base on Buttercup finds and patches software vulnerabilities # Buttercup Cyber Reasoning System (CRS) [](https://github.com/trailofbits/buttercup/actions/workflows/tests.yml) [](https://github.com/trailofbits/buttercup/actions/workflows/comp-integration.yml) [](https://github.com/trailofbits/buttercup/actions/workflows/integration.yml) **Buttercup** is a Cyber Reasoning System (CRS) developed by **Trail of Bits** for the **DARPA AIxCC (AI Cyber Challenge)**. Buttercup finds and patches software vulnerabilities in open-source code repositories like [example-libpng](https://github.com/tob-challenges/example-libpng). It starts by running an AI/ML-assisted fuzzing campaign (built on oss-fuzz) for the program. When vulnerabilities are found, Buttercup analyzes them and uses a multi-agent AI-driven patcher to repair the vulnerability. **Buttercup** system consists of several components: - **Orchestrator**: Coordinates the overall task process and manages the workflow - **Seed Generator**: Creates inputs for vulnerability discovery - **Fuzzer**: Discovers vulnerabilities through intelligent fuzzing techniques - **Program Model**: Analyzes code structure and semantics for better understanding - **Patcher**: Generates and applies security patches to fix vulnerabilities ## System Requirements ### Minimum Requirements - **CPU:** 8 cores - **Memory:** 16 GB RAM - **Storage:** 100 GB available disk space - **Network:** Stable internet connection for downloading dependencies **Note:** Buttercup uses third-party AI providers (LLMs from companies like OpenAI, Anthropic and Google), which cost money. Please ensure that you manage per-deployment costs by using the built-in LLM budget setting. **Note:** Buttercup works best with access to models from OpenAI **and** Anthropic, but can be run with at least one API key from one third-party provider. You can use a combination of OpenAI, Anthropic, and Google LLMs. ### Supported Systems - **Linux x86_64** (fully supported) - **ARM64** (partial support for upstream Google OSS-Fuzz projects) ### Required System Packages Before setup, ensure you have these packages installed: ```bash # Ubuntu/Debian sudo apt-get update sudo apt-get install -y make curl git # RHEL/CentOS/Fedora sudo yum install -y make curl git # or sudo dnf install -y make curl git # MacOS brew install make curl git ``` ### Supported Targets Buttercup works with: - **C source code repositories** that are OSS-Fuzz compatible - **Java source code repositories** that are OSS-Fuzz compatible - Projects that build successfully and have existing fuzzing harnesses ## Quick Start 1. Clone the repository with submodules: ```bash git clone --recurse-submodules https://github.com/trailofbits/buttercup.git cd buttercup ``` 1. Run automated setup (Recommended) ```bash make setup-local ``` This script will install all dependencies, configure the environment, and guide you through the setup process. **Note:** If you prefer manual setup, see the [Manual Setup Guide](guides/MANUAL_SETUP.md). 1. Start Buttercup locally ```bash make deploy ``` 1. Verify local deployment: ```bash make status ``` When a deployment is successful, you should see all pods in "Running" or "Completed" status. 1. Send Buttercup a simple task **Note:** When tasked, Buttercup will start consuming third-party AI resources. This command will make Buttercup pull down an example repo [example-libpng](https://github.com/tob-challenges/example-libpng) with a known vulnerability. Buttercup will start fuzzing it to find and patch vulnerabilities. ```bash make send-libpng-task ``` 1. Access Buttercup's web-based GUI Run: ```bash make web-ui ``` Then navigate to `http://localhost:31323` in your web browser. In the GUI you can monitor active tasks and see when Buttercup finds bugs and generates patches for them. 1. Stop Buttercup **Note:** This is an important step to ensure Buttercup shuts