N
Bounded worker execution
Delegate narrow coding tasks to local or cheap workers while the supervisor stays focused on planning and review.
AI agent harness development platform
Build, benchmark, and route agent execution without losing control.
Use one strong supervisor model as the architect, then route bounded coding work to cheap local workers with deterministic verification, policy guardrails, and operator control.
Optimized for solo power users running local or mixed-model execution.
agent-harness://quickstartlocal profile
harness init --profile local harness doctor harness demo --list-tasks harness demo --dry-run --task ts-isUUID # then run one bounded task harness run tasks/ts-lib/ts-isUUID.json \ --repo test-repos/ts-lib
3
supported paths: npm install, Docker, source dev
4
first-run flows: init, doctor, demo, docs
25
CLI integration tests protecting onboarding
Local-first
local-first, scales to team operation
See it in action
Watch a real run, not a script.
Agent Software Suite walkthrough
See how the suite connects context, reasoning, execution, and verification in one local-first workflow.
What it does
Productize agent delegation without turning it into a black box.
Agent Harness is the execution layer between a high-skill supervisor and a pool of cheaper workers. The point is not raw autonomy. The point is repeatable bounded execution with evidence, routing, verification, and recovery you can actually trust.
A
Deterministic verification
Check expected text, file scope, policy, and test commands before a task is allowed to pass.
D
Profile-driven first run
Generate current-schema configs with local, distributed, or semantic profiles instead of hand-assembling JSON from source code.
M
Operator trust surfaces
Doctor checks, reports, approvals, audit logs, and structured artifacts make failures and recoveries explainable.
L
Routing and provider flexibility
Mix Ollama, LM Studio, Anthropic, OpenAI, and OpenAI-compatible endpoints behind one model registry and router.
C
Distributed when needed
Run a local single-user harness today, then move to controller plus workers without changing the product story.
How it works
Start local, add sophistication only where it buys reliability.
1
Install Agent Harness
Clone the source repository and run its npm scripts, or start the Docker Compose stack. Native downloads are listed separately when a verified build is available.
2
Generate and validate config
Use `harness init --profile ...` to create a current config, then `harness doctor` to verify paths, git, and model connectivity.
3
Run a bounded task
Point the harness at a repo and one or more task definitions. A supervisor can route, verify, escalate, or require approval.
4
Inspect artifacts and recover
Use reports, audit logs, approvals, and demo flows to understand outcomes and recover from the common failure cases.
Supervisor agent via MCP or SDK
Worker adapters for local and hosted models
Git worktree isolation
Deterministic verifier
Policy and approvals
Reports, audit, and recovery artifacts
First-run shape
Start with `harness init`, `harness doctor`, and `harness demo`. Expand to distributed workers, semantic context, and approvals only when your workflow actually needs them.
Positioning
Not another general chat UI. A harness for execution quality.
Local-first architecture
Agent HarnessYesAiderNoOpenHandsNoCursorNo
Local-worker orchestration
Agent HarnessYesAiderNoOpenHandsYesCursorNo
Structured approvals and policy
Agent HarnessYesAiderNoOpenHandsNoCursorNo
Profile-driven init and doctor
Agent HarnessYesAiderNoOpenHandsNoCursorNo
Distributed controller and workers
Agent HarnessYesAiderNoOpenHandsYesCursorNo
Soft-stable reports and CLI surface
Agent HarnessYesAiderNoOpenHandsNoCursorNo
| Capability | Agent Harness | Aider | OpenHands | Cursor |
|---|---|---|---|---|
| Local-first architecture | Yes | No | No | No |
| Local-worker orchestration | Yes | No | Yes | No |
| Structured approvals and policy | Yes | No | No | No |
| Profile-driven init and doctor | Yes | No | No | No |
| Distributed controller and workers | Yes | No | Yes | No |
| Soft-stable reports and CLI surface | Yes | No | No | No |
What you can run today
The execution loop is already usable.
Start with a local profile, route work to the right model, and inspect the evidence before you trust the result.
L
Build your own harness
Profile-driven init, doctor checks, and a config-first workflow so you tune the harness to your stack instead of adapting to a fixed pipeline.
N
Model benchmarking and classification
Run real task suites against candidate models, capture the evidence, and get a capability map and scorecards you can route on with confidence.
C
Deterministic verification
Every claim of success gets independently checked before it's trusted — not just reported by the worker that made it.
D
Operator-first failure handling
Structured reports and audit logs make every failure and recovery explainable, so a bad run is a debuggable event, not a mystery.
M
Model-agnostic routing
One router in front of Ollama, LM Studio, Anthropic, OpenAI, and OpenAI-compatible endpoints — no lock-in to a single provider.
FAQ
Practical answers before platform mythology.
Can I self-host Agent Harness?
Yes. Agent Harness runs entirely on your own machine using Docker Compose and local models. No cloud dependency required.
What problem does it solve?
It gives supervisors a reliable way to delegate bounded coding work to cheaper workers while keeping verification, policy, routing, and recovery under operator control.
Do I need local models?
No, but that is the primary wedge. Agent Harness also supports hosted and OpenAI-compatible providers through the shared adapter layer.
What is the best first run?
Generate a config with `harness init --profile local`, run `harness doctor`, then inspect or run the built-in `harness demo` scenario.
Is this a hosted team product?
Not in this cycle. Team-ready operation is planned later, but the current roadmap explicitly keeps standalone local use as the primary product path.
Where should I start if I want to evaluate it quickly?
Use the install guide, quickstart, and examples docs. They map directly to the current first-run CLI and tested example configs.
From the blog
More on how Harness fits into the suite.
Affiliate Program
Promote Agent Software Suite. Earn 30% recurring.
Refer paying builders and earn 30% on every invoice they pay for the next 12 months.
30%
Commission
12 invoices
Window
60 days
Cookie
Get a real first run in under 10 minutes.
Start with the tested quickstart flow, inspect one demo task, and validate the example configs before you wire it into a bigger agent stack.