Project overview
AutoHarness is a lightweight governance layer for existing AI agents. It can wrap an LLM client, check tool calls for risk and permissions, sanitize outputs, record decisions, and manage context and token budgets. YAML rules select different governance levels, while multi-agent profiles, per-call cost attribution, and session persistence cover longer-running workflows.
Repository facts
- Primary language
- Python
- License
- MIT
- Repository updated
- Jul 8, 2026
- Default branch
- main
Resource types
Agent harnessFramework
Use cases
Software development
Platforms
Claude CodeCursor
Runtime
Command line
Capabilities
Code executionObservabilityTool useVerification and evals