Skip to main content
Glama
staticroostermedia-arch

Engram

by staticroostermedia-arch
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Rust
Local

Related Servers

Alternatives to Engram

No user-submitted related servers found.

    Related Servers

    • Cortex

      ryanfrigo
      A
      license
      Not graded
      quality
      D
      maintenance
      Local-first AI memory layer with hybrid retrieval and brain-inspired namespaces. Enables agents to save, search, and manage memories directly via MCP tools.
      3 npm
      MIT

    • mesh-memory

      dklymentiev
      A
      license
      Not graded
      quality
      D
      maintenance
      Self-hosted semantic memory for AI agents. Save worklogs, decisions, and notes via MCP, then recall them across sessions by meaning rather than keyword. Backed by Postgres + pgvector with local embeddings (multilingual-e5-base).
      1
      MIT

    • mnemos

      s60yucca
      A
      license
      B
      quality
      A
      maintenance
      Persistent memory engine for AI coding agents. Single Go binary, zero runtime dependencies, MCP-native. Stores, searches, and deduplicates memories across sessions using embedded SQLite with hybrid FTS + semantic search, memory decay, relation graph, and token-budget context assembly.
      10
      22
      MIT

    • rmbr

      SRock44
      A
      license
      A
      quality
      A
      maintenance
      Embedded memory and retrieval engine for AI agents, providing local-first memory with MCP support for multi-agent access control.
      3
      2
      MIT

    • memsem

      WindSeries83
      A
      license
      A
      quality
      A
      maintenance
      Semantic memory MCP server that gives AI agents a self-writing, priority-based memory with local semantic search and automatic contradiction handling. It persists across sessions and projects, entirely on your machine.
      18
      34 npm
      2
      MIT
    Deploy Server
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    TDQS

    B3.1/5.0

    Scored across 87 tools

    Disambiguation2/5

    There are several overlapping tool clusters: recall, query_pure, query_with_momentum, tensor_recall, and summarize all serve retrieval; context_for_file and context_for_edit overlap heavily; update and update_with_tensor_bond have similar write purposes. The descriptions are detailed, but at the set level an agent can easily pick the wrong variant.

    Naming Consistency3/5

    Most tools follow the mcp_engram_<verb>_<noun> pattern, and families like goal_*, thought_tile_*, and var_* are internally consistent. However, mcp_compress_linguistic, mcp_decompress_linguistic, mcp_fibered_linguistic_equivalence, and mcp_linguistic_calculus break the prefix pattern, and noun-only names like mcp_engram_genesis, mcp_engram_stats, and mcp_engram_leg_corpus further blur the convention.

    Tool Count1/5

    With 87 tools, this is far beyond a well-scoped MCP surface. Even a complex memory system does not justify dozens of overlapping retrieval, context, compression, and verification tools; the sheer count will bloat agent context and make selection costly.

    Completeness4/5

    The surface covers the domain unusually well: CRUD on memories, multiple search modes, relation traversal, namespaces, goals, thought tiles, spatial context, import/export, and integrity verification are all present. Minor gaps remain, such as no explicit relation deletion and limited user-model maintenance, but they are not critical for core workflows.

    Maintenance

    ActivitySlowing
    ResponsivenessNo issues

    Resources