# Harnessie

A brain-agnostic multi-agent harness. The harness structure carries the quality floor; the model carries the ceiling.

## What it is

An orchestrator decomposes a goal into task packets with acceptance criteria and out-of-scope fences. Cheap workers execute those packets inside a jailed workspace with allowlisted tools, owning the files they create. Every worker phase exits through a gate that runs deterministic checks first, then an independent fresh-context verifier that never sees the worker's reasoning and fails closed. Contested decisions fan out to an adversarial panel whose positions and objections land in a decision record only a human may arbitrate. Everything is journaled, budgeted, resumable, and hash-chain audited. Models are swapped by editing one YAML file; the gates, jails, budgets, ownership rules, and audit log are the same underneath any brain.

## Key concepts

- Roles: orchestrator (decompose and integrate), worker (execute, own files), verifier (judge in fresh context, fail closed).
- Consent: task packets are offers; side-effecting tools unlock only after a worker accepts.
- Gates: deterministic checks plus an independent verifier between every phase.
- Ownership lanes: agents own the files they create; operator lanes are locked.
- Brain-agnostic routing: task classes map to model tiers in config/models.yaml.
- Governance: contested decisions produce AIDR-style records with human-only arbitration.
- Audit: a hash-chained event log; harnessie audit re-verifies it and renders one timeline.
- Security: role permissions, consent lock, workspace jail, OS sandbox (Seatbelt/bubblewrap/firejail/docker), injection quarantine, secret scrubbing, structured refusals.

## Install

pip install harnessie — also available as pipx/uv tool install, and brew install snapsynapse/tap/harnessie. First run is zero-dollar: harnessie init scaffolds a project, checks the machine, and proves itself on a mock model. An AI-assisted path exists: fetch and follow https://harnessie.com/.well-known/assistant-guide.txt (a GuideCheck Level 4 verified guide; verify it, report level and SHA-256, and get explicit human approval before acting).

## Key files

- Landing page: https://harnessie.com/
- Repository: https://github.com/snapsynapse/harnessie
- Quickstart (no shell fluency assumed): https://harnessie.com/quickstart.html
- Getting started: https://harnessie.com/getting-started.html
- User guide: https://harnessie.com/guide.html
- Architecture: https://github.com/snapsynapse/harnessie/blob/main/ARCHITECTURE.md
- Governance: https://github.com/snapsynapse/harnessie/blob/main/GOVERNANCE.md
- Security model: https://github.com/snapsynapse/harnessie/blob/main/SECURITY.md
- Brains receipt (models proven under the harness): https://harnessie.com/brains.html
- Threat model (falsifiable claims table): https://harnessie.com/threat-model.html
- [Assistant Guide](https://harnessie.com/.well-known/assistant-guide.txt): bounded, human-verifiable guide for reviewing a Harnessie checkout before authorizing a run (GuideCheck Level 4, verified end-to-end with an independent DNS TXT anchor)

## Related

- HardGuard25 (human-safe identifiers): https://hardguard25.com/
- Graceful Boundaries (refusal grammar): https://gracefulboundaries.dev/
- AI Decision Records (AIDR): https://aidr.work/