Skip to main content
Glama
ambermem

Amber

Official
by ambermem

Related Servers

Alternatives to Amber

  • A
    license
    A
    quality
    A
    maintenance
    Hand a project over — to your next session, to Cursor/Codex/Gemini, to your successor — with the reasons attached. Local-first memory MCP for coding agents: decisions re-injected before the agent acts, drift detection across every project you run. One SQLite file, nothing leaves your machine.
    8
    190 npm
    14
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    Two-layer memory for AI agents. Episodes compress into identity. The only MCP memory server with an immune system. Patterns earn permanence through evidence, false knowledge gets caught and demoted, and stale information fades — so your agent's memory gets smarter over time, not just bigger. Zero dependencies. 5 tools. Works with any MCP client.
    16
    391 PyPI
    11
    MIT
  • A
    license
    Not graded
    quality
    Not graded
    maintenance
    Provides AI agents with persistent long-term memory capabilities using semantic search. Enables storing, retrieving, and searching memories through three core tools integrated with Mem0 and vector storage.
    MIT
  • A
    license
    Not graded
    quality
    D
    maintenance
    A template implementation of the Model Context Protocol server that integrates with Mem0 to provide AI agents with persistent memory capabilities for storing, retrieving, and searching memories using semantic search.
    MIT

Related Servers

  • F
    license
    B
    quality
    D
    maintenance
    Enables persistent memory for AI systems by providing tools for episodic, semantic, and procedural data storage through a vector-and-graph-enhanced database. It allows models to maintain long-term continuity using similarity search, thematic clustering, and identity tracking.
    24
    1
    -
  • A
    license
    A
    quality
    D
    maintenance
    Provides persistent long-term memory for AI agents through semantic search and automated knowledge graph extraction. It enables agents to store, recall, and reason over facts, preferences, and relationships across multiple conversations and sessions.
    14
    14 npm
    MIT
  • A
    license
    A
    quality
    D
    maintenance
    Gives AI assistants a persistent memory across conversations, allowing them to remember user preferences, notes, and facts between chats.
    6
    54 npm
    MIT
  • F
    license
    Not graded
    quality
    D
    maintenance
    Provides AI agents with persistent, searchable memory that survives across conversations using semantic search, temporal versioning, and smart organization. Enables long-term context retention and cross-session continuity for AI assistants.
    14
    -
  • A
    license
    Not graded
    quality
    D
    maintenance
    Provides persistent memory for AI assistants, enabling context retention across sessions through hybrid search and memory management tools.
    1
    MIT

TDQS

A4.6/5.0

Scored across 18 tools

Disambiguation5/5

Each tool targets a distinct resource or action: active memories, deleted memories, store tasks, account status, subscription management, and account deletion are all clearly separated. The only close pairs (search vs. list, active vs. deleted) are explicitly differentiated by purpose, so an agent should rarely misselect.

Naming Consistency5/5

Every tool follows the amber_<verb>_<object> pattern in snake_case, such as store_memory, list_deleted_memories, cancel_account_deletion, and reactivate_subscription. Multi-word objects like store_task_status or feedback_to_developer still fit the imperative-verb convention and are easy to predict.

Tool Count4/5

Eighteen tools is slightly above the ideal 3–15 range, but nearly every tool earns its place: about ten cover memory operations and the rest cover subscription/account lifecycle plus feedback/notifications. It feels slightly heavy because memory management and account management are bundled, but no tool is redundant.

Completeness4/5

The memory lifecycle is well covered: store with async status, search, get, list, soft-delete, restore, trash search/browse, and export. The main gaps are the lack of an update/edit operation for existing memories and no permanent single-memory purge, though agents can work around these by storing corrections or using account deletion.

Maintenance

ActivityMaintained
ResponsivenessResponsive