A
licenseA
qualityD
maintenanceEnables LLM agents to use associative memory with key/value graph-based retrieval, supporting multi-hop traversal and human-like associative leaps beyond embedding similarity.
10
MIT
keymem
by donggyun112
Related Servers
Alternatives to keymem
No user-submitted related servers found.
Related Servers
- AlicenseAqualityCmaintenancePersistent memory for LLM agents — episodic/semantic/procedural memory, auditable forgetting, and a benchmark proving it actually recalls things days later.5MIT
- AlicenseAqualityCmaintenanceLong-term memory for AI agents. Compiles conversations into a structured knowledge base with Claim/Evidence model, source provenance, append-only timeline, and contradiction detection. Multi-path retrieval (Exact + BM25 + Graph + weighted RRF + reranker) — 96.6% R@5 on LongMemEval-S, zero vector dependencies.83MIT
Nexusyn Engineofficial
AlicenseNot gradedqualityBmaintenanceLong-term persistent memory for AI agents with hybrid search (DiskANN + FTS), bi-temporal knowledge graph, and 81.1% LongMemEval accuracy.4Apache 2.0- AlicenseNot gradedqualityBmaintenanceSelf-evolving knowledge graph for AI agents — persistent memory that gets smarter with every interaction.Apache 2.0
- AlicenseNot gradedqualityDmaintenanceLong-term memory for AI agents over MCP — episodic + semantic memory, a temporal knowledge graph, and a dialectic user model, exposed as 32 tools (recall, remember, context, graph, dreaming, peers). Zero dependencies, runs fully offline; leads the LoCoMo benchmark at ~35x fewer LLM calls.2Apache 2.0
TDQS
A3.9/5.0
Scored across 10 tools
Disambiguation4/5
The read path (recall → read_key → read_memory) is a coherent pipeline with distinguishable roles, and the mutation tools (remember, correct, forget, dismiss, confirm_memory) have distinct intents. However, the boundaries are subtle enough that descriptions must repeatedly explain how each differs from its neighbors (e.g. dismiss vs correct vs forget, read_key vs read_memory), which signals real potential for misselection. remember vs remember_batch is a clean single/batch pair.
Naming Consistency3/5
There is a mix of bare verbs (recall, correct, dismiss, forget, remember) and verb_noun names (read_memory, read_key, confirm_memory, browse_keys, remember_batch). Both are readable and individually clear, but the conventions are not uniform, and the noun target varies (key vs memory) across similar read operations.
Tool Count4/5
Ten tools is well within a reasonable range for a memory subsystem and each tool maps to a real operation. The only mild redundancy is remember vs remember_batch, where the batch variant is an efficiency convenience rather than a distinct capability.
Completeness4/5
The surface covers the core memory lifecycle: recall/search, browse, key and memory reads, write, update (correct), delete (forget), confirmation, and link feedback (dismiss). Gaps are minor — no namespace listing/management, key merging, or export/stats operations — but these are workarounds, not blockers, for the primary recall/remember workflow.
Maintenance
ActivityActive
ResponsivenessNo issues