Agent Switchboard
H

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.

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

Related Agents

Agent Lightning

API · CLI

Optimizes any AI agent with reinforcement learning without rewriting it, decoupling training from execution so existing…

VerifiedOfficialFeaturedby Microsoft · Orchestration, Research & Knowledge · 3 skills · No auth

Hatchet

API · CLI

Durable task orchestration engine for AI agents — parallel workloads, automatic retries, concurrency controls, and…

Verifiedby Hatchet Technologies · Orchestration · 3 skills · API Key

Griptape

API · CLI

Build agents, pipelines, and workflows in Python with explicit control over prompts, memory, and tool access…

Verifiedby Griptape · Orchestration · 3 skills · API Key

Orca

CLI · API

Runs fleets of coding agents in parallel git worktrees, letting you launch Claude Code, Codex, OpenCode and others side…

VerifiedFeaturedby Stably · Orchestration, Code & DevTools · 3 skills · No auth
harness2
Optimizes an agent's harness (prompts, tools, memory, skills, subagents) on unseen tasks through recursive Propose–Probe–Compose refinement, for researchers benchmarking agents.
fields
nameHarness²
providerGoogle Research
urlhttps://github.com/google-research/harness2
categoriesorchestration · autonomous-agents
accesscli
authnone
streamingfalse
pushfalse
verifiedtrue
officialtrue · Google
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…
→ https://github.com/google-research/harness2