Persistent graph memory MCP server for AI agents using LadybugDB
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"memnest-mcp","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# Memnest Memory MCP Server [](https://pypi.org/project/memnest-mcp/) [](https://opensource.org/licenses/MIT) [](https://www.python.org/downloads/) Persistent graph memory for AI agents using [LadybugDB](https://ladybugdb.com/) — an embedded graph database with native vector search and full-text search. Give your AI agent memory that persists across sessions, deduplicates automatically, and models knowledge as a graph with typed relationships. ## Why Memnest? - **Graph memory** — memories linked via Topic nodes and relationships (RELATED_TO, SUPERSEDES, EXPLAINS) with Cypher queries - **Three-layer auto-dedup** — exact hash + semantic similarity + LLM-driven consolidation - **Workspace namespacing** — memories scoped per project; `global_search` opt-out - **HNSW vector search** — fast cosine similarity over FastEmbed embeddings - **Topic auto-linking** — tags become graph nodes, enabling traversal queries - **Embedded** — no Docker, no server process, single database directory - **Zero config** — sensible defaults, just install and run - **Importance & access tracking** — memories ranked by relevance and usage ## Benchmarks Memnest scores **82.9%** on the [LOCOMO benchmark](https://snap-research.github.io/locomo/) — the standard evaluation for long-term conversational memory (ACL 2024). | Category | Score | |----------|-------| | Single-hop | 84.4% | | Multi-hop | 76.9% | | Open-domain | 85.7% | | Temporal | 86.5% | | Adversarial | 76.6% | | **Overall** | **82.9%** | Evaluated 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. Re-measured on 0.24.1 (same protocol, 199 questions): **84.4%** and **85.4%** across two runs of the default `legacy` fusion. Note the…
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.