Agentless is a lightweight approach to autonomous software engineering that solves development problems without persistent agent loops. Developed by researchers from the University of Illinois Urbana-Champaign, it follows a simple three-phase “localize-then-repair” methodology. With over 2,000 GitHub stars, Agentless achieved 40.7% on SWE-bench Lite and 50.8% on SWE-bench Verified when integrated with Claude 3.5 Sonnet — proving that simpler approaches can rival complex agent systems.

GitHub: OpenAutoCoder/Agentless

• No Agent Loop — Unlike most AI coding tools, Agentless uses a fixed three-phase pipeline rather than an iterative agent loop
• Localize-Then-Repair — Hierarchical fault localization followed by targeted patch generation
• Cost Efficient — Significantly cheaper per task than agent-based approaches due to fewer LLM calls
• SWE-bench Performance — 40.7% on SWE-bench Lite, 50.8% on SWE-bench Verified (with Claude 3.5 Sonnet)
• Best Open-Source Approach — Achieved top open-source results on SWE-bench Lite at time of release
• Multi-Model Support — Works with GPT-4, Claude 3.5 Sonnet, and other LLMs
• Reproducible — Deterministic pipeline with published artifacts for all benchmark runs

Agentless follows a deliberate anti-pattern to traditional agent design:

• Phase 1: Localization — Hierarchical narrowing from repository level to file, class, method, and finally specific code lines
• Phase 2: Repair — Generate candidate patches using the localized context
• Phase 3: Selection — Rank and select the best patch using test execution and heuristics
• No Iterative Loop — Each phase runs once; no backtracking or multi-turn agent conversation
• Minimal Tool Use — Only needs file reading and test execution, no complex tool orchestration

# Clone and set up
git clone https://github.com/OpenAutoCoder/Agentless.git
cd Agentless
 
# Create conda environment
conda create -n agentless python=3.11
conda activate agentless
pip install -r requirements.txt
 
# Set API key
export OPENAI_API_KEY="your-key-here"
 
# Run localization phase
python3 agentless/localize.py \
    --instance django__django-16379 \
    --model gpt-4
 
# Run repair phase
python3 agentless/repair.py \
    --instance django__django-16379 \
    --localization results/localization.json
 
# Run patch selection
python3 agentless/select.py \
    --candidates results/patches/

The Agentless approach challenges the assumption that autonomous software engineering requires complex agent architectures:

• Simplicity — A fixed pipeline is easier to understand, debug, and improve than an open-ended agent loop
• Predictability — Deterministic phases produce more consistent results than stochastic agent exploration
• Cost — Fewer LLM calls mean significantly lower API costs per task
• Reproducibility — Fixed pipeline enables fair comparisons and scientific evaluation
• Baseline Value — Provides a strong baseline against which agent-based approaches should be measured

The authors argue that if a simple three-phase pipeline can match or exceed agent-based systems, the field should question whether agent complexity is always justified.

• GitHub Repository
• Research Paper
• Project Website

• AutoCodeRover — Agent-based autonomous program improvement
• Trae Agent — ByteDance's research-friendly CLI agent
• Smol Developer — Generates entire codebases from a prompt
• Devon — Open-source pair programmer
• Cline — Model-agnostic autonomous coding agent