agent-zero/plugins/_memory
Alessandro a8a4f1456e Theme dark checkboxes and center memory dashboard selection
Use native dark checkbox surfaces with light checkmarks and a readable indeterminate mark, while preserving light-mode appearance and native keyboard and disabled states.

Center Memory Dashboard selection controls in their table cells and replace scaled checkboxes with consistent 16px dimensions. Document the shared styling and dashboard alignment contracts.

Verified checkbox states, keyboard toggling, and desktop/mobile appearance in the live WebUI, using sample memory rows for dashboard layout checks.
2026-09-08 15:13:17 +02:00
..
api Scope memory JSON compatibility to the dashboard 2026-08-23 16:49:03 +02:00
extensions Make bundled memory behavior reliable 2026-08-23 14:15:51 +02:00
helpers Merge pull request #1846 from Jehu/fix/memory-float32-json-serialization 2026-08-23 17:01:09 +02:00
prompts Hide disabled capabilities from system prompts 2026-08-31 01:55:40 +02:00
tools Coerce memory load numeric args 2026-07-02 17:29:40 +02:00
webui Theme dark checkboxes and center memory dashboard selection 2026-09-08 15:13:17 +02:00
AGENTS.md Theme dark checkboxes and center memory dashboard selection 2026-09-08 15:13:17 +02:00
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 Improve auto-memory extraction quality 2026-06-02 09:42:47 +02:00

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
    • Includes tools for saving, loading, deleting, forgetting, and behavior adjustment workflows.
  • 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_save.py
    • tools/memory_load.py
    • tools/memory_delete.py
    • tools/memory_forget.py
    • tools/behaviour_adjustment.py
  • 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.