# SWE-agent/SWE-agent

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/swe-agent-swe-agent).**

18,510 stars · 1,992 forks · Python · mit

## Links

- GitHub: https://github.com/SWE-agent/SWE-agent
- Homepage: https://swe-agent.com
- awesome-repositories: https://awesome-repositories.com/repository/swe-agent-swe-agent.md

## Topics

`agent` `agent-based-model` `ai` `cybersecurity` `developer-tools` `llm` `lms`

## Description

SWE-agent is an autonomous software engineering platform designed to automate repository maintenance and issue resolution. By orchestrating language models to navigate codebases, diagnose software bugs, and apply fixes, the framework functions as an autonomous agent capable of executing shell commands, editing source code, and managing pull requests within isolated, containerized environments.

The platform distinguishes itself through its focus on end-to-end task autonomy and observability. It features a robust trajectory logging system that records every thought, action, and environment observation, providing a complete audit trail for debugging and human review. The agent supports multimodal input, allowing it to process visual content from screenshots and diagrams to resolve complex user interface issues, while its web interaction capabilities enable it to navigate external sites and perform browser-based tasks.

The framework provides a comprehensive suite of operational utilities for managing the agent lifecycle, including parallel execution management, automated code formatting, and syntax validation to ensure patch quality. It offers extensive configuration options for custom toolsets and interaction prompts, alongside security mechanisms that restrict unauthorized commands. Users can maintain oversight through human intervention support, allowing for manual overrides during active execution.

The project is available as a source-based installation for local environments or can be deployed within web-based development environments.

## Tags

### Artificial Intelligence & ML

- [Autonomous Software Engineering](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-architectures/ai-agents/software-engineering/autonomous-software-engineering.md) — Provides an autonomous agent that navigates codebases, diagnoses software bugs, and applies fixes within isolated environments.
- [Coding Agents](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/integration-deployment/ai-agent-tooling/coding-agents.md) — Ships a framework for building and deploying autonomous agents that interact with version control and shell environments to resolve software tasks.
- [AI Development Tools](https://awesome-repositories.com/f/artificial-intelligence-ml/ai-development-tools.md) — Automates repository maintenance and issue resolution by orchestrating language model decision-making with custom toolsets.
- [Language Model Integrations](https://awesome-repositories.com/f/artificial-intelligence-ml/artificial-intelligence-tooling/language-model-integrations.md) — Connects to various language models to power autonomous decision-making and task execution. ([source](https://swe-agent.com/latest/installation/keys/))
- [LLM-Driven Agent Loops](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/integration-deployment/agent-frameworks/agent-runtimes/llm-driven-agent-loops.md) — Parses language model outputs into structured tool calls and shell commands to manage the agent interaction loop.
- [Human-in-the-Loop Workflows](https://awesome-repositories.com/f/artificial-intelligence-ml/human-in-the-loop-workflows.md) — Enables human users to manually provide input or override agent decisions during active execution. ([source](https://swe-agent.com/latest/reference/model_config/))
- [Agent Observability Tools](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-observability-tools.md) — Logs every thought, action, observation, and environment state change during an autonomous task to provide a complete audit trail. ([source](https://swe-agent.com/latest/usage/trajectories/))
- [Agent Configurations](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/agent-orchestration-multi-agent/autonomous-agents/agent-configurations.md) — Defines custom toolsets, interaction prompts, and model parameters through modular configuration files. ([source](https://swe-agent.com/latest/config/config/))
- [Custom Tool Definitions](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/integration-deployment/agent-frameworks/tool-definitions-and-registration/custom-tool-definitions.md) — Creates executable commands with custom arguments and documentation for agent interaction. ([source](https://swe-agent.com/latest/reference/bundle_config/))
- [Context Window Management](https://awesome-repositories.com/f/artificial-intelligence-ml/context-window-management.md) — Compresses interaction history and filters observation data to maintain focus within model token limits.
- [Multimodal Vision Inputs](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/multimodal-processing-tools/multimodal-vision-inputs.md) — Processes visual content from screenshots and diagrams to provide context for vision-capable language models.
- [Agent State Persistence](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-state-persistence.md) — Provides a key-value registry for storing and retrieving complex data structures that persist across tool invocations. ([source](https://swe-agent.com/latest/usage/adding_custom_tools/))
- [Multimodal Agent Capabilities](https://awesome-repositories.com/f/artificial-intelligence-ml/multimodal-agent-capabilities.md) — Integrates image processing and web browsing into the agent workflow to resolve issues involving visual content. ([source](https://swe-agent.com/latest/config/))
- [Multimodal Analysis Tools](https://awesome-repositories.com/f/artificial-intelligence-ml/multimodal-analysis-tools.md) — Integrates visual context from screenshots and diagrams into agent workflows to resolve complex user interface issues.
- [Agent Result Aggregators](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/integration-deployment/agent-frameworks/agent-evaluation-frameworks/agent-result-aggregators.md) — Collects and merges generated patches from multiple concurrent agent runs into a unified output. ([source](https://swe-agent.com/latest/usage/batch_mode/))
- [Agent Demonstration Recorders](https://awesome-repositories.com/f/artificial-intelligence-ml/autonomous-agent-frameworks/agent-demonstration-recorders.md) — Records manual interaction sequences to guide future autonomous agent behavior. ([source](https://swe-agent.com/latest/config/demonstrations/))
- [Output Processors](https://awesome-repositories.com/f/artificial-intelligence-ml/model-output-formatting/output-processors.md) — Extracts structured tool calls, commands, and reasoning text from language model responses using specific formatting patterns. ([source](https://swe-agent.com/latest/reference/parsers/))
- [Prompt Caching Strategies](https://awesome-repositories.com/f/artificial-intelligence-ml/prompt-caching-strategies.md) — Reduces operational costs and improves response times by setting specific cache break points that allow language models to reuse previously processed data. ([source](https://swe-agent.com/latest/config/models/))

