# GitHub - google-research/harness2

> Harness² improves AI agents with recursive task-level and harness-level recursion.
- Title: GitHub - google-research/harness2 · GitHub | Shortify
- Summary: Harness² improves AI agents with recursive task-level and harness-level recursion. Harness² boosts AI agent performance by 11.5 points on WorkBuddy-Bench…
- Keywords: harness2, recursive agent, task-level recursion, harness-level recursion, open world, ai agents, glm-5, gemini 3.5 flash, workbuddy-bench, jobbench, lab benchmark, technology
- Source: GitHub — https://github.com/google-research/harness2
- Read time: 1 min
- Topics: harness2, recursive agent, task-level recursion, harness-level recursion, open world, ai agents, glm-5, gemini 3.5 flash, workbuddy-bench, jobbench, lab benchmark, technology
## What is Harness²
Harness² is a plug-and-play framework for recursive agent harnessing in an open world.
## Task-level recursion
Task-level recursion refines execution harness through propose probe compose steps without ground truth feedback.
## Harnessing-level recursion
Harnessing-level recursion updates persistent improvement harness with adopted harnesses and evidence supported lessons.
## Performance gains
Harness² improves GLM-5 and Gemini 3.5 Flash by up to 11.5 points on WorkBuddy-Bench and 11.8 percentage points on LAB.
## Components
Harness² exposes eight editable components: system prompt, guardrails, memory, tool guidance, subagents, skills, scripts, and plugins.
## Installation
Install with Linux, Python 3.12, and uv to run local demos without model credentials.
## Benchmarking
Run benchmarks like JobBench, LAB, and WorkBuddy-Bench with harness2 commands for model-backed evaluations.
## Key takeaway

Harness² boosts AI agent performance by 11.5 points on WorkBuddy-Bench through recursive task-level and harness-level optimization.