down and stops consuming third-party AI resources. ```bash make undeploy ``` ## Accessing Logs Buttercup includes local SigNoz deployment by default for comprehensive system observability. You can access logs, traces, and metrics through the SigNoz UI: ```bash make signoz-ui ``` Then navigate to `http://localhost:33301` in your web browser to view: - Distributed traces - Application metrics - Error monitoring - Performance insights If you configured LangFuse during setup, you can also monitor LLM usage and costs there. For additional log access methods, see the [Quick Reference Guide](guides/QUICK_REFERENCE.md). ## Additional Resources - [Quick Reference Guide](guides/QUICK_REFERENCE.md) - Common commands and troubleshooting - [Manual Setup Guide](guides/MANUAL_SETUP.md) - Detailed manual installation steps - [AKS Deployment Guide](guides/AKS_DEPLOYMENT.md) - Production deployment on Azure - [Contributing Guidelines](CONTRIBUTING.md) - Development workflow and standards - [Deployment Documentation](deployment/README.md) - Advanced deployment configuration - [Writing Custom Challenges](guides/CUSTOM_CHALLENGES.md) - Custom project configuration and setup - [Unscored rounds](guides/UNSCORED.md) - Running unscored round challenges - [Scored round](guides/SCORED.md) - Parsing post-final round results ", Assign "at most 3 tags" to the expected json: {"id":"14563","tags":[]} "only from the tags list I provide: [{"id":77,"name":"3d"},{"id":89,"name":"agent"},{"id":17,"name":"ai"},{"id":54,"name":"algorithm"},{"id":24,"name":"api"},{"id":44,"name":"authentication"},{"id":3,"name":"aws"},{"id":27,"name":"backend"},{"id":60,"name":"benchmark"},{"id":72,"name":"best-practices"},{"id":39,"name":"bitcoin"},{"id":37,"name":"blockchain"},{"id":1,"name":"blog"},{"id":45,"name":"bundler"},{"id":58,"name":"cache"},{"id":21,"name":"chat"},{"id":49,"name":"cicd"},{"id":4,"name":"cli"},{"id":64,"name":"cloud-native"},{"id":48,"name":"cms"},{"id":61,"name":"compiler"},{"id":68,"name":"containerization"},{"id":92,"name":"crm"},{"id":34,"name":"data"},{"id":47,"name":"database"},{"id":8,"name":"declarative-gui "},{"id":9,"name":"deploy-tool"},{"id":53,"name":"desktop-app"},{"id":6,"name":"dev-exp-lib"},{"id":59,"name":"dev-tool"},{"id":13,"name":"ecommerce"},{"id":26,"name":"editor"},{"id":66,"name":"emulator"},{"id":62,"name":"filesystem"},{"id":80,"name":"finance"},{"id":15,"name":"firmware"},{"id":73,"name":"for-fun"},{"id":2,"name":"framework"},{"id":11,"name":"frontend"},{"id":22,"name":"game"},{"id":81,"name":"game-engine "},{"id":23,"name":"graphql"},{"id":84,"name":"gui"},{"id":91,"name":"http"},{"id":5,"name":"http-client"},{"id":51,"name":"iac"},{"id":30,"name":"ide"},{"id":78,"name":"iot"},{"id":40,"name":"json"},{"id":83,"name":"julian"},{"id":38,"name":"k8s"},{"id":31,"name":"language"},{"id":10,"name":"learning-resource"},{"id":33,"name":"lib"},{"id":41,"name":"linter"},{"id":28,"name":"lms"},{"id":16,"name":"logging"},{"id":76,"name":"low-code"},{"id":90,"name":"message-queue"},{"id":42,"name":"mobile-app"},{"id":18,"name":"monitoring"},{"id":36,"name":"networking"},{"id":7,"name":"node-version"},{"id":55,"name":"nosql"},{"id":57,"name":"observability"},{"id":46,"name":"orm"},{"id":52,"name":"os"},{"id":14,"name":"parser"},{"id":74,"name":"react"},{"id":82,"name":"real-time"},{"id":56,"name":"robot"},{"id":65,"name":"runtime"},{"id":32,"name":"sdk"},{"id":71,"name":"search"},{"id":63,"name":"secrets"},{"id":25,"name":"security"},{"id":85,"name":"server"},{"id":86,"name":"serverless"},{"id":70,"name":"storage"},{"id":75,"name":"system-design"},{"id":79,"name":"terminal"},{"id":29,"name":"testing"},{"id":12,"name":"ui"},{"id":50,"name":"ux"},{"id":88,"name":"video"},{"id":20,"name":"web-app"},{"id":35,"name":"web-server"},{"id":43,"name":"webassembly"},{"id":69,"name":"workflow"},{"id":87,"name":"yaml"}]" returns me the "expected json"