mirror of
https://github.com/agent0ai/agent-zero.git
synced 2026-05-30 03:35:47 +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
888 B
888 B
Agent Zero Setup And Deployment
Docker image:
docker pull agent0ai/agent-zero
docker run -p 50001:80 agent0ai/agent-zero
Persist user data by mounting /a0/usr:
docker run -p 50001:80 -v /path/on/host:/a0/usr agent0ai/agent-zero
After first start, configure API keys, chat model, utility model, and embedding model in Settings. Embeddings are required for memory and knowledge recall.
For local development:
python -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt
pip install -r requirements2.txt
python run_ui.py
Typical troubleshooting:
- Web UI unreachable: check
docker ps, port mapping, and startup logs. - Model errors: verify provider, model name, and API key.
- Memory/knowledge not recalling: verify embedding config and reindex if needed.
- Host-local access: use A0 CLI connector tools, not Docker tools.