Skip to content

DeconBear/actoviq-agent-sdk

Repository files navigation

Actoviq Agent SDK

CI Publish npm Package npm version Docs

English | Chinese

Documentation site: https://deconbear.github.io/actoviq-agent-sdk/

Actoviq Agent SDK is an experimental TypeScript SDK for building multi-tool, multi-session agents with a clean-first public API, MCP integration, memory helpers, and an optional compatibility bridge path.

This project is inspired by excellent agent projects and runtimes including Claude Code, Codex, Deepagents, and similar work in the ecosystem. Actoviq remains an independent project with its own public SDK surface and documentation.

This repository is still under active development. APIs and runtime behavior may continue to evolve. Issues and pull requests are very welcome.

Install

npm install actoviq-agent-sdk zod

For local examples, place your config at:

~/.actoviq/settings.json

You can also preload a custom JSON file with loadJsonConfigFile(...).

Quick Start

import { createAgentSdk, loadDefaultActoviqSettings } from 'actoviq-agent-sdk';

await loadDefaultActoviqSettings();

const sdk = await createAgentSdk();

try {
  const result = await sdk.run('Introduce yourself in one short sentence.');
  console.log(result.text);
} finally {
  await sdk.close();
}

Run the repository examples with:

npm run example:quickstart
npm run example:actoviq-interactive-agent
npm run example:actoviq-agent-helpers

Tutorials

If you want a ready-to-run terminal chat program with streaming output and tool calls, start with:

If you want the clean SDK path first, start with:

Bridge documentation is kept as compatibility guidance. New application work should prefer the clean SDK path first.

Contributing

Contributions are welcome. If you spot a bug, a documentation gap, or a parity issue, please open an issue or submit a pull request.

Licensed under the MIT License.

About

Actoviq Agent SDK is an independent, experimental agent SDK for practical multi-tool, multi-session, and bridge-assisted agent workflows, learned from the outstanding and valuable experience of Claude code, codex and deepagents.

Resources

License

Stars

Watchers

Forks

Packages

 
 
 

Contributors