Linksee Memory
Related Servers
Alternatives to Linksee Memory
- AlicenseAqualityBmaintenanceGives 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.291MIT
Related Servers
- AlicenseNot gradedqualityBmaintenanceLocal-first, file-based memory layer for AI agents — one shared Markdown vault across Claude, Codex, Gemini, Cursor and any MCP client. Provides read/write memory tools with an audit trail, per-agent trust levels, and Git sync; no cloud and no lock-in.2MIT
- FlicenseNot gradedqualityCmaintenanceLocal-first cross-agent memory for AI coding agents. Persistent, shared memory over MCP — what you tell one agent can be recalled by another — with all data stored in a single local SQLite file, no cloud and no API keys.-
- AlicenseAqualityDmaintenancelocal-first long-term memory for MCP agents (no DB, no API keys)313 npmMIT
- AlicenseAqualityCmaintenanceLocal-first persistent memory for coding agents and MCP clients. It keeps important project context across sessions and reduces wasted tokens by retrieving only relevant memories instead of replaying unnecessary history.81MIT
- AlicenseNot gradedqualityDmaintenanceLocal-first AI memory layer with hybrid retrieval and brain-inspired namespaces. Enables agents to save, search, and manage memories directly via MCP tools.MIT
- AlicenseAqualityCmaintenanceLocal-first, source-traceable memory for AI agents — no LLM at ingest, $0 per message, zero data egress. Gives Claude Code, Cursor, and any MCP client one shared persistent memory with semantic recall, belief revision, selective forgetting, and a provenance guard that blocks acting on stale or unconfirmed memories.2318 PyPI14MIT
TDQS
Scored across 7 tools
remember vs declare_anchor both create decision anchors (remember docs even say 'add anchor: {}'), and recall's no-arg brief / dream modes overlap heavily with drift_status's 'what needs attention at session start'. The boundaries exist but require careful reading of long descriptions to resolve, and read_smart is a file reader dropped into a memory server, which muddies the set's identity.
Naming mixes bare verbs (remember, recall) with verb_noun compounds (declare_anchor, resolve_drift, share_draft) and a noun_verb style (drift_status), plus read_smart. All names are readable and mostly snake_case, but there is no single predictable pattern for an agent to infer new tool names from.
Seven tools is a well-scoped count for a memory + drift system, and each broadly maps to a distinct phase (write, read, observe, remediate, share). read_smart and share_draft feel like adjacent add-ons rather than core, but the set is not bloated.
Memory lifecycle is covered via remember (create/update/delete) and recall (search, file history, brief), and drift has status/declare/resolve. Minor gaps remain: no way to delete or edit an existing anchor outright, and no explicit list-all-memories listing beyond recall's modes.