{"id":25204469,"url":"https://github.com/afri-bit/debugsprai","last_synced_at":"2026-02-21T04:33:43.945Z","repository":{"id":276217940,"uuid":"926254232","full_name":"afri-bit/DebugsprAI","owner":"afri-bit","description":"Automatic Coder using AI","archived":false,"fork":false,"pushed_at":"2025-02-19T22:15:04.000Z","size":221,"stargazers_count":2,"open_issues_count":1,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-10-14T15:11:47.088Z","etag":null,"topics":["ai","artificial-intelligence","autodebug","automation","debug","gemini","githubactions","google","google-gemini-ai","googleg","issues","llm","python"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/afri-bit.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2025-02-02T22:34:25.000Z","updated_at":"2025-02-19T22:15:08.000Z","dependencies_parsed_at":"2025-06-19T07:06:02.303Z","dependency_job_id":"3cfde1ca-9180-4a78-ba48-d275ed923954","html_url":"https://github.com/afri-bit/DebugsprAI","commit_stats":null,"previous_names":["afri-bit/ai-coder","afri-bit/debugsprai"],"tags_count":1,"template":false,"template_full_name":null,"purl":"pkg:github/afri-bit/DebugsprAI","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/afri-bit%2FDebugsprAI","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/afri-bit%2FDebugsprAI/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/afri-bit%2FDebugsprAI/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/afri-bit%2FDebugsprAI/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/afri-bit","download_url":"https://codeload.github.com/afri-bit/DebugsprAI/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/afri-bit%2FDebugsprAI/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29673785,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-02-21T03:11:15.450Z","status":"ssl_error","status_checked_at":"2026-02-21T03:10:34.920Z","response_time":107,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai","artificial-intelligence","autodebug","automation","debug","gemini","githubactions","google","google-gemini-ai","googleg","issues","llm","python"],"created_at":"2025-02-10T08:18:07.303Z","updated_at":"2026-02-21T04:33:43.903Z","avatar_url":"https://github.com/afri-bit.png","language":"Python","readme":"# DebugsprAI - The Bug Spray\n\n![Python](https://img.shields.io/badge/python-3670A0?style=for-the-badge\u0026logo=python\u0026logoColor=ffdd54)\n![Google Gemini](https://img.shields.io/badge/google%20gemini-8E75B2?style=for-the-badge\u0026logo=google%20gemini\u0026logoColor=white)\n![GitHub Actions](https://img.shields.io/badge/github%20actions-%232671E5.svg?style=for-the-badge\u0026logo=githubactions\u0026logoColor=white)\n![GitHub](https://img.shields.io/badge/github-%23121011.svg?style=for-the-badge\u0026logo=github\u0026logoColor=white)\n![Linux](https://img.shields.io/badge/Linux-FCC624?style=for-the-badge\u0026logo=linux\u0026logoColor=black)\n![Git](https://img.shields.io/badge/git-%23F05033.svg?style=for-the-badge\u0026logo=git\u0026logoColor=white)\n\n\u003ch2 align=\"center\"\u003e\n🌟 The Ultimate AI-Powered Debugging Assistant 🌟\n\u003c/h2\u003e\n\n![](resources/img/debugsprai.svg)\n\nWelcome to **debugsprAI**, where AI meets automation to revolutionize debugging! 🐞🔫\n\nIn today's fast-paced development world, AI isn't just assisting—it's solving real problems. From writing code to detecting vulnerabilities, AI is reshaping the way developers work. **DebugsprAI** takes it a step further by automatically fixing bugs directly from GitHub issues, making debugging effortless and efficient.\n\nImagine this: A developer opens an issue describing a bug. Instead of waiting for manual intervention, **DebugsprAI** jumps in, scans the source code, applies a fix, and submits a pull request—*automatically*.  \nNo delays, no bottlenecks, just seamless AI-powered debugging.\n\n\u003e Even better when AI is integrated into the review process in the automated manner.\n\n## Table of Content \u003c!-- omit header--\u003e\n\n- [Table of Content ](#table-of-content-)\n- [Proof of Concept](#proof-of-concept)\n  - [Technology Stacks](#technology-stacks)\n- [Installation](#installation)\n  - [Prerequisites](#prerequisites)\n  - [Setup](#setup)\n- [How to Use](#how-to-use)\n  - [Subcommand `debug`](#subcommand-debug)\n  - [Subcommand `parse`](#subcommand-parse)\n- [🎯 Why Choose _DebugsprAI_?](#-why-choose-debugsprai)\n- [🚀 Future Enhancements](#-future-enhancements)\n- [🤝🏻 Contributing](#-contributing)\n- [💡 Have feedback or ideas? Create an issue or reach out!](#-have-feedback-or-ideas-create-an-issue-or-reach-out)\n- [🪪 License](#-license)\n\n## Proof of Concept\n\nDebugsprAI is a proof of concept project that demonstrates AI-powered bug fixing. It is built with Python and integrates Google's Gemini LLM, leveraging GitHub Actions to automate the debugging workflow.\n\nThe system listens for newly created GitHub issues, analyzes the reported problem, identifies the affected code, and applies intelligent fixes. Here's how it works:\n\n1. **Issue Detection** – When a developer reports a bug on GitHub, DebugsprAI captures the issue.\n2. **AI-Powered Analysis** – The AI (Gemini) interprets the issue description, locates the relevant code, and suggests potential fixes.\n3. **Automated Code Modification** – Using AI-driven debugging, it adjusts the source code accordingly.\n4. **Pull Request Generation** – The fixed code is committed, and a pull request is automatically created for review.\nThis project explores the potential of AI in software debugging, automating tedious processes to enhance development efficiency. 