# OpenAutoCoder/Agentless

Agentless🐱:  an agentless approach to automatically solve software development problems

Repository: https://github.com/OpenAutoCoder/Agentless
Canonical: https://ross.abutalabs.com/products/agentless
Language: Python
License: MIT
License Family: permissive
Topics: agent, artificial-intelligence, llm, software-development
Last push: 2024-12-22T19:29:31+00:00

## Health v2 (maintenance only)
Score: 14/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 56
- inputs: {"age_days": 794, "days_push": 619, "days_rel": 674, "gap_med": null, "n_releases_24m": 1}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2104, forks 238 (observed 2026-08-28T04:06:13.810163+00:00)

## What it is
Agentless is a Python framework that automatically solves software development problems (bug fixing) using LLMs without an agent loop. It follows a three-phase pipeline of fault localization, patch repair, and patch validation, achieving strong SWE-bench results at low cost.

## Use cases
- automatically fix github issues with llms
- localize bugs to files and functions in a codebase
- generate candidate patches for software bugs
- benchmark automated program repair on swe-bench
- validate and rank generated patches with tests
- compare agentless vs agent-based coding approaches

## When to choose
- you want low-cost automated bug fixing without complex agent frameworks
- you need reproducible SWE-bench experiments or a research baseline
- you prefer a simple deterministic pipeline over autonomous agents

## When to avoid
- you need interactive, multi-step autonomous coding agents
- you lack an OpenAI-compatible LLM API key
- you need general software engineering beyond bug localization and repair

## Facets
- artifact type: framework
- maturity: active
- function: llm-inference, agent-framework, developer-tools, testing
- domain: artificial-intelligence, large-language-models, developer-tools
- platform: python, cli
- tags: swe-bench, automated-bug-fixing, agentless-ai, program-repair, fault-localization, llm-pipelines, software-engineering, linux, macos

## Member repositories
- OpenAutoCoder/Agentless (main) score 14

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:13.810163+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 2026-08-30T02:54:12.521705+00:00, confidence not recorded.
  - readme: https://github.com/OpenAutoCoder/Agentless (fetched 2026-08-28T04:06:13.810163+00:00, sha 02117e972fec)
- Data as of 2026-08-30T08:39:29.467469+00:00.