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

What you can do with Swe Sweep

SWE-sweep is a Python benchmark harness where an agent must find and fix as many bugs as it can in a real repository, with no hints about bug type or location.

Trended earlier

facebookresearch/swe-sweep 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?

3 use cases

  • Score one agent patch on a SWE-sweep task

    Run a unified diff against one benchmark task and get graded Harbor results.

    View prompt
    Using the repo at facebookresearch/swe-sweep, run the Harbor command for the task tasks/<task-name> with the patch at <path-to-model.patch> as the patch_path, writing output to jobs/. Report the directory where results were written and whether the trial completed without errors.

  • Summarize graded trials by task and in total

    Turn a folder of graded Harbor trials into per-task and JSON score summaries.

    View prompt
    In the facebookresearch/swe-sweep repo, run `sweep info <path-to-graded-trials> --json` and save the output. Verify that the reported total equals the number of bugs solved across tasks divided by the total number of bugs.

  • Check the harness tests before editing it

    Run the repo's test suite and lint hooks to get a clean baseline before changes.

    View prompt
    In the facebookresearch/swe-sweep repo, run `uv sync --extra test` then `uv run pytest` and report the pass and fail counts. Confirm that `uvx pre-commit run --all-files` passes before making any edits to <file-to-change>.

How to use Swe Sweep

  1. Check you have what it needs: Python with uv (or pip) installed; Harbor, as pinned by the repo; A unified diff file (model.patch) made against a task's base commit.
  2. Open facebookresearch/swe-sweep on GitHub and read the README and license.
  3. git clone https://github.com/facebookresearch/swe-sweep.git
  4. cd swe-sweep
  5. uv sync
  6. sweep infra doctor

These steps come from our top use case, Score one agent patch on a SWE-sweep task, which also has a copy-paste agent prompt.

Swe Sweep alternatives · Best AI repos for Software and DevOps

About this repo

Requirements

  • Python with uv (or pip) installed
  • Harbor, as pinned by the repo
  • A unified diff file (model.patch) made against a task's base commit
  • Docker or the environment Harbor needs for the verifier, if Harbor requires it (inferred)
Maintain Swe Sweep? Add the Featured on Deduped badge

Paste this into your README:

[![Featured on Deduped](https://dedupedai.com/badge/facebookresearch-swe-sweep.svg)](https://dedupedai.com/use-cases/facebookresearch-swe-sweep/?ref=badge)

More badge styles and HTML

Questions about Swe Sweep

What is Swe Sweep?

SWE-sweep is a Python benchmark harness where an agent must find and fix as many bugs as it can in a real repository, with no hints about bug type or location. It is an open-source project on GitHub: https://github.com/facebookresearch/swe-sweep.

Who is Swe Sweep for?

Written for engineers and AI agent builders who want to score a coding agent's patches on SWE-sweep tasks or summarize graded runs.

What can I do with Swe Sweep?

3 use cases so far, for example: Score one agent patch on a SWE-sweep task; Summarize graded trials by task and in total; Check the harness tests before editing it. Each has steps and a copy-paste agent prompt.

What do I need to run Swe Sweep?

Python with uv (or pip) installed; Harbor, as pinned by the repo; A unified diff file (model.patch) made against a task's base commit; Docker or the environment Harbor needs for the verifier, if Harbor requires it (inferred).

What are alternatives to Swe Sweep?

Other hot AI repos in Software and DevOps: Harness2, iFixAi, Orca, Diagram Design, AI Memory.

Is Swe Sweep 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.