Frontend Agents and Generative UI · Public

harness-sdk

Frontend agent and generative UI project for checking React/Angular integration, app actions, UI state, and UX boundaries.

Generative UIFrontend agentsReactApp actionsUX boundaries

Best fitFrontend or full-stack developers adding in-app agents, generative UI, or app actions to a product surface.

Check whether this project matches your task before installing it.

What it can doFrontend integration checks, app-action permissions, UI state boundaries, rollback paths, and acceptance checks

Review the portable capability path.

Before continuingVerify in a sandbox

Do not treat a preview pack as a proven local install.

GitHub snapshot6.0k stars

862 forks · 207 contributors

Doramagic.ai Last verification date: 2026-06-20 Verification method: source evidence, semantic profile, public page gate, and static build acceptance.

Official first step Read manual preview Source repository

Publication status · 2026-06-20

What is harness-sdk?

harness-sdk is a frontend agent or generative UI project for connecting app actions, UI state, and agent interaction.
Best fit: Frontend or full-stack developers adding in-app agents, generative UI, or app actions to a product surface.
Not for: Not for browser automation, web scraping, or workflows without clear user-action permission boundaries.
Capability added to an AI workflow: Frontend integration checks, app-action permissions, UI state boundaries, rollback paths, and acceptance checks
First safe verification step: Verify one reversible app action and UI state sync in a demo page first.
Verification state: source, Quick Start, and sandbox install checks are recorded as passed.
Top risk: May increase setup, validation, or first-run risk for the user.
Evidence base: https://github.com/strands-agents/harness-sdk, https://github.com/strands-agents/harness-sdk#readme, Human Manual, Pitfall Log

Quick decision

Use this section to decide whether the project is worth a deeper read.

Best forFrontend or full-stack developers adding in-app agents, generative UI, or app actions to a product surface.

Match the project to your task before installing it.

CapabilityFrontend integration checks, app-action permissions, UI state boundaries, rollback paths, and acceptance checks

Frontend agent and generative UI project for checking React/Angular integration, app actions, UI state, and UX boundaries.

Repositorystrands-agents/harness-sdk

6.0k stars · 862 forks

What it can do

Translate the upstream project into concrete capabilities the user can judge before installing.

Monorepo Architecture & SDKs Overview

Related topics: Agent Loop, Tools & Hooks, Plugins, Bidirectional Streaming & WASM Interop

Source: https://github.com/strands-agents/harness-sdk / Human Manual

Agent Loop, Tools & Hooks

Related topics: Monorepo Architecture & SDKs Overview, Model Providers & Multi-Agent Patterns

Source: https://github.com/strands-agents/harness-sdk / Human Manual

Model Providers & Multi-Agent Patterns

Related topics: Agent Loop, Tools & Hooks, Plugins, Bidirectional Streaming & WASM Interop

Source: https://github.com/strands-agents/harness-sdk / Human Manual

Plugins, Bidirectional Streaming & WASM Interop

Related topics: Monorepo Architecture & SDKs Overview, Model Providers & Multi-Agent Patterns

Source: https://github.com/strands-agents/harness-sdk / Human Manual

Doramagic Pitfall Log

Source-linked risks stay visible on the manual page so the preview does not read like a recommendation.

Source: Doramagic discovery, validation, and Project Pack records

Sources: https://github.com/strands-agents/harness-sdk, Human Manual, Project Pack evidence, and downstream validation signals.

Community Discussion Evidence

Project-level external discussion stays visible on the detail page, not only inside the manual.

Stars6.0k stars

Forks862 forks

Contributors207 contributors

Licenseunknown

Community Discussion Evidence

12 source-linked items

Review these external discussions before using harness-sdk with real data or production workflows. They are review inputs, not standalone proof that the project is production-ready.

01
Python middleware: add interrupt source field to distinguish middleware-
github / github_issue
02
[BUG] Gemini rejects tool results with multiple same-format images: dupl
github / github_issue
03
[FEATURE] Support Managed Bedrock Knowledge Bases for Memory Manager
github / github_issue
04
[FEATURE] Support for multiple MCP servers (and loading from config file
github / github_issue
05
[BUG] CacheConfig(strategy="auto") does not detect Claude models when us
github / github_issue
06
[FEATURE] Support audio input for standard Agent (Specially using Bedroc
github / github_issue
07
[WASM] Python SDK - Gaps and Limitations
github / github_issue
08
[WASM] MCP tools
github / github_issue
09
[BUG] OpenAIModel tool message content sent as array instead of string b
github / github_issue
10
typescript/v1.6.0
github / github_release
11
python/v1.44.0
github / github_release
12
typescript/v1.5.0
github / github_release

How to start

Only source-backed commands are shown here. Verify them in an isolated environment first.

