Skip to main content
Glama
phillipclapham

anneal-memory

by phillipclapham
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

Related Servers

Alternatives to anneal-memory

  • Amber by ambermem

    Amberofficial

    ambermem
    A
    license
    A
    quality
    B
    maintenance
    Gives your AI persistent memory across conversations. Stores facts automatically, finds them by meaning using hybrid search with query expansion, and organizes everything into topics without manual tagging.
    18
    1
    MIT

Related Servers

  • mnemosis-mcp

    liyexiaoyi
    A
    license
    C
    quality
    A
    maintenance
    Provides AI agents with a human-inspired memory layer via MCP, enabling episodic and semantic memory recall, forgetting curves, consolidation, and contradiction detection. It integrates with MCP clients to offer local-first, dependency-free memory management.
    98
    1
    MIT

  • mnemo

    krat214
    A
    license
    Not graded
    quality
    B
    maintenance
    Persistent memory MCP server for AI agents, featuring a visual interface to browse, search, edit, and delete memory. It provides tools for capturing episodes, recalling, consolidating, crystallizing traits, and forgetting, with local SQLite storage and optional authenticated web UI.
    MIT

  • GroundMemory

    huss-mo
    A
    license
    Not graded
    quality
    A
    maintenance
    An MCP-native, local-first memory server that gives AI agents persistent, structured memory across sessions and tools, enabling them to maintain identity and context without reconfiguration.
    3
    MIT
  • dakera-mcp by Dakera-AI

    dakera-mcpofficial

    Dakera-AI
    A
    license
    A
    quality
    B
    maintenance
    Self-hosted MCP-native agent memory server. Gives AI agents persistent, decay-weighted memory via 83 MCP tools — no cloud, full control. RocksDB+HNSW backend. Works with Claude Code, Cursor, and any MCP-compatible agent.
    14
    8
    MIT
Deploy Server
Context All Your Agents Can ShareAgents share what they learn, hand off work, and hold it when you switch models. Start with 5 GB free.fulcradynamics.comAd

TDQS

A3.7/5.0

Scored across 17 tools

Disambiguation4/5

Most tools target distinct resources (episodes, spores, crystals, wraps), and tricky pairs like spore_touch vs spore_update and spore_descend vs spore_ascend are explicitly differentiated in their descriptions. The main soft spots are spore_list vs spore_surface (both enumerate open spores) and recall vs crystal_recall (both surface 'durable facts'), which require careful reading to separate.

Naming Consistency3/5

Names are domain-grouped (spore_*, crystal_*, wrap_*) but ordering conventions are mixed: noun_verb (spore_list, crystal_recall, wrap_cancel) sits alongside verb_noun (prepare_wrap, save_continuity, delete_episode) and bare verbs (record, recall, status). It remains readable and largely predictable within the spore_ and crystal_ families, but the global pattern is inconsistent.

Tool Count4/5

17 tools is slightly above the ideal band but justified by three genuinely distinct memory layers (episodic/continuity, prospective spores, crystallized patterns) plus health/diagnostics. Each tool earns its place; the eight spore_* tools are the heaviest cluster but map to a real state machine.

Completeness4/5

Coverage is strong across the lifecycle: episodes (record/recall/delete), continuity (prepare_wrap/save_continuity/wrap_cancel), spores (add/get/update/touch/list/surface/descend/ascend), crystals (index/recall), and status. Minor gaps like fetching a single episode by ID or any direct episode correction path (intentionally delegated to re-recording) are workable around.

Maintenance

ActivityActive
ResponsivenessUnresponsive

Resources