{"id":27443001,"url":"https://github.com/edolor/cipherwhisperer","last_synced_at":"2025-04-15T01:18:22.060Z","repository":{"id":287256643,"uuid":"964140682","full_name":"Edolor/cipherwhisperer","owner":"Edolor","description":"Cipher Whisperer is a state-of-the-art tool built with LangGraph that automates the process of detecting and decrypting ciphers embedded in text.","archived":false,"fork":false,"pushed_at":"2025-04-10T19:57:02.000Z","size":39,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-04-15T01:18:07.744Z","etag":null,"topics":["aiagents","cipher-algorithms","ciphertext","langchain","langgraph","openai"],"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/Edolor.png","metadata":{"files":{"readme":"readme.md","changelog":null,"contributing":null,"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":"2025-04-10T18:47:21.000Z","updated_at":"2025-04-10T19:57:05.000Z","dependencies_parsed_at":"2025-04-10T20:10:04.164Z","dependency_job_id":null,"html_url":"https://github.com/Edolor/cipherwhisperer","commit_stats":null,"previous_names":["edolor/cipherwhisperer"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Edolor%2Fcipherwhisperer","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Edolor%2Fcipherwhisperer/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Edolor%2Fcipherwhisperer/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Edolor%2Fcipherwhisperer/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Edolor","download_url":"https://codeload.github.com/Edolor/cipherwhisperer/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248986312,"owners_count":21194025,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","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":["aiagents","cipher-algorithms","ciphertext","langchain","langgraph","openai"],"created_at":"2025-04-15T01:18:21.383Z","updated_at":"2025-04-15T01:18:22.043Z","avatar_url":"https://github.com/Edolor.png","language":"Python","readme":"# Cipher Whisperer\n\n## Overview\n\nCipher Whisperer is a software project that aims to decrypt and analyze cipher texts using a graph-based approach. The project utilizes various software libraries and tools to process and transform the input text.\n\nGraph Architecture above.\n![Graph Architecture](architecture.png)\n\n## Software and Libraries Used\n\n* Python 3 as the primary programming language\n* `dotenv` for environment variable management\n* `langgraph` for graph-based processing and transformation\n* `langchain_core` and `langchain_openai` for natural language processing and AI-powered decryption\n* `pydantic` for data validation and parsing\n\n## Decryptors\n\nThe project features a range of decryptors, including:\n\n* BruteForceDecryptor: a brute-force decryptor that uses a list of English words to decrypt Caesar ciphers\n* Other decryptors (to be added in future updates)\n\n## Getting Started\n\n### Prerequisites\n\n* Python 3\n* Required libraries: `dotenv`, `langgraph`, `langchain_core`, `langchain_openai`, `pydantic`\n\n### Installation\n\n1. Clone this repository.\n2. Create a virtual environment.\n3. Install the required libraries: `pip install -r requirements.txt`\n4. Create a `.env` file with your environment variables (i.e. API keys) following the `.env.example` file\n\n### Running the Code\n\n1. Run the main script: `python main.py`\n2. Follow the prompts to input a cipher text and receive the decrypted output\n\n## Project Structure\n\n* `cipherwhisperer/`: main project directory\n\t+ `main.py`: entry point for the project\n\t+ `graph.py`: graph-based processing and transformation of input text\n\t+ `chains.py`: chain-based processing and transformation of input text\n\t+ `models.py`: data models for the project (e.g. `GraphState`)\n\t+ `decryptors.py`: decryptor implementations (e.g. BruteForceDecryptor)\n\t+ `.gitignore`: ignore file for Git\n\n## Contributing\n\nContributions are welcome! Please submit a pull request with your changes and a brief description of what you've added or fixed.\n\n## License\n\nThis project is licensed under the MIT License. See `LICENSE` for details.\n\n## Reference\n1. Yuan, Y., Jiao, W., Wang, W., Huang, J., He, P., Shi, S., \u0026 Tu, Z. (2024). GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher. In The Twelfth International Conference on Learning Representations [Link Here](https://openreview.net/forum?id=MbfAK4s61A). ","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fedolor%2Fcipherwhisperer","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fedolor%2Fcipherwhisperer","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fedolor%2Fcipherwhisperer/lists"}