{"id":45593058,"url":"https://github.com/aayush0325/reverse-engineering-agent","last_synced_at":"2026-02-23T13:01:43.065Z","repository":{"id":336665995,"uuid":"1150663917","full_name":"aayush0325/reverse-engineering-agent","owner":"aayush0325","description":"a small ai agent to solve crackmes, WIP","archived":false,"fork":false,"pushed_at":"2026-02-05T14:49:43.000Z","size":92,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"master","last_synced_at":"2026-02-06T01:21:21.108Z","etag":null,"topics":["ai-agents","langgraph","reverse-engineering"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/aayush0325.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-02-05T14:46:49.000Z","updated_at":"2026-02-05T14:49:56.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/aayush0325/reverse-engineering-agent","commit_stats":null,"previous_names":["aayush0325/reverse-engineering-agent"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/aayush0325/reverse-engineering-agent","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aayush0325%2Freverse-engineering-agent","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aayush0325%2Freverse-engineering-agent/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aayush0325%2Freverse-engineering-agent/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aayush0325%2Freverse-engineering-agent/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/aayush0325","download_url":"https://codeload.github.com/aayush0325/reverse-engineering-agent/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aayush0325%2Freverse-engineering-agent/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29743765,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-02-23T07:44:07.782Z","status":"ssl_error","status_checked_at":"2026-02-23T07:44:07.432Z","response_time":90,"last_error":"SSL_read: 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-agents","langgraph","reverse-engineering"],"created_at":"2026-02-23T13:01:13.829Z","updated_at":"2026-02-23T13:01:43.059Z","avatar_url":"https://github.com/aayush0325.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Reverse Engineering Agent\n\nAn autonomous agentic system designed to analyze, reverse engineer, and solve binary challenges (crackmes) using static and dynamic analysis. Powered by LangGraph and multiple LLM providers.\n\n## Features\n\n-   **Multi-Agent Architecture**: Discrete agents for Planning, Execution, Observation, and Criticism.\n-   **Interactive Binary Analysis**: Integrated `pexpect` for handling TTY-style interactive prompts in binaries.\n-   **Dynamic Analysis**: GDB integration for deep inspection of program flow and memory.\n-   **Multi-Provider Support**: Switch between **Groq** (fast inference) and **Google Gemini** (large context, advanced reasoning).\n-   **Structured State Management**: Maintains a comprehensive state of observations, hypotheses, and artifact discoveries.\n-   **Self-Correction**: The Critic agent detects circular reasoning or failures and prompts the Planner to adapt.\n\n## Architecture\n\nThe system uses **LangGraph** to manage the lifecycle of an analysis task:\n\n```mermaid\ngraph TD\n    Start --\u003e Planner\n    Planner --\u003e Executor\n    Executor --\u003e Observation\n    Observation --\u003e Critic\n    Critic -- Unsatisfied --\u003e Planner\n    Critic -- Satisfied --\u003e End\n```\n\n-   **Planner**: Analyzes the goal and current state to generate a sequence of tool calls.\n-   **Executor**: Translates natural language steps into concrete tool inputs (e.g., GDB commands or `stdin` payloads).\n-   **Observation**: Parses raw tool outputs into structured observations and updates the model of the target binary.\n-   **Critic**: Evaluates progress towards the goal, identifies missing information, and determines when to terminate.\n\n## Toolset\n\n-   **Static**: `strings`, `file`, `hexdump`.\n-   **Dynamic**: `run_binary` (via `pexpect`), `gdb`.\n\n## Getting Started\n\n### Prerequisites\n\n-   [uv](https://github.com/astral-sh/uv) (for package management)\n-   GCC (to compile examples)\n-   GDB (for dynamic analysis)\n\n### Installation\n\n1.  Clone the repository:\n    ```bash\n    git clone https://github.com/aayush/reverse-engineering-agent.git\n    cd reverse-engineering-agent\n    ```\n\n2.  Install dependencies:\n    ```bash\n    uv sync\n    ```\n\n3.  Configure environment:\n    Create a `.env` file with your API keys:\n    ```bash\n    GROQ_API_KEY=your_groq_key\n    GOOGLE_API_KEY=your_google_key\n    ```\n\n### Usage\n\nAnalyze a binary by providing its path and your goal:\n\n```bash\nuv run python main.py --path ./example/demo --prompt \"find the secret license key\" --provider gemini\n```\n\n### CLI Arguments\n\n| Argument | Description | Default |\n| :--- | :--- | :--- |\n| `--path` | **Required**. Absolute or relative path to the binary. | N/A |\n| `--prompt` | **Required**. The analysis goal or question. | N/A |\n| `--provider` | LLM provider to use (`groq`, `gemini`). | `groq` |\n| `--model` | Specific model identifier (optional). | Default for provider |\n\n## Examples\n\nThe `example/` directory contains a sample `demo.c` challenge. You can compile and run it with:\n\n```bash\n./demo.sh\n```\n\n## Contributing\n\nThis project is a experimental prototype for agentic reverse engineering. Feel free to open issues or submit PRs to improve tool integration or agent reasoning!\n\n---\n*Built with love by aayush*\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faayush0325%2Freverse-engineering-agent","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Faayush0325%2Freverse-engineering-agent","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faayush0325%2Freverse-engineering-agent/lists"}