🔥\n\n### Technology Stacks\n\n![Python](https://img.shields.io/badge/python-3670A0?style=for-the-badge\u0026logo=python\u0026logoColor=ffdd54)\n![Google Gemini](https://img.shields.io/badge/google%20gemini-8E75B2?style=for-the-badge\u0026logo=google%20gemini\u0026logoColor=white)\n![GitHub Actions](https://img.shields.io/badge/github%20actions-%232671E5.svg?style=for-the-badge\u0026logo=githubactions\u0026logoColor=white)\n![GitHub](https://img.shields.io/badge/github-%23121011.svg?style=for-the-badge\u0026logo=github\u0026logoColor=white)\n\n## Installation\n\n**DebugsprAI** is a proof of concept project, therefore there is no python package deployed, that can be downloaded via package manager.\n\nIn this section we will guide you through the installation process.\n\n### Prerequisites\n\n- Python 3.9+\n- Google Gemini Access (The API Key)\n  \u003e More LLM will be supported in the future.\n\n### Setup\n\n```bash\n# Clone the repository\ngit clone https://github.com/afri-bit/DebugsprAI.git\n\n# Change directory to the project directory\ncd DebugsprAI\n\n# Install project\npip install .\n\n# Setup API Key\nexport GEMINI_API_KEY=\u003cyour_api_key_here\u003e\n```\n\n**Optional**\n\n```bash\nexport GEMINI_MODEL_NAME=gemini-2.0-flash-exp\n```\n\n\u003e You can set the model as you required, but the whole setup currently is tested under the `gemini-2.0-flash-exp` model.  \n\u003e Unpredicted behaviour may occur, if you take different model.\n\n## How to Use\n\nThe **DebugsprAI** application relies on specific user inputs, that is constructed as people normally describe an issue in the github or another repository.  \nThis application is targeted to run not only for the automation, but also on your local machine. It takes a JSON file with specific format as the main input.\n\nAs the first step, let's make sure that the application is installed properly by executing following command\n\n```bash\ndebugsprai --help\n```\n\nIf everything is installed correctly you will see following output on your terminal\n\n```bash\nUsage: debugsprai [OPTIONS] COMMAND [ARGS]...\n\nOptions:\n  --help  Show this message and exit.\n\nCommands:\n  debug  _summary_\n  parse  Sub command to parse issue markdown file to json format\n```\n\n### Subcommand `debug`\n\nThis subcommand is the core of the application to debug with help of LLM.\n\nIt takes a JSON file as input with following format:\n\n```json\n{\n  \"id\": 1,\n  \"title\": \"Some Bug\",\n  \"summary\": \"This bug has something to do with errors\",\n  \"severity_level\": \"Low (minor issue, doesn't block usage)\",\n  \"programming_language\": \"python\",\n  \"project_folder\": \".\",\n  \"source_folder\": \"src\",\n  \"test_folder\": \"tests\",\n  \"system_information\": \"Linux\",\n  \"actual_behavior\": \"Actual behaviour is not working as expected\",\n  \"expected_behavior\": \"The function must be working\",\n  \"logs\": \"some logs\"\n}\n```\n\nBased on the provided in the JSON file, the request will be sent to LLM and your files in the project will be scanned based on the `programming_language` you choose.\n\n\u003e Currently we only support `python` as proof of concept.\n\nAfter the process is done, you can see the result under the folder `.airesults`. The LLM will only make the necesssary to the files, that may be related to the description in the issue. The changes will be marked with `AIFIX` comments.\n\nIn the folder `.airesults` you will find the folder called `project` where the folder structure will be structured exactly as in your project. The last step you have to do is just copy the whole folder into your project, and you will notice the changes.\n\n\u003e LLM will not change anything unless it is necessary.\n\n### Subcommand `parse`\n\nThe command is intended as a helper function to parse a specific style of the markdown file and convert it to JSON file, that is required for `debug` command as input.\n\nFollowing is the example of the markdown file, that is derived from github issue.\n\n```markdown\n### Summary\n\n\u003cYour Summary\u003e\n\n### Severity Level\n\n\u003cLow, Medium, High\u003e\n\n### Programming Language\n\n\u003cpython\u003e\n\n### Project Folder\n\n.\n\n### Source Folder\n\nsrc\n\n### Test Folder\n\ntests\n\n### System Information\n\nLinux\n\n### Actual Behavior\n\n\u003cDescribe the current behaviour\u003e\n\n### Expected Behavior\n\n\u003cDescribe the expected behaviour\u003e\n\n### Logs\n\n\u003cPut your log information here\u003e\n```\n\n## 🎯 Why Choose _DebugsprAI_?\n\n✅ **Saves developer time** - No more manual debugging bottlenecks.\\\n✅ **Seamless GitHub integration** - Works directly with your existing workflows.\\\n✅ **AI-powered accuracy** - Smart debugging with minimal false positives.\\\n✅ **Automated PRs** - Fixes are delivered in a developer-friendly way.\n\n## 🚀 Future Enhancements\n\nWe're continuously improving **DebugsprAI** to:\n\n- Support multiple programming languages\n- Enhance bug-fixing accuracy with fine-tuned models\n- Introduce custom AI training for project-specific debugging\n\n## 🤝🏻 Contributing\n\nJoin the revolution in AI-driven debugging! Fork the project, contribute, and help shape the future of **DebugsprAI**.\n\n💡 Have feedback or ideas? Create an issue or reach out!\n---\n\n🔗 [GitHub Repository](https://github.com/afri-bit/DebugsprAI) | 🚀 Happy Debugging! 🐞\n\n\n## 🪪 License\n\nMIT\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fafri-bit%2Fdebugsprai","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fafri-bit%2Fdebugsprai","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fafri-bit%2Fdebugsprai/lists"}