### Development Tools & Productivity

- [Automated Issue Resolvers](https://awesome-repositories.com/f/development-tools-productivity/issue-trackers/automated-issue-resolvers.md) — Automates the end-to-end lifecycle of repository issues by using language models to reproduce bugs and submit patches.
- [Autonomous Repository Managers](https://awesome-repositories.com/f/development-tools-productivity/repository-management-tools/autonomous-repository-managers.md) — Automates software engineering workflows by executing shell commands, editing source code, and managing pull requests through language models.
- [Automated Code Editing Assistants](https://awesome-repositories.com/f/development-tools-productivity/automated-code-editing-assistants.md) — Modifies source code files using search-and-replace or line-range operations to implement automated fixes. ([source](https://swe-agent.com/latest/config/tools/))
- [Containerized Development Workflows](https://awesome-repositories.com/f/development-tools-productivity/containerized-development-workflows.md) — Executes software tasks within secure, isolated containerized environments to ensure consistent dependency management.
- [AI Agent Benchmarks](https://awesome-repositories.com/f/development-tools-productivity/debugging-profiling-testing/ai-agent-benchmarks.md) — Executes agents against standardized coding tasks to measure performance and resolve issues. ([source](https://swe-agent.com/latest/usage/competitive_runs/))
- [Isolated Execution Environments](https://awesome-repositories.com/f/development-tools-productivity/isolated-execution-environments.md) — Spawns containerized shell sessions to safely execute commands and interact with repository files in isolated environments. ([source](https://swe-agent.com/latest/background/architecture/))
- [Shell Command Runners](https://awesome-repositories.com/f/development-tools-productivity/shell-command-runners.md) — Executes arbitrary shell commands within containerized environments and captures output, exit codes, and errors. ([source](https://swe-agent.com/latest/config/tools/))
- [Code Formatting Tools](https://awesome-repositories.com/f/development-tools-productivity/code-quality-analysis/static-analysis-engines/static-analysis-tools/code-formatting-tools.md) — Applies consistent project-wide code style rules to resolve merge conflicts and ensure quality. ([source](https://swe-agent.com/latest/dev/formatting_conflicts/))

