# AutoCodeRoverSG/auto-code-rover

A project structure aware autonomous software engineer aiming for autonomous program improvement. Resolved 37.3% tasks (pass@1) in SWE-bench lite and 46.2% tasks (pass@1) in SWE-bench verified with each task costs less than $0.7.

Repository: https://github.com/AutoCodeRoverSG/auto-code-rover
Canonical: https://ross.abutalabs.com/products/auto-code-rover
Language: Python
License: NOASSERTION
License Family: other
Last push: 2025-04-24T07:58:24+00:00

## Health v2 (maintenance only)
Score: 34/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 18, release rhythm 40, longevity 62
- inputs: {"age_days": 877, "days_push": 496, "days_rel": 722, "gap_med": 0, "n_releases_24m": 2}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3100, forks 332 (observed 2026-08-28T04:07:43.533474+00:00)

## What it is
AutoCodeRover is an autonomous software engineering agent that combines LLMs with code structure analysis to automatically resolve GitHub issues by locating and patching code. It achieves strong SWE-bench results (46.2% on Verified, pass@1) at low per-task cost.

## Use cases
- automatically fix github issues
- autonomous bug fixing with llm
- resolve swe-bench tasks
- generate patches for feature requests
- find likely fix locations in a codebase
- run an ai software engineer on a local repo

## When to choose
- you want automated issue resolution or patch generation for Python repositories
- you need a benchmark-proven SWE-bench agent with low per-task cost
- you want structure-aware code search rather than naive LLM file browsing

## When to avoid
- you need guaranteed-correct patches without human review
- your project is not Python or lacks test infrastructure
- you cannot expose an LLM API key or pay per-task inference costs

## Facets
- artifact type: application
- maturity: active
- function: agent-framework, llm-inference, developer-tools, code-review
- domain: artificial-intelligence, large-language-models, developer-tools
- platform: python, cli, cross-platform
- tags: autonomous-coding, swe-bench, bug-fixing, llm-agent, program-repair, github-issues, ai-agents, automation, docker

## Member repositories
- AutoCodeRoverSG/auto-code-rover (main) score 34

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:43.533474+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:27:00.287081+00:00, confidence not recorded.
  - readme: https://github.com/AutoCodeRoverSG/auto-code-rover (fetched 2026-08-28T04:07:43.533474+00:00, sha a538659f1f3c)
- Data as of 2026-08-30T08:39:29.467469+00:00.