AutoCodeRover is an open-source autonomous coding agent designed to resolve GitHub issues and fix bugs in complex codebases. Developed by researchers at the National University of Singapore (AutoCodeRoverSG), the tool focuses on automated program repair (APR) and structured software engineering tasks, featuring native integration with benchmarks like SWE-bench. The agent operates as a command-line harness that ingests an issue description and a target repository. Rather than relying strictly on unstructured file browsing or raw text grep, AutoCodeRover uses Abstract Syntax Tree (AST) based search APIs to retrieve classes, methods, and code contexts. It iteratively localizes faults, constructs an understanding of the surrounding logic, formulates a patch, and verifies fixes against available test suites using LLM backends such as OpenAI GPT models. What differentiates AutoCodeRover from general-purpose CLI coding assistants is its syntax-aware fault localization architecture. By querying code structure at the method and class level rather than injecting entire files into the prompt, the agent reduces context overhead and focuses token budget directly on relevant call graphs and code units. AutoCodeRover is released as open-source software under the MIT license, making it suitable for benchmarking, academic research, and automated patch-generation workflows in isolated containerized environments.
AST-Driven Code Search — Navigates codebases by querying classes, methods, and docstrings via structural AST lookups instead of brute-force text search. - Automated Fault Localization — Iteratively analyzes issue reports to isolate problematic functions and code blocks before attempting edits. - SWE-bench Docker Integration — Bundles harnesses and submodule integration for running automated benchmarks across standard SWE-bench tasks. - Patch & Hotpatch Generation — Generates precise code modifications and unified diffs targeted strictly to the localized fault scope. - Automated Test Validation — Coordinates with local test frameworks like PyTest within containers to validate generated patches before output.
Use cases
Use Case: Autonomous Issue Resolution A developer feeds a GitHub issue description and a local repository clone into AutoCodeRover. The agent scans the code structure, pinpoints the faulty method, generates a fix, and outputs a patch ready for human review.
Use Case: SWE-bench Benchmark Execution Researchers evaluate LLM coding capabilities by executing AutoCodeRover across the SWE-bench evaluation suite inside Docker containers to measure task resolution rates and token efficiency.
Use Case: Automated Regression Diagnosis When a bug report arrives with a minimal reproduction description, the agent traces the relevant class hierarchies and dependencies to explain the root cause and propose a corrective patch.
Who it is for
AutoCodeRover is intended for software engineering researchers, benchmark developers, and tooling teams looking for an autonomous, structural program repair agent. It is not designed for real-time interactive pair programming or inline IDE autocompletion.
Install guide
Installation Clone the repository and set up a Python virtual environment: bash git clone https://github.com/AutoCodeRoverSG/auto-code-rover.git cd auto-code-rover conda create -n acr python=3.10 -y conda activate acr pip install -r requirements.txt
First Run Configure your OpenAI API key in your environment: bash export OPENAI_API_KEY="your-openai-api-key" Ensure Docker is running if executing repairs inside isolated test environments.
Example Session Execute AutoCodeRover on a target repository with a specified issue description: bash python -m app.main \ --issue-file ./sample_issue.txt \ --repo-path /path/to/target/repository \ --output-dir ./output_patches
OpenHands — OpenHands (formerly OpenDevin) is an open-source autonomous AI software development agent and orchestration platform. It provides an extensible runtime environment…
OpenCode — OpenCode is an open-source AI coding agent developed by Anomaly that operates across terminal environments, desktop applications, and IDE extensions.…
Amp — Amp (developed by AmpCode) is an autonomous coding agent platform and remote development harness designed to execute software engineering tasks…
Kiro — Kiro is an agentic engineering platform and CLI coding agent built and operated by AWS. It extends beyond standard code-completion…
Continue — Continue is an open-source AI code assistant and agent framework originally developed by the Continue team (continuedev) and recently acquired…
Plandex — Plandex is an open-source terminal-based AI coding agent designed to handle complex, multi-file engineering tasks in large codebases. Created by…