### DevOps & Infrastructure

- [Web Interaction Agents](https://awesome-repositories.com/f/devops-infrastructure/automation-orchestration/task-execution-frameworks/automation-frameworks/ai-agent-control/web-interaction-agents.md) — Navigates websites and performs browser-based actions to automate web interaction tasks. ([source](https://swe-agent.com/latest/usage/multimodal/))
- [Containerized Execution Environments](https://awesome-repositories.com/f/devops-infrastructure/containerized-execution-environments.md) — Executes agents within containerized environments to ensure consistent dependency management and security. ([source](https://swe-agent.com/latest/config/environments/))
- [Agent Batch Orchestrators](https://awesome-repositories.com/f/devops-infrastructure/distributed-task-orchestrators/agent-batch-orchestrators.md) — Orchestrates parallel agent instances across multiple repository issues while managing resource limits and API credentials.
- [Agent Task Managers](https://awesome-repositories.com/f/devops-infrastructure/automation-orchestration/task-execution-frameworks/task-job-management/task-schedulers/agent-task-managers.md) — Loads software engineering tasks from local files or datasets for autonomous resolution. ([source](https://swe-agent.com/latest/reference/batch_instances/))

### Security & Cryptography

- [Container-Based Sandboxes](https://awesome-repositories.com/f/security-cryptography/security/infrastructure-and-hardware/infrastructure-system-hardening/execution-sandboxes/container-based-sandboxes.md) — Runs autonomous agents within sandboxed container environments to ensure secure and consistent execution.
- [Path Access Restrictions](https://awesome-repositories.com/f/security-cryptography/security/policies/host-resource-access/file-system-access-controls/path-access-restrictions/path-access-restrictions.md) — Filters out interactive or unauthorized commands to prevent the agent from executing blocked operations within the environment. ([source](https://swe-agent.com/latest/reference/tools_config/))
- [API Credential Managers](https://awesome-repositories.com/f/security-cryptography/api-credential-managers.md) — Distributes requests across multiple authentication keys to bypass rate limits during automated sessions. ([source](https://swe-agent.com/latest/usage/competitive_runs/))

### Software Engineering & Architecture

- [Automated Patch Appliers](https://awesome-repositories.com/f/software-engineering-architecture/code-patching-engines/patch-generators/automated-patch-appliers.md) — Generates and applies patches to local files or opens pull requests upon issue resolution. ([source](https://swe-agent.com/latest/usage/cl_tutorial/))
- [Agent Tool Registries](https://awesome-repositories.com/f/software-engineering-architecture/modular-extension-architectures/agent-tool-registries.md) — Bundles custom shell commands and scripts into extensible collections for agent interaction.
- [Syntax Validation Linters](https://awesome-repositories.com/f/software-engineering-architecture/syntax-tree-analysis/syntax-inspection/syntax-validation-linters.md) — Prevents code edits from being applied if they contain syntax errors by running a linter. ([source](https://swe-agent.com/latest/background/aci/))

### System Administration & Monitoring

- [Agent Observability](https://awesome-repositories.com/f/system-administration-monitoring/agent-observability.md) — Includes a visual interface to navigate, search, and review the step-by-step actions taken by an autonomous agent during repository interaction tasks. ([source](https://swe-agent.com/latest/installation/migration/))
- [Agent Trajectory Logs](https://awesome-repositories.com/f/system-administration-monitoring/audit-logs/agent-trajectory-logs.md) — Records every thought, action, and observation into structured logs for debugging and audit trails.
- [Usage Limiters](https://awesome-repositories.com/f/system-administration-monitoring/usage-limiters/usage-limiters.md) — Monitors and halts agent execution when predefined thresholds for task costs, total costs, or API call counts are reached. ([source](https://swe-agent.com/latest/reference/exceptions/))
- [AI Cost Monitoring](https://awesome-repositories.com/f/system-administration-monitoring/ai-cost-monitoring.md) — Tracks cost metrics for unsupported or local language models to enable accurate expenditure monitoring and comparison. ([source](https://swe-agent.com/latest/config/models/))
- [Codebase Contextualizers](https://awesome-repositories.com/f/system-administration-monitoring/repository-inspection/codebase-contextualizers.md) — Reads and displays file contents and directory structures to provide agents with necessary codebase context. ([source](https://swe-agent.com/latest/config/tools/))