Agent Switchboard

Harness²

by Google Research

VerifiedOfficial

Official listing: built and published by Google. More from Google

Optimizes an agent's harness (prompts, tools, memory, skills, subagents) on unseen tasks through recursive Propose–Probe–Compose refinement, for researchers benchmarking agents.

Use it now

Keep it with up to 9 other tools you're setting up, then share them all as one link.

Try this first

Ask your coding agent:

  • Task-Level Recursion

    Use Harness² to propose harness edits: ‹what you need›

  • Harnessing-Level Recursion

    Use Harness² to update a persistent improvement harness: ‹what you need›

  • Parallel and Sequential Recursion

    Use Harness² to explore K candidate harnesses in parallel: ‹what you're looking for›

Install the CLI

Install it as its own instructions say.

Setup guide: github.com/google-research/harness2

Compare

Press Compare to add it to the tray at the bottom of the window, then pick up to 2 others anywhere on the site.

Access
CLI
Auth
None
Skills
4

Skills

  • Task-Level Recursion

    Proposes harness edits, probes their effects on the same task, and composes a refined harness without ground-truth feedback.

  • Harnessing-Level Recursion

    Updates a persistent improvement harness with adopted harnesses and lessons from each task to guide later refinement.

  • Parallel and Sequential Recursion

    Explores K candidate harnesses in parallel or refines one harness through K successive steps.

  • Benchmark Runs

    Sets up, runs, judges, and reports JobBench, LAB, and WorkBuddy-Bench tasks with OpenCode or Codex executors.

OrchestrationAutonomous Agentsharness-optimizationprompt-optimizationself-improvementagent-benchmarksopencodecodexpythonresearch-framework
Visit Agent
harness2
Optimizes an agent's harness (prompts, tools, memory, skills, subagents) on unseen tasks through recursive Propose–Probe–Compose refinement, for researchers benchmarking agents.
try this first
Ask your coding agent:
Use Harness² to propose harness edits: ‹what you need›task-level-recursion
Use Harness² to update a persistent improvement harness: ‹what you need›harnessing-level-recursion
Use Harness² to explore K candidate harnesses in parallel: ‹what you're looking for›parallel-sequential-modes
use it now
fields
nameHarness²
providerGoogle Research
urlhttps://github.com/google-research/harness2
categoriesorchestration · autonomous-agents
accesscli
authnone
streamingfalse
pushfalse
verifiedtrue
officialtrue · Google
sponsoredfalse
tagsharness-optimization, prompt-optimization, self-improvement, agent-benchmarks, opencode, codex, python, research-framework
skills
task-level-recursionTask-Level RecursionProposes harness edits, probes their effects on the sam…
harnessing-level-recursionHarnessing-Level RecursionUpdates a persistent improvement harness with adopted h…
parallel-sequential-modesParallel and Sequential RecursionExplores K candidate harnesses in parallel or refines o…
benchmark-runsBenchmark RunsSets up, runs, judges, and reports JobBench, LAB, and W…
alternatives
/agents/harness2/alternatives8 listedagent-lightning, hatchet, griptape
compare
/compare?a=harness2&b=agent-lightning&c=hatchetwith agent-lightning, hatchet