harness-sdk
Build an agent harness and control it end-to-end. Open-source SDK for production AI agents in Python & TypeScript - any model, any cloud.
Source#
- Repository: strands-agents/harness-sdk
- Last source update: 2026-06-14
- Last verified: 2026-06-14
Tags#
Integration notes#
Repository is focused on tool/server interoperability; wrap in bounded worker contracts for production use.
worker.md example#
Starter worker.md contract mapped from this registry entry. Copy this file and adapt schemas, constraints, and statuses for your task.
---
id: harness-sdk-repo-derived-worker
name: harness-sdk Repo-Derived Worker
version: 1.0.0
source_registry_url: https://worker.md/registry/harness-sdk/
source_repository: https://github.com/strands-agents/harness-sdk
repository_default_branch: main
repository_language: Python
repository_license: Apache-2.0
repository_updated_at: 2026-06-14
worker_mode: agent-orchestration-worker
derivation_method: github_repository_metadata_plus_raw_readme
derivation_confidence: 0.95
derived_on: 2026-06-14
tags:
- agent-framework
- agentic
- agentic-ai
- agents
- ai
- ai-agents
---
# harness-sdk Repo-Derived Worker
## Repo-derived summary
- Registry summary: Build an agent harness and control it end-to-end. Open-source SDK for production AI agents in Python & TypeScript - any model, any cloud.
- Repository description: Build an agent harness and control it end-to-end. Open-source SDK for production AI agents in Python & TypeScript - any model, any cloud.
- Stars (snapshot): 6,125
- Primary language: Python
- Worker mode classification: agent-orchestration-worker
## Extracted from
- https://github.com/strands-agents/harness-sdk
- https://github.com/strands-agents/harness-sdk/blob/main/README.md
- https://github.com/strands-agents/harness-sdk/releases?q=python%2F&expanded=false
- https://github.com/strands-agents/harness-sdk/releases?q=typescript%2F&expanded=false
- https://strandsagents.com/docs/user-guide/concepts/model-providers/
## Evidence notes (from repository text)
- README summary paragraph: A model-driven approach to building AI agents in just a few lines of code.
- A model-driven approach to building AI agents in just a few lines of code.
- This monorepo contains the Python SDK, TypeScript SDK, documentation site, and supporting packages:
- | `strands-py/` | Python SDK: agent loop, model providers, tools (https://pypi.org/project/strands-agents/ · https://github.com/strands-agents/harness-sdk/releases?q=python%2F&expanded=false) |
- | `strands-ts/` | TypeScript SDK: agent loop, model providers, tools (https://www.npmjs.com/package/@strands-agents/sdk · https://github.com/strands-agents/harness-sdk/releases?q=typescript%2F&expanded=false) |
- | `strands-wasm/` | WebAssembly bindings for running Python tools from TypeScript agents |
## Installation hints found in README
- `pip install strands-agents strands-agents-tools`
- `pip install hatch`
- `npm install @strands-agents/sdk`
## worker.md contract (derived starter)
Purpose: Execute one orchestrated agent task as a bounded worker step.
### Input schema
```json
{
"type": "object",
"additionalProperties": false,
"required": [
"run_id",
"task",
"context"
],
"properties": {
"run_id": {
"type": "string"
},
"task": {
"type": "string"
},
"context": {
"type": "object"
}
}
}
```
### Output schema
```json
{
"type": "object",
"additionalProperties": false,
"required": [
"run_id",
"status",
"result"
],
"properties": {
"run_id": {
"type": "string"
},
"status": {
"type": "string",
"enum": [
"ok",
"retryable_error",
"invalid_request",
"invalid_output"
]
},
"result": {
"type": "object"
}
}
}
```
### Constraints
- timeout_seconds: 30
- max_attempts: 2
- idempotency_key: run_id
- status_enum: [ok, retryable_error, invalid_request, invalid_output]
- notes: adapt to concrete APIs/classes documented in this repository before production use
## How this should be used
1. Treat this file as a repo-derived starter profile, not a claim of an official repository API contract.
2. Replace schemas with exact interfaces from code/docs you adopt.
3. Keep execution bounded and auditable using worker protocol constraints.
How to use#
- Save this as a worker spec file (for example:
harness-sdk-my-task.worker.md). - Replace the input/output schemas and purpose with your real bounded task.
- Enforce schema validation + timeout + retry policy in your runtime before production use.
Citation#
Reference URL: https://worker.md/registry/harness-sdk/
Source URL: https://github.com/strands-agents/harness-sdk