Try the prompt first

Test the workflow without installing the upstream project.

preview

Read the Human Manual

Understand inputs, outputs, limits, and failure modes.

manual

Take context to your AI host

Use the compiled assets in your preferred AI environment.

context

Run sandbox verification

Confirm install commands and rollback before using a primary environment.

verify

pip install strands-agents

Official start command · https://github.com/strands-agents/harness-sdk#readme · verified: yes

Human Manual

The English page must expose the real manual, not a short placeholder.

8+ sections · Human Manual

harness-sdk Manual

A model-driven approach to building AI agents in just a few lines of code.

Open the full manual

https://github.com/strands-agents/harness-sdk Project Manual
Table of Contents
Monorepo Architecture & SDKs Overview
Related Pages
Purpose and Scope
High-Level Repository Layout
Architecture Overview
Component Responsibilities

Monorepo Architecture & SDKs Overview

Related topics: Agent Loop, Tools & Hooks, Plugins, Bidirectional Streaming & WASM Interop

Source: https://github.com/strands-agents/harness-sdk / Human Manual

Agent Loop, Tools & Hooks

Related topics: Monorepo Architecture & SDKs Overview, Model Providers & Multi-Agent Patterns

Source: https://github.com/strands-agents/harness-sdk / Human Manual

Model Providers & Multi-Agent Patterns

Related topics: Agent Loop, Tools & Hooks, Plugins, Bidirectional Streaming & WASM Interop

Source: https://github.com/strands-agents/harness-sdk / Human Manual

Plugins, Bidirectional Streaming & WASM Interop

Related topics: Monorepo Architecture & SDKs Overview, Model Providers & Multi-Agent Patterns

Source: https://github.com/strands-agents/harness-sdk / Human Manual

Doramagic Pitfall Log

Source-linked risks stay visible on the manual page so the preview does not read like a recommendation.

Source: Doramagic discovery, validation, and Project Pack records

AI Context Pack and portable assets

After deciding to continue, take the project context into your own AI host.

Complete pack plus user-owned assets

These files are planning and verification assets for Claude Code, Codex, Gemini, Cursor, ChatGPT, and other AI hosts.

Download complete pack Read Human Manual

BundleComplete Project Pack AssetAI Context Pack AssetBoundary & Risk Card AssetHuman Manual AssetPitfall Log AssetPrompt Preview AssetQuick Start EvidenceREPO_INSPECTION.json

Preflight checks

Treat this page as a planning asset, not proof that your local environment is ready.

The manual is generated from source-linked project files and Doramagic validation signals.
Community evidence warnings stay visible instead of being converted into marketing claims.
This English page is indexable because the locale quality gate passed and explicit English index approval is enabled.
Use the upstream repository as the final authority for installation commands, license, and version-specific behavior.

Pitfall Log and verification risks

Doramagic surfaces high-risk items before users treat a candidate capability as verified.

high

Installation risk requires verification

May increase setup, validation, or first-run risk for the user.

high

Security or permission risk requires verification

Developers may expose sensitive permissions or credentials: [BUG] CacheConfig(strategy="auto") does not detect Claude models when using ARN-based inference profiles

high

Security or permission risk requires verification

May increase setup, validation, or first-run risk for the user.

medium

Identity risk requires verification

May increase setup, validation, or first-run risk for the user.

medium

Installation risk requires verification

Developers may fail before the first successful local run: [BUG] Gemini rejects tool results with multiple same-format images: duplicate displayName in function_response.parts (400 INVALID_ARGUMENT)

medium

Installation risk requires verification

Developers may fail before the first successful local run: [BUG] OpenAIModel tool message content sent as array instead of string breaks OpenAI-compatible endpoints (e.g., Kimi K2.5)

medium

Installation risk requires verification

Upgrade or migration may change expected behavior: python/v1.41.0

medium

Installation risk requires verification

Upgrade or migration may change expected behavior: v1.41.0