agent-zero/plugins/_memory
Alessandro dc34830447 fix: preserve compatibility across tool plugin refactor
Initialize the scheduler store before snapshots. Preserve legacy memory calls and per-action permissions while advertising the unified tool, and retain saved policy IDs for moved tools. Restore legacy log rendering and connector tool events, and reject malformed boolean arguments by default.
2026-10-27 17:33:33 +01:00
..
api Scope memory JSON compatibility to the dashboard 2026-08-23 16:49:03 +02:00
extensions fix: preserve compatibility across tool plugin refactor 2026-10-27 17:33:33 +01:00
helpers feat(memory): unify memory tools under one action-based memory tool 2026-10-21 23:37:32 +03:00
prompts feat(memory): unify memory tools under one action-based memory tool 2026-10-21 23:37:32 +03:00
tests feat(memory): unify memory tools under one action-based memory tool 2026-10-21 23:37:32 +03:00
tools fix: preserve compatibility across tool plugin refactor 2026-10-27 17:33:33 +01:00
webui feat(memory): unify memory tools under one action-based memory tool 2026-10-21 23:37:32 +03:00
AGENTS.md fix: preserve compatibility across tool plugin refactor 2026-10-27 17:33:33 +01:00
default_config.yaml refactor - plugin names and builtin plugins 2026-03-10 22:20:53 +01:00
plugin.yaml refactor - plugin names and builtin plugins 2026-03-10 22:20:53 +01:00
README.md fix: preserve compatibility across tool plugin refactor 2026-10-27 17:33:33 +01:00

Memory

Provide persistent vector-based memory and knowledge retrieval for Agent Zero.

What It Does

This plugin stores memories and knowledge embeddings in a FAISS-backed vector database, exposes tools for saving and recalling memories, and provides APIs and UI support for browsing, importing, updating, and deleting memory entries.

Main Behavior

  • Persistent vector store
    • Creates and loads FAISS indexes per memory subdirectory.
    • Stores embedding metadata so the index can be rebuilt if the embedding model changes.
  • Knowledge preloading
    • Loads configured knowledge directories into memory when a database is initialized.
  • Memory tools
    • Uses one memory tool with load, save, delete, and forget actions.
    • Old memory_load, memory_save, memory_delete, and memory_forget calls use the same implementation. Existing action permissions remain effective; permission to load memory does not grant permission to delete it.
  • Automatic conversation memory
    • Stores durable preferences, project facts, and recurring constraints while filtering transient action-history fragments before insertion.
  • Dashboard APIs
    • Exposes search, delete, bulk delete, update, and subdirectory listing endpoints for the memory dashboard.
  • Scoped storage
    • Supports different memory subdirectories so memory can be separated by context or agent scope.

Key Files

  • Core memory engine
    • helpers/memory.py implements FAISS storage, index loading, embedding configuration, and knowledge preload.
  • Knowledge import
    • helpers/knowledge_import.py imports external knowledge into memory storage.
  • Consolidation
    • helpers/memory_consolidation.py contains memory consolidation logic.
  • Tools
    • tools/memory.py (single tool, action selects load, save, delete or forget)
  • API
    • api/memory_dashboard.py powers the memory management dashboard.
    • api/import_knowledge.py and api/knowledge_reindex.py handle knowledge import and reindexing.

Configuration Scope

  • Settings section: agent
  • Per-project config: true
  • Per-agent config: true

Plugin Metadata

  • Name: _memory
  • Title: Memory
  • Description: Provides persistent memory capabilities to Agent Zero agents.