Understand the project
Practical overview
When it fits
Use it when you want a code-first agent framework with model-provider flexibility and control over execution limits and lifecycle events.
Who it is for
- Developers building custom AI agents in Python or TypeScript.
- Teams integrating agent behavior into applications across local, server, cloud or self-hosted environments.
- Engineers needing explicit controls over agent execution.
Documented uses
- Build custom AI agents.
- Create an in-process agent harness with turn and token limits.
- Add tool use to production agents.
- Implement cancellation and stop-reason handling.
- Develop agents using supported model providers.
Before you choose
Requirements & limits
The project is publicly available as open-source software under the Apache-2.0 license. The evidence does not specify pricing or account requirements.
- Python and TypeScript support
- In-process execution without a required hosted control plane
- Model-provider flexibility
- Built-in turn limits, token budgets, cancellation and stop-reason handling
- Tool integration for production agents
Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.
Evidence and transparency
Sources & review
Source record details
- Source availability
- Active
- Sources checked
- 30 September 2026
- Original website title
- strands-agents/harness-sdk · Official homepage title · retained in its source language