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

Monan SDK

Monan SDK is a TypeScript framework for creating and orchestrating AI agents with Bun, with a CLI for interactive execution and API serving. Its documented capabilities include local inference through Ollama, OpenRouter-backed cloud models, SQLite vector storage, agent routing, workflows, and developer-defined tools.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Monan SDK — 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 Monan when building a Bun-based TypeScript application that needs code-defined agents, CLI-managed execution, and documented options for model routing or workflow orchestration.

Who it is for

  • TypeScript developers building AI agents with Bun.
  • Teams that want to route requests among agents or compose agents into workflows.
  • Developers who want to run local models through Ollama or connect to cloud models through OpenRouter.

Documented uses

  • Define an agent in TypeScript and run it in interactive chat mode.
  • Expose an agent through a CLI-started API server.
  • Route requests to different agents based on intent or complexity.
  • Chain agents, run tasks in parallel, and provide agents with custom tools.
  • Use local Ollama models or OpenRouter-connected cloud models.
Before you choose

Requirements & limits

The repository is public and lists an MIT license. Its README requires the CLI to run and test agents and identifies the project as Alpha and in active development.

  • The framework is built for Bun and uses TypeScript.
  • Local model execution requires Ollama to be running in a separate terminal.
  • Cloud-model examples use OpenRouter and include an API token or the OPEN_ROUTER_API_KEY environment variable.
  • The README says PII masking is enabled by default for external calls and can be disabled.
  • The project is Alpha, so features may change.

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

Define and run an agent with Ollama

Create a TypeScript agent and start it in interactive mode using a local Ollama model.

Before you start

  • Bun
  • The Monan SDK and its CLI
  • Ollama and a selected local model
  • Ollama serving in a separate terminal before agent execution

Steps

  1. Install the SDK with bun add monan-sdk and install the CLI with bun add -g monan-sdk.

  2. Create src/agent.ts, import Agent from monan-sdk, and export an agent configured with a name, model, and description.

  3. Start Ollama with ollama serve in a separate terminal.

  4. Run monan test assistant:src.agent to open the documented interactive test mode.

Expected outcome

The CLI starts the exported agent in an interactive chat session.

Guide limitations

  • The README marks the framework Alpha and says features may change.
  • The example command assumes the exported agent is named assistant in src/agent.ts.
Documentation 1 ↗
Source-based practical guide

Expose an agent through a local API

Run a code-defined agent through Monan’s CLI as an API server.

Before you start

  • Bun
  • The Monan SDK and its CLI
  • An exported agent in a TypeScript source file
  • A configured model; Ollama must be running separately when using a local model

Steps

  1. Install the SDK with bun add monan-sdk and the CLI with bun add -g monan-sdk.

  2. Create and export an agent in src/agent.ts.

  3. Run monan run assistant:src.agent --port 3000.

Expected outcome

The README says the CLI starts an Elysia server at `http://localhost:3000` and provides documentation at `http://localhost:3000/docs`.

Guide limitations

  • The repository identifies Monan as Alpha and notes that features may change.
  • The documented command uses the example export name and source path.
Documentation 1 ↗
COMPARE OPTIONS

Compare options for Agent orchestration

These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.

ProjectDocumented purposePlatformAccess and requirements
Monan SDKDefine an agent in TypeScript and run it in interactive chat mode.Linux, macOS, Server, WindowsThe repository is public and lists an MIT license. Its README requires the CLI to run and test agents and identifies the project as Alpha and in active development.
AgeniteDefine typed tools with JSON Schema validation and error handling.CLI
VeldraCreate an agent with a policy, tools, skills, knowledge base and reasoning method.Self-hostedThe documented deployment is self-hosted and uses a sign-in gate after a first-run administrator account is created.
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
16 October 2026
Original website title
Monan-AI/monan-sdk · Official homepage title · retained in its source language
How we review sourcesSuggest a correction