Amber
OfficialRelated Servers
Alternatives to Amber
- AlicenseAqualityBmaintenanceHand 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.71,683 npm16MIT
- AlicenseAqualityDmaintenanceSmart memory for AI agents. Solves the Karpathy problem: memories decay, topics are frequency-weighted, one-time questions don't become obsessions. 7 tools. Zero deps.42MIT
- AlicenseAqualityBmaintenanceTwo-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.172,731 PyPI12MIT
- AlicenseNot gradedqualityNot gradedmaintenanceProvides 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
- AlicenseNot gradedqualityDmaintenanceA 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
- AlicenseNot gradedqualityDmaintenanceA Model Context Protocol server that provides AI agents with persistent memory capabilities through Mem0, allowing them to store, retrieve, and semantically search memories.687MIT
Related Servers
- FlicenseBqualityDmaintenanceEnables 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.241-

Memsolus MCP Serverofficial
AlicenseAqualityDmaintenanceProvides 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.146 npmMIT- AlicenseAqualityDmaintenanceGives AI assistants a persistent memory across conversations, allowing them to remember user preferences, notes, and facts between chats.636 npmMIT
- FlicenseNot gradedqualityDmaintenanceProvides 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-
- AlicenseAqualityCmaintenanceProvides persistent, searchable memory for AI agents, enabling them to retain, recall, and reflect on information across conversations.1932 PyPI1MIT
- AlicenseNot gradedqualityDmaintenanceProvides persistent memory for AI assistants, enabling context retention across sessions through hybrid search and memory management tools.1MIT
TDQS
Scored across 29 tools
Most tools target a clearly distinct operation, and the potentially confusable pairs (list vs search, active vs trash, export vs backup key, upload vs import from URL) are explicitly contrasted in the descriptions. The main residual friction is the overloaded word 'restore' (amber_restore_memory for un-deleting vs restoring a backup via upload_backup/import_memories) and the three near-identical status-polling tools, which an agent must map by task type rather than by name alone.
Every tool uses the same amber_ prefix plus lowercase snake_case with a verb_noun shape (store_memory, delete_memory, list_subjects, get_import_status). No camelCase or style mixing anywhere, and the verb choice reliably signals read vs write (list/get/search vs store/update/delete/restore).
29 tools is heavy for one server and spans several sub-domains beyond the core memory CRUD (subscription billing, backup keys, import/export plumbing, feedback, notification dismissal). Each tool does have a real job, but the surface is at the upper edge of what an agent can hold, and peripheral capabilities like backup-key rotation and feedback submission arguably belong in a separate administrative surface.
Coverage is unusually thorough: writes, reads, search, subject/topic hygiene, soft-delete and restore, trash browsing, account and subscription lifecycle, export/import and async status polling are all present. The notable gap is that deletion is only ever soft — there is no way to permanently purge a memory or empty the trash, so an agent cannot fully complete a 'delete this forever' request.