Store important facts, decisions, user preferences, and project context for long-term retrieval. Memories persist across sessions with automatic chunking and duplicate detection.
MIT
734,658 tools. Updated 2026-11-02 07:20
"Methods to store and persist memories for AI systems" matching MCP tools:
- Identify POS hardware, kitchen display systems, and online ordering gateways for a store by brand and store ID. Use for competitive tech auditing and vendor market share tracking.MIT
- List AI-generated memory categories in a bucket with overviews and recent memories, so you can decide which categories to load fully.MIT
- List all AI systems in your workspace with registration status and evidence coverage to identify unregistered systems and gaps before the EU AI Act deadline.MIT
- Retrieve relevant saved memories from past AI conversations using hybrid semantic and keyword matching. Results are ranked by relevance and may include temporary image URLs.MIT
- Save or replace a user preference across projects and return its key, title, and value, enabling agents to persist conventions as user-scoped memories for reuse.MITDestructive
Matching MCP Servers
- AlicenseAqualityCmaintenanceEnables structured extraction of methods and reproducibility heuristics from academic papers, allowing AI agents to obtain metadata, full text, structured methods, code repository discovery, and a no-clone reproducibility verdict from a paper URL.835 PyPIMIT
- AlicenseAqualityBmaintenanceEnables local coding agents to manage disposable Colab GPU runtimes, restore and save Google Drive checkpoints, execute scripts, and safely stop VMs through MCP stdio tools.9MIT
Matching MCP Connectors
Research methods for AI assistants: study design guidance, R and Python code, and citations
BOLD Systems (Barcode of Life Data System, University of Guelph) — the global DNA barcode…
- Process raw conversation messages to automatically extract and store useful memories, facts, decisions, preferences, and lessons.MIT
- Store up to 20 memories in a single API call for bulk imports or multi-fact storage. Ideal for populating an AI assistant's memory efficiently.MIT
- Persist and retrieve key-value memory for AI agents across sessions. Supports store, recall, list, and delete operations up to 16 KB per key.MIT
- List all stored memories for the current user from both Arc and Atlas in the shared store.MIT
- Extract and store important information from conversations to maintain persistent memory across interactions, enabling AI assistants to recall facts and user context.MIT
- Persist agent memories (facts, decisions, context) with an importance score to control decay and retention.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
- Fix AI mistakes by storing corrections that always appear first. Override previous memories with accurate behavior.MIT
- Retrieve REST API endpoint details for AgentOS resources, including HTTP methods, parameters, and response schemas.MIT
- Store and persist conversation memories for AI agents. Supports episodic, semantic, and procedural memory types with adjustable importance weights.MIT
- Save durable, searchable memories for decisions, facts, preferences, and lessons. Indexes immediately, persists across sessions, and is recallable from any MCP host.MIT
- Store memory in one of two modes — single-memory (set top-level `content`) or batch (set `memories: [...]` for up to 500).MIT
- Retrieve paginated memories from an agent's archival store with search, sorting, and filtering capabilities.MIT
- Export memories from Project Tessera to migrate knowledge to other AI platforms like ChatGPT or Gemini using supported formats.AGPL 3.0
- Deduplicate similar memories, apply time-based decay, clean low-value entries, and detect patterns for rule promotion to maintain a healthy memory store.MIT