SWE-agent

SWE-agent

Open Source(MIT)
Verified
AI-Native
Superseded by mini-swe-agent (2026) — this version is now maintenance-only.View mini-swe-agent

Open-source autonomous agent for GitHub issues & coding challenges

Global
Self-hostable
Function calling
Public API
No signup
+2
Autonomous
Last updated: Oct 13, 2026
Compiled and verified by Intelloro · Ref INT-JPMZFA
Open Source
Visit Site20.1k
More
swe-agent.com

Quick Answer

SWE-agent is an open-source AI agent for developers that enables large language models to autonomously fix GitHub issues, find cybersecurity vulnerabilities, and solve coding challenges. It achieves state-of-the-art performance on SWE-bench and supports multimodal input. Free and open source.

About SWE-agent

SWE-agent is an open-source AI agent that allows language models like GPT-4o or Claude Sonnet 4 to autonomously use tools to fix issues in real GitHub repositories, find cybersecurity vulnerabilities, or perform custom tasks. It is state of the art on SWE-bench among open-source projects and is made for research, governed by a single YAML file and fully documented. It is built and maintained by researchers from Princeton University and Stanford University.

AI-extracted from public sources. May contain errors. Methodology · Report an error
What Makes SWE-agent UniqueAI

SWE-agent is built for research, offering a simple and hackable design that provides maximal agency to the language model, making it highly generalizable for various coding tasks.

Decision Intelligence

Best For

AI
Researchers building and evaluating autonomous coding agents
Developers automating GitHub issue resolution
Cybersecurity professionals identifying vulnerabilities with AI
Teams solving competitive coding challenges with AI
Pricing Overview

Type

Open Source

Starting Price

$0/mo

Free Trial

No

Credit Card

Not Required

Free Plan

Yes

Dimension Scores

· 5.0 avg

How good it is, across universal quality axes

Ease of Use2/10
Customization7/10
Support8/10
Integration2/10
Compliance & Data Protection5/10
Performance5/10
Planning Quality6/10
AI-scored from up to 37 public sources, reviewed by a person·Medium confidenceHow we score

Task Scores

· 5.3 avg

What it can do, per category it works in · showing 8 of 10 tasks scoring 5+

Observability8/10
Scalability Throughput8/10
Error Recovery7/10
Role Definition6/10
State Management6/10
Task Decomposition5/10
Workflow Orchestration5/10
Tool Use Delegation5/10

Scores are AI-estimated from publicly available data — not an independent test or a verified user rating. How we rank →

Capabilities
Code
Code Review
Automation
Vision
Categories
Code Assistant
Cybersecurity
Limitations
  • -SWE-agent is now in maintenance-only mode, with development focused on mini-swe-agent
  • -Requires a language model of choice (e.g., GPT-4o or Claude Sonnet 4) to function
Fit Score

Complexity

Advanced

Company Size

Solo
Small

Team Size

Individual
Small Team

Skill Level

Expert
Features
Autonomously fix GitHub issues
Find cybersecurity vulnerabilities
Perform custom tasks
State of the art on SWE-bench among open-source projects
Configurable via a single YAML file
Supports multimodal input for images from GitHub issues
Allows adding custom tools
Technical Capabilities
SDK Available
MCP Compatible (unknown)
Multi-Agent (unknown)
Human-in-Loop (unknown)
Team Features
Webhook Support (unknown)
Has Demo
Function Calling
Sandbox Mode
Audit Logs
No Signup
Works Offline (unknown)
Requires Host App
Framework
MCP Server
Digital Employee

Deployment

Self Hosted
Developer Access
API
Public
Compliance, Privacy & Trust
GDPR: No info available
SOC 2: No info available
HIPAA: No info available
Trains on user data: Unknown
Human review:
Recommended
Tech Specs
Max upload: 10MB
Response time (est.):
Moderate

The Model(s) Behind It

Model details — extracted from public vendor sources by our pipeline (AI extraction plus a source check) or admin-entered. Shown as claimed by the vendor; not independently audited by Intelloro.

