{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_2243rfrqj73w","handle":"memnest-mcp","url":"https://wellknown.network/agents/memnest-mcp","links":{"self":"https://wellknown.network/agents/memnest-mcp/record.json","html":"https://wellknown.network/agents/memnest-mcp","markdown":"https://wellknown.network/agents/memnest-mcp/record.md","api":"https://wellknown.network/api/v1/agents/memnest-mcp","status":"https://wellknown.network/api/v1/agents/memnest-mcp/status","claim":"https://wellknown.network/agents/memnest-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/memnest-mcp/claim.json","badge":"https://wellknown.network/agents/memnest-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/memnest-mcp/history","tools":"https://wellknown.network/api/v1/agents/memnest-mcp/tools"},"ard":{"identifier":"urn:air::server:memnest-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"memnest-mcp","summary":"Persistent graph memory MCP server for AI agents using LadybugDB","description":"# Memnest Memory MCP Server\n\n[![PyPI version](https://badge.fury.io/py/memnest-mcp.svg)](https://pypi.org/project/memnest-mcp/)\n[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)\n[![Python 3.10+](https://img.shields.io/badge/python-3.10+-blue.svg)](https://www.python.org/downloads/)\n\nPersistent graph memory for AI agents using [LadybugDB](https://ladybugdb.com/) — an embedded graph database with native vector search and full-text search.\n\nGive your AI agent memory that persists across sessions, deduplicates automatically, and models knowledge as a graph with typed relationships.\n\n## Why Memnest?\n\n- **Graph memory** — memories linked via Topic nodes and relationships (RELATED_TO, SUPERSEDES, EXPLAINS) with Cypher queries\n- **Three-layer auto-dedup** — exact hash + semantic similarity + LLM-driven consolidation\n- **Workspace namespacing** — memories scoped per project; `global_search` opt-out\n- **HNSW vector search** — fast cosine similarity over FastEmbed embeddings\n- **Topic auto-linking** — tags become graph nodes, enabling traversal queries\n- **Embedded** — no Docker, no server process, single database directory\n- **Zero config** — sensible defaults, just install and run\n- **Importance & access tracking** — memories ranked by relevance and usage\n\n## Benchmarks\n\nMemnest scores **82.9%** on the [LOCOMO benchmark](https://snap-research.github.io/locomo/) — the standard evaluation for long-term conversational memory (ACL 2024).\n\n| Category | Score |\n|----------|-------|\n| Single-hop | 84.4% |\n| Multi-hop | 76.9% |\n| Open-domain | 85.7% |\n| Temporal | 86.5% |\n| Adversarial | 76.6% |\n| **Overall** | **82.9%** |\n\nEvaluated with Claude Sonnet 4.5 as the answer agent and Haiku 4.5 as the judge, using the industry-standard LLM-as-a-Judge methodology. All 5 LOCOMO categories included.\n\nRe-measured on 0.24.1 (same protocol, 199 questions): **84.4%** and **85.4%**\nacross two runs of the default `legacy` fusion. Note the…","publisher":{"name":"arunkse","url":null},"homepage":"https://github.com/arunkumars-mf/memnest-mcp","repository":"https://github.com/arunkumars-mf/memnest-mcp","version":"0.32.0","license":null,"protocols":["mcp"],"tags":["agent","graph","ladybugdb","mcp","memory","vector-search"],"pricing":null,"endpoints":[{"url":"pypi:memnest-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.vector-search","name":"Vector Search","confidence":1,"provenance":"declared"},{"slug":"knowledge.memory","name":"Agent Memory","confidence":1,"provenance":"declared"},{"slug":"ai.evaluation","name":"Evaluation & Benchmarks","confidence":1,"provenance":"derived"},{"slug":"knowledge.knowledge-graph","name":"Knowledge Graphs","confidence":1,"provenance":"declared"}],"categories":["ai","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":"memnest-mcp","registry":"pypi","observedAt":"2026-10-28T15:26:03.518Z","publishedAt":"2026-09-16T22:45:27.391068Z","latestVersion":"0.32.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"memnest-mcp","url":"https://pypi.org/project/memnest-mcp/","firstSeenAt":"2026-09-10T05:22:47.141Z","fetchedAt":"2026-10-28T15:24:33.817Z","normalizedAt":"2026-10-28T15:24:33.817Z"}]},"firstSeenAt":"2026-09-10T05:22:47.141Z","updatedAt":"2026-10-28T15:26:03.518Z"}