OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Agent Frameworks

Baseai

BaseAI is a TypeScript framework for building AI agents from configurable pipes, memory and tools, with a documented workflow for local development and serverless deployment. Its README shows how to define an agent pipe, connect it to an application, and receive streamed output. The repository says BaseAI has been archived in favour of Langbase AI primitives.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Baseai — OpenViST project profile in Agent Frameworks.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use BaseAI when you need to understand or work with its documented TypeScript pipe workflow, especially in an existing project. For a new foundation, factor in the repository’s notice that it is archived in favour of Langbase AI primitives.

Who it is for

  • TypeScript developers prototyping agent-backed application features.
  • Developers exploring local agent pipelines that combine prompts, model settings, memory and tools.
  • Teams maintaining or assessing an existing BaseAI project.

Documented uses

  • Scaffold a BaseAI project with dedicated configuration, memory, pipe and tool directories.
  • Create an agent pipe and adjust its prompt and model parameters.
  • Integrate a pipe into a TypeScript app and handle streamed responses.
  • Explore a local-to-serverless agent workflow, while accounting for the repository’s archival notice.
Before you choose

Requirements & limits

The repository is public and identifies the project as open source. The supplied repository metadata does not state an explicit license.

  • The framework is TypeScript-first, with a documented project scaffold and agent-pipe configuration.
  • The README shows a streamed pipe integration using @baseai/core and event handling.
  • Local pipe runs require API credentials for the providers being used; the README says to keep keys server-side.
  • The repository says BaseAI is archived in favour of Langbase AI primitives, an important consideration for new projects. The repository metadata also reports that it is not archived, so the README’s project-status statem

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up a BaseAI project and configure a pipe

Initialize the TypeScript project structure, prepare provider credentials and create a pipe configuration.

Before you start

  • A TypeScript project and Node.js tooling that can run the documented npx commands.
  • A Langbase API key; provider API keys for the providers used in local pipe runs.

Steps

  1. Run the command below in the project to create the BaseAI configuration, memory, pipes and tools directories.

    Documented command
    npx baseai@latest init

  2. Add the required keys to server-side environment files, following the README’s distinction between the Langbase key and provider keys for local runs.

  3. Run the command below and provide the requested name and description to create a pipe under baseai/pipes.

    Documented command
    npx baseai@latest pipe

  4. Edit the pipe’s system prompt and model parameters as needed.

Expected outcome

A project scaffold and a configurable agent pipe are created; this guide covers setup, not deployment.

Guide limitations

  • The repository says BaseAI is archived in favour of Langbase AI primitives.
  • Provider keys are needed only for providers used in local pipe runs; the README directs users to Langbase keysets for Langbase.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
17 October 2026
Original website title
CommandCodeAI/BaseAI · Official homepage title · retained in its source language
How we review sourcesSuggest a correction

Related options

Langbase AI primitives — The repository names Langbase AI primitives, including memory, pipes and agents, as the successor direction and links to their documentation.