Skip to content

DashScope AgenticX

v1.0.2 Python 3.10+ MIT

Enterprise AI experts, built to act. AgenticX is a Python agent runtime for building and running domain experts. It connects models, tools, skills, permissions, and persistent sessions through one runtime, with a terminal interface and APIs for embedded applications.

Use it directly as a local assistant, embed it in a Python application, or package a domain expert as a versioned App Bundle. DashScope SDK Expert and Bailian Expert are bundled expert templates illustrating this application layer.

Features

  • One runtime


    Instance-owned tool, skill, hook, and session state; shared construction through RuntimeBuilder.

  • Terminal & TUI


    A full interactive CLI with 40+ slash commands, plus an optional Textual TUI with rich Markdown output.

  • Embeddable SDK


    run_once, run_stream, and typed run_events for scripts, CI, IDE plugins, and applications.

  • Tools & skills


    Filesystem, shell, web, browser, camera, MCP services, markdown skills, and declarative TOML extensions — no code required.

  • Governed execution


    Permission tiers, policy files, OS sandbox backends, audit log, privacy mode, and event hooks.

  • Apps & experts


    Versioned App manifests with checksum verification and permission diffs; one-command expert workspace initialization.

Requirements

  • Python 3.10+ (Pillow-backed vision/media extras need 3.11+).
  • A model API key for your provider — for the default Tongyi/DashScope provider:
export DASHSCOPE_API_KEY="<your-api-key>"

Installation

python -m pip install "dashscope-agenticx[tui]"
agenticx --version

For a minimal, non-TUI install use pip install dashscope-agenticx and start with agenticx --cli. Optional extras (provider SDKs, web, browser, media) are listed in Quickstart.

Examples

Run it in the terminal

agenticx                                    # interactive session
agenticx -c "Summarize this project"        # one-shot, then exit

Run it from Python

from dashscope_agenticx.sdk import run_once_sync

reply = run_once_sync("Inspect this project's structure without changing files")
print(reply)

Consume typed events

import asyncio

from dashscope_agenticx.sdk import run_events


async def main():
    async for event in run_events("Summarize the project"):
        print(event.type.value, event.payload)


asyncio.run(main())

One-shot runs execute tools, not just generate text — start in a suitable workspace and choose permissions appropriate to the task.

Where to go next

AgenticX is not a hosted service, a hardened OS sandbox, or a complete workflow platform. Voice, camera, browser, web search, scheduler, and experimental features are optional, not prerequisites for the core runtime.