Autonomous Nervous System for AI Agents — local-first MCP middleware with temporal graph memory, active coercion, and proactive goal alignment.","description":"<div align=\"center\">\n  <img src=\"assets/memento-logo.svg\" alt=\"Memento Logo\" width=\"100%\">\n\n  <h1>Memento</h1>\n  <p><strong>The Autonomous Nervous System for AI Agents</strong></p>\n\n  [![PyPI version](https://img.shields.io/pypi/v/memento-mcp.svg)](https://pypi.org/project/memento-mcp/)\n  [![License: AGPL v3](https://img.shields.io/badge/License-AGPL_v3-blue.svg)](https://www.gnu.org/licenses/agpl-3.0)\n  [![Python 3.10+](https://img.shields.io/badge/python-3.10+-blue.svg)](https://www.python.org/downloads/)\n  [![MCP Protocol](https://img.shields.io/badge/MCP-Ready-success.svg)](https://modelcontextprotocol.io/)\n</div>\n\n---\n\nMemento is a local-first, open-source MCP middleware that gives your AI agents (Cursor, Claude Desktop, Trae, etc.) persistent memory, proactive goal enforcement, and autonomous intelligence — all running on a zero-cost **SQLite temporal graph** with **Reciprocal Rank Fusion (RRF)** retrieval.\n\nNo cloud databases. No API calls for storage. Everything stays on your machine.\n\n---\n\n## Architecture\n\n### Temporal Graph Memory (RRF)\nBuilt on **SQLite FTS5** (full-text search) and **cosine similarity** (vector embeddings). Fuses keyword matches and semantic meaning via **Reciprocal Rank Fusion**. WAL-mode enabled for concurrency.\n\n### Tri-State Goal Enforcer\nKeep your AI aligned with project objectives at three escalation levels:\n- **Level 1 — Context Injection**: Automatically injects active goals into every search result. Active by default.\n- **Level 2 — Strict Mentor**: Forces the AI to submit code/plans for goal alignment evaluation via LLM.\n- **Level 3 — Daemon Push**: File-watcher monitors your workspace and proactively flags goal drift.\n\n### Active Coercion (Code Immune System)\nDeterministic regex/tree-sitter rules that block anti-patterns at commit time and in the IDE. 100% deterministic — zero LLM hallucination risk during enforcement.\n\n### Autonomous Agent\nBackground cognitive loop with four levels:\n- **off**: No background behavior (default)…","publisher":{"name":"Daniele Corrao","url":null},"homepage":"https://github.com/JoyciAkira/memento","repository":"https://github.com/JoyciAkira/memento/blob/main/CHANGELOG.md","version":"1.2.1","license":null,"protocols":["mcp"],"tags":["mcp","ai-agents","memory","graph-database","sqlite","coercion","llm","knowledge-graph","model-context-protocol"],"pricing":null,"endpoints":[{"url":"pypi:memento-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi","publisherName":"pypi"}},"derived":{"capabilities":[{"slug":"data.database","name":"Databases","confidence":1,"provenance":"declared"},{"slug":"knowledge.memory","name":"Agent Memory","confidence":1,"provenance":"declared"},{"slug":"knowledge.knowledge-graph","name":"Knowledge Graphs","confidence":1,"provenance":"declared"},{"slug":"data.vector-search","name":"Vector Search","confidence":0.825,"provenance":"derived"}],"categories":["data","knowledge"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"memento-mcp","registry":"pypi","observedAt":"2026-10-28T15:26:02.164Z","publishedAt":"2026-07-17T03:47:26.589856Z","latestVersion":"1.2.1"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"memento-mcp","url":"https://pypi.org/project/memento-mcp/","firstSeenAt":"2026-09-10T05:22:45.204Z","fetchedAt":"2026-10-28T15:24:31.761Z","normalizedAt":"2026-10-28T15:24:31.761Z"}]},"firstSeenAt":"2026-09-10T05:22:45.204Z","updatedAt":"2026-10-28T15:26:02.164Z"}