DEDUPED Hot AI repos, turned into use cases Get 5 a day

What you can do with Harness Zero

Harness-Zero is a Python research repo that distills an optimized agent harness into Qwen3.5-9B model weights, so the gains remain when the harness is removed at deployment.

Trended earlier

metaevo-ai/harness-zero on GitHub

Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk.

What do you want to do?

4 use cases

  • Generate reviewed agent trajectories for training data

    Run a harnessing agent over benchmark tasks and export successful trials as an SFT dataset.

    View prompt
    Using the repo metaevo-ai/harness-zero, run a reviewed rollout on the task IDs in <tasks-file> with the USPTO harness bank, then build an SFT dataset from runs/demo. Expected output: sft.jsonl containing only trials that met reward threshold 1.0. Verify that runs/demo contains trial results before you run build-sft.

  • Distill a harness into Qwen3.5-9B weights

    Fine-tune the base model on reviewed trajectories so it runs well under the minimal harness alone.

    View prompt
    Using the repo metaevo-ai/harness-zero, train a LoRA SFT run from sft.jsonl on Qwen/Qwen3.5-9B with run name hz-demo. Expected output: a training run under runs/train. Verify the confirmation prompt shows the intended dataset and settings before you approve the submission.

  • Adapt the harness bank to a new task domain

    Use the bundled evolution skills to build student and reference harnesses for another domain.

    View prompt
    Using the repo metaevo-ai/harness-zero, study harness_bank/uspto and the skills in .agents/skills/, then draft a new harness_bank folder for the domain <domain-name>. Expected output: a folder layout and a short plan listing the student harness and reference harness files. Verify that the plan matches the existing per-domain structure before writing any files.

  • Reproduce the AppWorld evaluation with the dedicated setup

    Run AppWorld rollouts through the included mini-SWE-agent and environment to match the reported setup.

    View prompt
    Using the repo metaevo-ai/harness-zero, follow envs/appworld/README.md to run AppWorld test_normal rollouts with the dedicated agent and environment. Expected output: SGC scores across the 168 test tasks. Verify that the run uses the dedicated environment and not a generic harness before reporting scores.

How to use Harness Zero

  1. Check you have what it needs: Python 3.12 to 3.13 and uv installed; Docker running, since rollouts run in local Docker sandboxes via Harbor; API key for your model route (OpenAI, Azure AI Foundry, or OpenRouter) in a .env file copied from .env.example.
  2. Open metaevo-ai/harness-zero on GitHub and read the README and license.
  3. Run uv sync in the cloned Harness Zero folder.
  4. Copy .env.example to .env and fill in the key for the model route you use.
  5. Create a task list with printf 'uspto-train-000\nuspto-train-001\n' > /tmp/tasks.txt.
  6. Run harness-zero run-rollout --dataset data/uspto --components harness_bank/uspto --teacher-middleware-factory harness_bank.uspto.middlewares:build_teacher_middlewares --tasks-file /tmp/tasks.txt --attempts 1 --concurrency 8 --student-model openai: --student-reasoning-effort high --teacher-provider openai --teacher-model --teacher-reasoning-effort high --job-name demo --output-dir runs, filling in the model names for your route. (inferred, check the README)

These steps come from our top use case, Generate reviewed agent trajectories for training data, which also has a copy-paste agent prompt.

Harness Zero alternatives · Best AI repos for Research

About this repo

Requirements

  • Python 3.12 to 3.13 and uv installed
  • Docker running, since rollouts run in local Docker sandboxes via Harbor
  • API key for your model route (OpenAI, Azure AI Foundry, or OpenRouter) in a .env file copied from .env.example
  • A Tinker key (TM_API_KEY) if you plan to run training
Maintain Harness Zero? Add the Featured on Deduped badge

Paste this into your README:

[![Featured on Deduped](https://dedupedai.com/badge/metaevo-ai-harness-zero.svg)](https://dedupedai.com/use-cases/metaevo-ai-harness-zero/?ref=badge)

More badge styles and HTML

Questions about Harness Zero

What is Harness Zero?

Harness-Zero is a Python research repo that distills an optimized agent harness into Qwen3.5-9B model weights, so the gains remain when the harness is removed at deployment. It is an open-source project on GitHub: https://github.com/metaevo-ai/harness-zero.

Who is Harness Zero for?

Written for ML researchers and agent engineers who want to reproduce or extend harness distillation on the three published benchmarks.

What can I do with Harness Zero?

4 use cases so far, for example: Generate reviewed agent trajectories for training data; Distill a harness into Qwen3.5-9B weights; Adapt the harness bank to a new task domain. Each has steps and a copy-paste agent prompt.

What do I need to run Harness Zero?

Python 3.12 to 3.13 and uv installed; Docker running, since rollouts run in local Docker sandboxes via Harbor; API key for your model route (OpenAI, Azure AI Foundry, or OpenRouter) in a .env file copied from .env.example; A Tinker key (TM_API_KEY) if you plan to run training.

What are alternatives to Harness Zero?

Other hot AI repos in Research: Scientific Agent Skills, Speaker Mem R1, DSH Council, Evo Bot, AI Engineering Course.

Is Harness Zero safe to run?

Deduped does not own, audit or vouch for it. Read the README and license, run it on your own systems first and review every command before you run it.