mirror of
https://github.com/agent0ai/agent-zero.git
synced 2026-05-17 04:01:13 +00:00
daf95ec3ab
Standardize multi-action tools around tool_args.action while keeping parser compatibility for older tool/args, tool_name:action, and method-shaped requests. This keeps new prompts clean without breaking agents that learned the previous dialect. Move A0 connector remote execution/file tools into stable standard prompts, make remote targeting independent of the active chat context, and skill-gate beta computer-use remote so it no longer weighs down the always-on tool list. Align text editor, scheduler, skills, office artifact, memory, notify, and browser prompts/tools around the canonical action contract. Add scheduler update/timezone handling, skills_tool read_file, text editor patch coverage, and fixes for memory_forget, behaviour_adjustment, and code execution progress warnings. Reduce default prompt pressure by compacting browser and scheduler prompts into skill-backed manifests, shortening skill catalog descriptions, and pruning noisy framework knowledge. Remove obsolete connector prompt stubs and root tool-call knowledge examples. Tests: conda run -n a0 pytest tests/test_a0_connector_prompt_gating.py tests/test_tool_action_contracts.py tests/test_task_scheduler_timezone.py tests/test_text_editor_context_patch.py tests/test_tool_request_normalization.py tests/test_office_document_store.py::test_odf_is_advertised_and_docx_remains_explicit_compatibility tests/test_office_document_store.py::test_document_artifact_accepts_method_alias_for_ods_create tests/test_skills_runtime.py tests/test_default_prompt_budget.py::test_a0_small_profile_removed_and_prompt_text_generic -q |
||
|---|---|---|
| .. | ||
| api | ||
| extensions | ||
| helpers | ||
| prompts | ||
| tools | ||
| webui | ||
| default_config.yaml | ||
| plugin.yaml | ||
| README.md | ||
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.
- 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.pyimplements FAISS storage, index loading, embedding configuration, and knowledge preload.
- Knowledge import
helpers/knowledge_import.pyimports external knowledge into memory storage.
- Consolidation
helpers/memory_consolidation.pycontains memory consolidation logic.
- Tools
tools/memory_save.pytools/memory_load.pytools/memory_delete.pytools/memory_forget.pytools/behaviour_adjustment.py
- API
api/memory_dashboard.pypowers the memory management dashboard.api/import_knowledge.pyandapi/knowledge_reindex.pyhandle 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.