Search long-term memory to retrieve past user preferences, project decisions, or earlier context. Returns relevant matches ranked by semantic similarity.
MIT
344,212 tools. Last updated 2026-07-30 15:02
"Techniques and Strategies to Improve Long-Term Memory" matching MCP tools:
- Save important information to long-term memory with tags, collections, and workspace support. Append to existing memories to prevent duplicates.AGPL 3.0
- Renew expiring crypto loans by creating a new loan to repay the old one. Optionally add collateral to improve loan-to-value ratio and extend term.MIT
- Reduce memory bloat by merging near-duplicate memories and summarizing related clusters into concise long-term memories. Compress episodic experiences into semantic knowledge.MIT
- Resolve memory entry conflicts by applying priority, scope-narrow, time-bound, or merge strategies.MIT
- Promotes a session episode to a persistent engram for long-term memory retention, using episode ID from the timeline.Apache 2.0
Matching MCP Servers
- Alicense-qualityDmaintenanceA persistent, self-organizing memory MCP server for AI assistants, using semantic search, knowledge graphs, and reinforcement learning to automatically manage and retrieve memories.Last updatedMIT
- Alicense-qualityFmaintenanceA persistent, human-like memory system for AI companions in LM Studio, using SQLite and ChromaDB for hybrid storage, enabling seamless recall across sessions and models.Last updated33MIT
Matching MCP Connectors
Persistent long-term memory for AI agents: semantic search, knowledge graph, and task canvas.
Search events, conference weeks, cities, venues and artist schedules via remote MCP.
- Promote a working-memory entry to long-term memory and tombstone the original. Supports decision (fully wired) and future skill/playbook stores.MIT
- Save a session close summary to retain context for the next conversation. Automatically promotes soon-expiring short-term memories to long-term storage to ensure continuity.Apache 2.0
- Retrieve the athlete's full long-term coach memory, including PRs, goals, training context, and patterns, from stored markdown.MIT
- Save a conversation turn into long-term memory by curating topic, keywords, and typed links for a persistent concept graph.PolyForm Noncommercial 1.0.0
- Retrieve a ~300-character summary of a long-term memory chunk by ID. Use after recall to preview a relevant match before requesting the full text.Apache 2.0
- Trace the provenance of a long-term memory chunk to understand its origin, creation, and source material.Apache 2.0
- Analyze Bitcoin's market cycle position using eight key indicators including MVRV Z-Score, NUPL, and Puell Multiple to inform long-term positioning and trading strategies.MIT
- Deprecate outdated long-term memory chunks to keep recall results relevant. Flag incorrect or superseded information without deletion, with optional link to replacement.Apache 2.0
- Save important information from conversations into long-term memory to retain project preferences, coding conventions, and decisions across sessions.MIT
- Store important information such as decisions, preferences, and facts in long-term vector memory. Automatically deduplicates and filters noise for reliable recall across sessions.MIT
- Compress and merge your session into long-term memory. Provide structured blueprints, file anchors, and lessons to preserve architectural facts and fixes without raw code.MIT
- Store facts, preferences, or conversations in long-term memory. Optionally extract salient facts using an LLM before storage.Apache 2.0
- Semantically search long-term memory for insights, digests, and observations. Returns relevant snippet previews based on meaning, not exact keywords.Apache 2.0
- Retrieve the complete text of a long-term memory entry by its ID. Use this after recall or summary to access the full institutional memory.Apache 2.0