| Pricing | Startup: Free for up to 3 users and 3 projects. Cloud Starter: $9 per user/month with unlimited users and projects. Cloud Pro: $19 per user/month with unlimited users, projects, 1,000 included AI credits per licensed user per month, and priority support. Self-hosted: Starting at $3,000 per instance/
| Not given
|
|---|
| Key features | - Specification Management: Manage connected requirements, data entities, APIs, interfaces, wireframes, and test cases in a versioned product model with traceable relations and branch-aware revisions
- Change Management: Define each product change through a Change Request that connects goal, affected specifications, project branch, implementation impact, and linked issue
- Architecture & Software Units Blueprints: Define subsystem architecture and software unit blueprints with implementation rules, responsibilities, dependencies, and file boundaries linked to product sp
- AI Assistants: AI Analyst, AI Test Designer, AI Architect, and AI Product Expert for refining specifications, designing tests, developing architecture, and reviewing implementation
- MCP for AI Coding Agents: Give coding agents branch-aware specifications, architecture guidance, software units, file traces, and Change Request context through MCP
- Specification and Code Alignment Verification: Check that code matches specifications and follows architecture rules as the system evolves
- Test Management: Organize test cases, test runs, execution, and result history
- MCP for QA Agents: Give QA agents prepared test runs, cases, steps, and expected outcomes through MCP to record execution results
| - Configure plugins, skills, MCP servers, and hooks in a single harness.yaml file
- Observatory: monitor every session, tool call, and minute of activity
- Memory: persistent knowledge graph for AI orientation
- Comparator: run prompts across Claude Code, Cursor, and Copilot side by side
- Import existing configs from multiple AI coding tools automatically
- Share complete setup via single file with teammates
- Harness Parity: verify all connected AI tools end up with identical configuration
- Cross-harness compatibility table showing actual tool capabilities
|
|---|
| What makes it different | - Preserves product context across tasks, agents, and code changes through a structured, verified product model
- Reduces handoffs and coordination by delegating whole features with connected specifications and implementation scope
- Prevents architecture drift by connecting implementation with subsystem architecture rules, unit guidelines, and component responsibilities
- Built for complex products where a single feature touches connected data, APIs, interfaces, and business rules across multiple repositories and systems
- Keeps product model current as specifications and implementation change using AI assistance and team review
| - Import-first approach: reads existing configs from all your tools and converges them before you write YAML
- No marketing gloss: capability table generated at build time from actual adapter code, not hand-maintained
- Portable across tools: single harness.yaml travels with you to every machine and tool
- Open source and free: no cost beyond existing Claude subscription
- Based on open specification: Harness Protocol is vendor-neutral and JSON Schema validated
|
|---|