Save, search, and manage long-term memories across conversations. Set preferences, facts, and skills; recall them later by topic.
MIT
750,862 tools. Updated 2026-11-06 11:15
"Memory" matching MCP tools:
- Retrieve relevant memories from a markdown corpus using hybrid search, then answer state questions with latest, trace sequences with thread, verify git claims, and import external notes.MIT
- Persist and retrieve semantic memory across sessions. Supports storing key-value entries, appending fragments, editing sections, and semantic search.MIT
- Retrieve, edit, promote, demote, or purge AI agent knowledge nodes while preserving learning state. Check accessibility state to ensure reliable retrieval.AGPL 3.0
- Manage and retrieve stored AI-agent memories: search, list, get by rid, archive, restore, update importance, submit relevance feedback, and access current chain-head or history.MIT
- Legacy dispatcher for backward compatibility; use add/search/list/update/delete/export/import/archive/restore/consolidate/stats to manage persistent AI context.Apache 2.0Destructive
Matching MCP Servers
- AlicenseAqualityBmaintenanceEnables MCP-capable coding agents to semantically search, store, and inspect a single local, cross-tool index of session histories and project docs. Agents can retrieve what other tools and prior sessions already discovered.3MIT
- AlicenseAqualityAmaintenanceGives every AI agent on a machine a shared, local-first long-term memory: 16 tools to save, search, edit and organize structured notes in one SQLite file, with attribution per client. Runs over stdio or localhost HTTP, so Claude Code, omp and any other MCP client recall the same facts, decisions and entities.1625 PyPIMIT
Matching MCP Connectors
- List review-memory entries to spot dead pricing via lastApplied timestamps and identify repeated rules for promotion to glob memory or profile rules.AGPL 3.0
- Store and manage persistent facts across sessions. Add, view, update, or remove structured memories organized by sections like work, personal, and preferences.MIT
- Store, search, read, and update shared AI coding context with conflict arbitration, enabling tools like Codex, Cursor, and Claude Code to reuse structured notes across sessions.Apache 2.0
- Store and retrieve temporary key-value data during development workflows, supporting set, get, list, delete, search, and clear operations with tag-based organization.MIT
- Manages conversation memory through hierarchical storage, adaptive retrieval, compression, knowledge graphing, inspection, and curation to maintain context integrity in long AI dialogues.MIT
- Retrieve Linux RAM and swap usage to check system health, monitor resource consumption, and diagnose pressure on homelab hosts.MIT
- Inspect JS heap size, DOM node counts, and event listeners, or capture DevTools-compatible heap snapshots that summarize large object classes and detached DOM nodes.Apache 2.0
- Store project notes, recall context, search memories with hybrid semantic and keyword retrieval, cluster related items, deduplicate, archive old memories, and set permanent rules for persistent session intelligence.MIT
- Persist AI discoveries with save, recall, and search actions. Organize insights by category and retrieve by task or query.MIT
- Manage persistent shopping memory: read or write T1D config, preferences, and notes. Use get, set, or note actions to retrieve or update saved information.-
- Changes agent memory, markdown files under /memories, with the writing commands of Anthropic's memory tool; memory_view reads it. Each file is a static.md note in the user's /memories folder: /memories/projects/static-md.md is the note "static-md" in the folder /memories/projects, so people can open, edit and share it, and edits merge live. create writes a file, replacing the text of one that exists. str_replace replaces old_str, which must occur exactly once, with new_str. insert puts insert_text after line insert_line (0 for the top). delete removes a file, or a directory with everything in it. rename moves a file or directory from old_path to new_path. File names: up to 32 characters before ".md", of letters A-Z, digits, "-", "_" and "."; directories up to 9 levels. Encrypted notes are refused.ConnectorDestructiveOAuth
- Persistent memory storage — docs, runbooks, specs, ADRs, RFCs, decisions, lessons, preferences, tasks, todos, knowledge nodes, transcripts. NOT for codebase/file search (use `search`). Finding a doc, runbook, spec, ADR, or decision? Use this tool, NOT `find`, `ls`, `grep`, or filesystem search: ContextStream docs are not on disk. Start with memory(action="search", query="…") (memory nodes and relevant docs together), then memory(action="list_docs", query="…") + get_doc (ID or natural-language title query), memory(action="decisions", query="…"), or session(action="recall", query="…") for past sessions. Elsewhere: plans → session(action="capture_plan"); tickets/handoffs → entity; lessons → session; bundles → capsule. create_task is a lightweight todo, not a ticket (pass plan_id + plan_step_id for plan tasks). Actions include create_decision, create_node, create_event, create_task, create_todo, create_diagram, create_doc, list_transcripts. Full action reference: the `action` parameter.ConnectorOAuth
- Long-term memory behind your key: add facts (deduplicated by meaning), recall by meaning with an optional recency boost, list, forget. Spaces per user or agent, 20 000 items. Add billed per item. Cost €0.001 per operation, charged to the API key in Authorization: Bearer. Parameters — op: search (default) | add | list | spaces | delete; space: namespace, e.g. user:42 (default 'default'); text: memory text for add; items: JSON array [{text, meta}] for batch add; meta: JSON object; query: what to recall; top_k: 1–50 (default 5); recency: 0–1, weight of freshness (default 0); ids: ids to delete, comma-separated; all: bool, delete the whole space.ConnectorNo auth
- Agent memory system: create, list, search, and delete persistent memories. Memories persist across sessions and can be searched by vector similarity. Requires API key.ConnectorNo auth
- Save a memory in CortexPlus. CortexPlus decides whether it is a note, task, or reminder and extracts the client.ConnectorNo auth