Uses Models
Bring your own model — use your own API key or endpoint

Underlying Model Benchmarks

Third-party leaderboard scores for the AI model(s) powering this — including price & speed. These describe the underlying model, not the product's own metrics.

llm-coding

SWE-bench Verified
Princeton + OpenAI 2024 · SWE-bench
66.6
67th pct

Best submission: "SWE-agent + Claude 4 Sonnet" (2025-05-22)

11/15/2026·source

Scores from official leaderboards or vendor-reported. Percentile is cross-benchmark normalized when populated by an aggregator. See methodology.

Training Data Provenance
Not disclosed
Relevant to EU AI Act Art. 53 / Annex XI (GPAI)
Supported Tools
Bash Tool (Terminal)
Pricing Plans
Free
Free

    Looking for more SWE-agent alternatives?

    Explore our complete list of alternatives with filters for free, cheaper, and higher-rated options.

    View All Alternatives

    User Reviews

    No reviews yet. Be the first to review!

    Who It's For
    4 roles
    Software DevelopersComputer ProgrammersWeb Developers+1 more
    Platform, Content & Languages
    2 content types
    1 languages
    CodeTextEnglish+6 more

    Output Languages

    English

    Content Types

    Code
    Text

    Accepts

    Text
    Image
    Code
    URL

    Produces

    Code
    Text
    Languages: English

    Frequently Asked Questions

    What can SWE-agent do?

    SWE-agent can: Autonomously fix GitHub issues, Find cybersecurity vulnerabilities, Perform custom tasks, State of the art on SWE-bench among open-source projects. Best for: Researchers building and evaluating autonomous coding agents.

    How much does SWE-agent cost?

    SWE-agent is open source and free to self-host. Cloud hosting options may have separate pricing.

    Is SWE-agent free?

    Yes, SWE-agent is open source and free to self-host. Managed hosting may carry separate costs.

    What makes SWE-agent unique?

    SWE-agent is built for research, offering a simple and hackable design that provides maximal agency to the language model, making it highly generalizable for various coding tasks.

    Does SWE-agent have an API?

    Yes, SWE-agent offers a public API for developers to integrate its capabilities into custom applications and workflows.

    What platforms does SWE-agent support?

    SWE-agent is available on CLI and API.

    What languages does SWE-agent support?

    SWE-agent supports English.

    Who is SWE-agent for?

    SWE-agent is designed for Researchers building and evaluating autonomous coding agents; Developers automating GitHub issue resolution; Cybersecurity professionals identifying vulnerabilities with AI.

    Trust Score

    60/100

    Good

    Based on 6 data signals

    Evidence: 5 of 12 expected facts verified · highest possible score 60

    Evidence strength: Strong

    Reflects publicly available data, not an independent audit

    Compliance & Verified38/38
    VerifiedYes
    Open-source licenseMIT
    Human ReviewYes
    Reliability0/10

    No published data

    Company17/17
    Company ListedYes
    User Base10K-100K
    FundingGrant
    Health—

    Not yet checked

    AI-Assisted Data

    Some details are AI-generated estimates — verify with the vendor.

    AI-generated estimate: Best For, What Makes Unique

    How we source data

    AI Governance & Regulatory Disclosures

    Legally-sensitive fields — extracted from public vendor sources by our pipeline (AI extraction plus a source check) or admin-entered. Shown as claimed by the vendor; not independently audited by Intelloro.

    EU AI Act Risk Tier
    Unclassified

    Switching & Migration

    Migration Difficulty
    Moderate Effort
    Support:
    GitHub
    Documentation
    Community
    Quick Stats
    Agent TypeAutonomous
    MemoryShort Term
    PlanningBasic
    PlatformsCLI, API
    User Base10K-100K
    LaunchedApr 2024
    VerifiedOct 2026
    Company & Links
    Company NamePrinceton University
    Based inUnited States
    Last major updateJul 2024
    FundingGrant
    DocumentationChangelog

      We value your privacy

      We use cookies to enhance your browsing experience, analyze site traffic, and personalize content. Privacy Policy•Cookie Policy