# Strands harness-sdk

> Updated 2026-09-22 · type: tool · category: ai-infrastructure · status: active · rev 1

Strands harness-sdk is an Apache-2.0 SDK for building in-process AI-agent harnesses that run model-agnostic across Bedrock, Anthropic, OpenAI and local Ollama.

- Open source: yes (Apache-2.0)
- Self-hostable: yes
- Pricing model: free
- Best for: An AI-native or RevOps engineer building production agents who wants them portable across any model and cloud — and runnable locally — rather than locked to a single provider's hosted agent runtime.
- Last verified: 2026-09-22

- **Canonical:** https://gtmstacker.com/registry/tool/strands-harness-sdk/
- **Source:** [github · strands-agents/harness-sdk](https://github.com/strands-agents/harness-sdk)
- **Tags:** ai-infrastructure, mcp-agents, self-hostable, agent-framework, developer-tooling
- **Repository:** https://github.com/strands-agents/harness-sdk

## Is Strands harness-sdk open source?

Yes, Strands harness-sdk is open source under the Apache-2.0 license.

## How much does Strands harness-sdk cost?

Strands harness-sdk is free to use.

## Can I self-host Strands harness-sdk?

Yes, Strands harness-sdk can be self-hosted (the source is available under the Apache-2.0 license).

## Alternatives & related

- [DeepSeek Harness (dsh)](https://gtmstacker.com/registry/tool/deepseek-harness/)
- [HarnessRouter](https://gtmstacker.com/registry/tool/harnessrouter/)


---

Apache-2.0 SDK (Python and TypeScript) from the AWS-backed Strands Agents project for building AI-agent harnesses that run in-process, with no hosted control plane. It is model-agnostic — first-class Amazon Bedrock plus Anthropic, OpenAI and Gemini, and local models via Ollama — so an agent you build stays portable across providers and can run entirely on your own hardware instead of being tied to one vendor's runtime.

## Provenance

- Apache-2.0 (LICENSE independently verified), ~7.5K stars, ~2,743 commits, created 2025-05-14, pushed 2026-09-22; in-process execution, no hosted control plane; first-class Bedrock plus Anthropic/OpenAI/Gemini and local Ollama (WebFetch 2026-09-22, github.com/strands-agents/harness-sdk).
- Surfaced in both the 2026-09-22 X viral-posts brief ("AWS open-sourced an agent harness you can run with a local model") and the studio discovery lane; cross-pull corroborated.
- Curated from the GTM Stacker signal registry (2026-09-22 pass); license independently verified 2026-09-22.

## Why it matters for a GTM stack

The quiet tax on agent infrastructure is the runtime lock-in: build on a hosted control plane and your agents assume that provider's models, quotas and availability. harness-sdk is the portable answer — an in-process SDK where the harness is yours, the model is a swap, and the same agent can point at Bedrock in production or Ollama on a laptop. For a team standardizing how it ships agents and wanting an escape hatch from any single vendor, that portability plus Apache-2.0 is worth the build cost. The honest read: it is AWS-backed (the strands-agents org, Bedrock first-class), not the official aws/ org, and "local model" means Ollama specifically. It is a builder's kit, not a turnkey product — the leverage is in what you assemble on it.