A
licenseA
qualityA
maintenanceLocal deterministic BM25 memory for AI agents — offline-first, no API key, SHA-256 content-addressed shards, stdio MCP transport. Same query always returns the same ranked result.
11
42 npm
MIT
Why this server?
A local, deterministic BM25 memory node for AI agents that is offline-first, requires no API key, uses SHA-256 content-addressed shards, and speaks stdio MCP. This is the closest match to a self-contained, deterministic memory server like the one hosted in the linked repository.
Why this server?
A dedicated memory operating system for AI applications, giving agents long-term memory that can be invoked, updated, and scheduled — the core purpose any 'Stemem'-style memory project would serve.
AlicenseAqualityDmaintenanceMemOS (Memory Operating System) is a memory management operating system designed for AI applications. Its goal is: to enable your AI system to have long-term memory like a human, not only remembering what users have said but also actively invoking, updating, and scheduling these memories.4178 npm7Apache 2.0Why this server?
A self-evolving memory system for coding agents that organizes knowledge into a graph with semantic and structural search, matching the memory-plus-retrieval scope of the referenced repo.
AlicenseNot gradedqualityDmaintenanceA-MEM is a self-evolving memory system for coding agents that automatically organizes knowledge into a Zettelkasten-style graph with dynamic relationships, enabling semantic and structural search.129 PyPI35MITWhy this server?
Developer context-continuity memory server that builds a temporal knowledge graph from your git repos and serves it over MCP — good fit if Stemem targets persistent coding-agent context.
AlicenseAqualityAmaintenancememex is a developer context-continuity MCP server — it watches your git repos and builds a temporal knowledge graph (modules, symbols, decisions, open problems) via Graphiti + Neo4j, then serves it to any AI coding agent over MCP. Every edge carries a validity window and a confidence score that decays over time. 12 tools across read and write. Install via npx -y stifler-memex-mcp. MIT licensed.1441 PyPI12MITWhy this server?
Cognitive memory implementing multi-store memory, semantic RAG, forgetting curves, and 76+ MCP tools, fully local and MIT licensed — broadly comparable in ambition to a memory framework like Stemem.
AlicenseCqualityFmaintenanceCognitive memory for AI agents. Implements Atkinson-Shiffrin multi-store memory (sensory → STM → LTM), semantic RAG with fastembed, Ebbinghaus forgetting curves, trust scoring, and metacognitive guard. 76+ MCP tools. 100% local, MIT licensed.100791 npm27AGPL 3.0Why this server?
Fast hybrid code search with BM25 lexical ranking, semantic embeddings, and RRF fusion in a single Go binary; relevant if Stemem centers on term/stem-based lexical retrieval over code.
AlicenseNot gradedqualityAmaintenanceFast hybrid code search for agents. Pure Go, single static binary, BM25 lexical + Model2Vec semantic embeddings + RRF fusion + a code-aware reranker, with the retrieval algorithm ported verbatim from semble31MITWhy this server?
Local BM25 engine on SQLite FTS5 with camelCase/snake_case/Japanese tokenization support, stateless MCP stdio server — directly relevant to a stemming/lexical search memory project.
AlicenseAqualityBmaintenanceEnables fast, low-token code search for AI coding agents via a local BM25 engine built on SQLite FTS5, with support for camelCase, snake_case, and Japanese text. Provides a stateless MCP stdio server and a Hermes adapter for multi-agent environments.1MITWhy this server?
Searchable long-term memory server using BM25 indexing over document chunks for durable cross-session recall without cloud dependencies.
AlicenseNot gradedqualityDmaintenanceA searchable long-term memory server for AI agents using BM25 indexing over document chunks, enabling durable recall across sessions without cloud dependencies.1Apache 2.0Why this server?
Long-term memory that compiles conversations into a structured knowledge base with multi-path retrieval (Exact + BM25 + Graph + RRF) and zero vector dependencies — similar deterministic-retrieval design.
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.813 PyPI3MIT