Skip to main content
Glama
yamantaka520

agent-memory-os

by yamantaka520
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

Related Servers

Alternatives to agent-memory-os

Related Servers

  • SharedBrain

    awictor
    A
    license
    Not graded
    quality
    B
    maintenance
    Local-first, multi-user shared memory for AI agents with semantic search, offline support, and team synchronization.
    MIT

  • alaya

    SecurityRonin
    A
    license
    Not graded
    quality
    C
    maintenance
    A local memory engine for AI agents. Stores conversation episodes, consolidates knowledge through a neuroscience-inspired lifecycle, and builds a personal knowledge graph — all in a local SQLite database.
    17
    MIT

  • kepta

    DamianTodorovic
    F
    license
    Not graded
    quality
    A
    maintenance
    Local memory for AI agents in one SQLite file on your own machine. Facts carry a validity window and a confidence score, so an outdated one is superseded and downweighted rather than deleted, and retrieval fuses BM25, vector similarity and a knowledge graph.
    2
    -

  • polarmem

    m1kuno
    A
    license
    Not graded
    quality
    C
    maintenance
    A local-first memory engine for AI agents that stores embeddings in polar-quantized form in a single SQLite file, enabling private, compact, and human-like recall.
    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

A4.1/5.0

Scored across 12 tools

Disambiguation3/5

Most tools have distinct purposes, but memory_search, memory_context_pack, and memory_orchestrate_context clearly overlap in the recall/context-assembly space. The descriptions help somewhat by positioning each for different use cases, but an agent could still struggle to pick the right one.

Naming Consistency4/5

All tools share the memory_ prefix and use lowercase snake_case, which is a strong unifying pattern. Most names follow a verb-object structure, though memory_snapshot_diff, memory_context_pack, and memory_recall_feedback are slightly noun-heavy and break the otherwise predictable pattern.

Tool Count5/5

With 12 tools, the server covers a broad memory lifecycle without feeling bloated. Each tool earns its place in the set, and the count is well within the expected range for a domain-specific server.

Completeness3/5

The lifecycle covers add, search, update, share, link, and context snapshot operations, but there is no delete/forget tool and no way to remove a link between memories. These are notable gaps, though an agent can mostly work around them.

Maintenance

ActivityActive
ResponsivenessUnresponsive

Resources