Store important facts, decisions, user preferences, and project context for long-term retrieval. Memories persist across sessions with automatic chunking and duplicate detection.
MIT
400,891 tools. Last updated 2026-08-06 09:56
"Methods to Store and Learn Dynamic Context Memories" matching MCP tools:
- Retrieve saved memories at session start to restore context, installed skills, and user preferences. Filter by type for specific categories.MIT
- Store observations as persistent memories with optional tags, importance levels, context, and auto-expiration to manage AI agent memory.MIT
- Process raw conversation messages to automatically extract and store useful memories, facts, decisions, preferences, and lessons.MIT
- Retrieve relevant memories for user queries to fetch prior context, preferences, and facts before responding.MIT
- List all stored memories for the current user from both Arc and Atlas in the shared store.MIT
Matching MCP Servers
- AlicenseAqualityDmaintenanceA Model Context Protocol (MCP) server that injects 'Just-in-Time' context into AI conversations based on file paths and glob patterns.Last updated1291ISC
- Alicense-qualityCmaintenanceEnables AI assistants to interact with Databricks workspaces, running SQL queries, managing jobs, and exploring schemas via the Model Context Protocol.Last updated1GPL 3.0
Matching MCP Connectors
Official Microsoft Learn MCP Server – real-time, trusted docs & code samples for AI and LLMs.
Personal finance, bank account, and shared memory connector for Claude, ChatGPT, Gemini Spark & more
- Extract and store important information from conversations to maintain persistent memory across interactions, enabling AI assistants to recall facts and user context.MIT
- Retrieve project context at session start: recent memories and an AI summary covering architecture, tech stack, and patterns. Use this to avoid manual memory recall.MIT
- Store durable preferences, decisions, and facts as persistent memories accessible across any connected AI tool and session. Invoke proactively whenever you learn something meaningful.MIT
- Store important information, decisions, patterns, and preferences for future recall. Supports single memories or batch imports of up to 500 memories, with options to correct or supersede existing memories.MIT
- Retrieve aggregate counts of stored memories and session events for monitoring. Check store health or confirm data was saved after a session.MIT
- Save information like preferences, lessons, or project context to a persistent local database. Memories are retained across sessions and can be retrieved later.MIT
- Retrieve paginated memories from an agent's archival store with search, sorting, and filtering capabilities.MIT
- Check for duplicate titles, stale memories, oversized notes, and unresolved wikilinks to maintain memory store health without altering files.MIT
- Store key decisions, insights, or notes in a private memory wiki that auto-titles, tags, and links them to related memories for easy future recall.MIT
- Audit memory store health: view totals, categories, stale memories, near-duplicates, and expired references. Read-only.AGPL 3.0
- Gather the most reflection-worthy memories by importance and recency, then synthesize and store higher-level insights linked to their source memories.PolyForm Noncommercial 1.0.0
- Retrieve and decrypt memories from an encrypted store to restore past context. Use with a keyword to filter or leave empty to load all.Apache 2.0
- Starting a project? Retrieve relevant memories from its path and return a compressed summary to restore working context.MIT
- Store text memories in an agent's archival memory for later retrieval and management within the Letta system.MIT