Framework-agnostic helpers for building A2UI subagent tools — op builders, prompt assembly, history walkers, and validation against Google's a2ui-agent-sdk.
Project description
ag-ui-a2ui-toolkit
Framework-agnostic helpers for building A2UI subagent tools.
Each per-framework adapter (LangGraph, ADK, Mastra, …) composes these helpers with its own framework-specific glue: tool decorator, runtime accessor, model binding + invoke. Nothing in this package depends on any agent framework.
Surface
- Constants:
A2UI_OPERATIONS_KEY,BASIC_CATALOG_ID - Op builders:
create_surface,update_components,update_data_model RENDER_A2UI_TOOL_DEF- State + history helpers:
build_context_prompt,find_prior_surface - Prompt composer:
build_subagent_prompt - Output:
assemble_ops,wrap_as_operations_envelope
See also
The TypeScript counterpart lives in
@ag-ui/a2ui-toolkit and exposes the
same surface in camelCase.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file ag_ui_a2ui_toolkit-0.0.1a0.tar.gz.
File metadata
- Download URL: ag_ui_a2ui_toolkit-0.0.1a0.tar.gz
- Upload date:
- Size: 3.9 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: poetry/2.1.3 CPython/3.11.9 Darwin/24.1.0
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
9916e4c58096cdca054afaa35103f1e9b92fbf47e06a1f3244112f98326ee8ec
|
|
| MD5 |
87ea8a5ea8ad04961a450771fc734cc9
|
|
| BLAKE2b-256 |
4dbda56e16f27000ad30989ceedb022d9a170aa225059c608ce031aff8e6eacd
|
File details
Details for the file ag_ui_a2ui_toolkit-0.0.1a0-py3-none-any.whl.
File metadata
- Download URL: ag_ui_a2ui_toolkit-0.0.1a0-py3-none-any.whl
- Upload date:
- Size: 4.9 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: poetry/2.1.3 CPython/3.11.9 Darwin/24.1.0
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
10dd66dc48ae82cd31bc14bd28bac6aec4e7885c45b5913700f10f6917cffcc1
|
|
| MD5 |
907a0814fc76ccc09fbc1b2a7d871bf1
|
|
| BLAKE2b-256 |
fe2f096656eb0062ea6a15d1c846659f3bbe8bb75ef8d40c5ab6802d9db40fa4
|