{"id":25692680,"url":"https://github.com/0xdea/oneiromancer","last_synced_at":"2026-03-02T10:03:50.691Z","repository":{"id":278910739,"uuid":"935337120","full_name":"0xdea/oneiromancer","owner":"0xdea","description":"Reverse engineering assistant that uses a locally running LLM to aid with pseudocode analysis.","archived":false,"fork":false,"pushed_at":"2026-02-13T17:03:52.000Z","size":2251,"stargazers_count":120,"open_issues_count":0,"forks_count":11,"subscribers_count":1,"default_branch":"master","last_synced_at":"2026-02-14T00:51:48.369Z","etag":null,"topics":["aidapal","ollama","pseudo-code","reverse-engineering","vuln-dev"],"latest_commit_sha":null,"homepage":"https://ollama.com","language":"Rust","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/0xdea.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","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,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null},"funding":{"github":3562}},"created_at":"2025-02-19T09:30:51.000Z","updated_at":"2026-02-13T17:04:18.000Z","dependencies_parsed_at":null,"dependency_job_id":"735dab94-a783-4508-8cdb-1fa7c426ba5e","html_url":"https://github.com/0xdea/oneiromancer","commit_stats":null,"previous_names":["0xdea/oneiromancer"],"tags_count":19,"template":false,"template_full_name":null,"purl":"pkg:github/0xdea/oneiromancer","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/0xdea%2Foneiromancer","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/0xdea%2Foneiromancer/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/0xdea%2Foneiromancer/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/0xdea%2Foneiromancer/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/0xdea","download_url":"https://codeload.github.com/0xdea/oneiromancer/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/0xdea%2Foneiromancer/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29995910,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-03-02T01:47:34.672Z","status":"online","status_checked_at":"2026-03-02T02:00:07.342Z","response_time":60,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"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":["aidapal","ollama","pseudo-code","reverse-engineering","vuln-dev"],"created_at":"2025-02-24T23:28:10.240Z","updated_at":"2026-03-02T10:03:50.551Z","avatar_url":"https://github.com/0xdea.png","language":"Rust","funding_links":["https://github.com/sponsors/3562"],"categories":["Applications","LLM Tools"],"sub_categories":["Security tools"],"readme":"# oneiromancer\n\n[![](https://img.shields.io/github/stars/0xdea/oneiromancer.svg?style=flat\u0026color=yellow)](https://github.com/0xdea/oneiromancer)\n[![](https://img.shields.io/crates/v/oneiromancer?style=flat\u0026color=green)](https://crates.io/crates/oneiromancer)\n[![](https://img.shields.io/crates/d/oneiromancer?style=flat\u0026color=red)](https://crates.io/crates/oneiromancer)\n[![](https://img.shields.io/badge/ollama-0.13.5-violet)](https://ollama.com/)\n[![](https://img.shields.io/badge/twitter-%400xdea-blue.svg)](https://twitter.com/0xdea)\n[![](https://img.shields.io/badge/mastodon-%40raptor-purple.svg)](https://infosec.exchange/@raptor)\n[![build](https://github.com/0xdea/oneiromancer/actions/workflows/build.yml/badge.svg)](https://github.com/0xdea/oneiromancer/actions/workflows/build.yml)\n\n\u003e \"A large fraction of the flaws in software development are due to programmers not fully understanding all the possible\n\u003e states their code may execute in.\" -- John Carmack\n\n\u003e \"Can it run Doom?\" -- \u003chttps://canitrundoom.org/\u003e\n\nOneiromancer is a reverse engineering assistant that uses a locally running LLM that has been fine-tuned for Hex-Rays\npseudocode to aid with code analysis. It can analyze a function or a smaller code snippet, returning a high-level\ndescription of what the code does, a recommended name for the function, and variable renaming suggestions, based on the\nresults of the analysis.\n\n![](https://raw.githubusercontent.com/0xdea/oneiromancer/master/.img/screen01.png)\n\n## Features\n\n* Cross-platform support for the fine-tuned LLM [aidapal](https://huggingface.co/AverageBusinessUser/aidapal) based on\n  `mistral-7b-instruct`.\n* Easy integration with the pseudocode extractor [haruspex](https://github.com/0xdea/haruspex) and popular IDEs.\n* Code description, recommended function name, and variable renaming suggestions are printed on the terminal.\n* Improved pseudocode of each analyzed function is saved in a separate file for easy inspection.\n* External crates can invoke [`analyze_code`] or [`analyze_file`] to analyze pseudocode and then process analysis\n  results.\n\n## Blog post\n\n* \u003chttps://hnsecurity.it/blog/aiding-reverse-engineering-with-rust-and-a-local-llm\u003e\n\n## See also\n\n* \u003chttps://www.atredis.com/blog/2024/6/3/how-to-train-your-large-language-model\u003e\n* \u003chttps://huggingface.co/AverageBusinessUser/aidapal\u003e\n* \u003chttps://github.com/atredispartners/aidapal\u003e\n* \u003chttps://plugins.hex-rays.com/atredispartners/aidapal\u003e\n\n## Installing\n\nThe easiest way to get the latest release is via [crates.io](https://crates.io/crates/oneiromancer):\n\n```sh\ncargo install oneiromancer\n```\n\nTo install as a library, run the following command in your project directory:\n\n```sh\ncargo add oneiromancer\n```\n\n## Compiling\n\nAlternatively, you can build from [source](https://github.com/0xdea/oneiromancer):\n\n```sh\ngit clone https://github.com/0xdea/oneiromancer\ncd oneiromancer\ncargo build --release\n```\n\n## Configuration\n\n1. Download and install [Ollama](https://ollama.com/).\n2. Download the fine-tuned weights and the Ollama modelfile from [Hugging Face](https://huggingface.co/):\n   ```sh\n   wget https://huggingface.co/AverageBusinessUser/aidapal/resolve/main/aidapal-8k.Q4_K_M.gguf\n   wget https://huggingface.co/AverageBusinessUser/aidapal/resolve/main/aidapal.modelfile\n   ```\n3. Configure Ollama by running the following commands within the directory in which you downloaded the files:\n   ```sh\n   ollama create aidapal -f aidapal.modelfile\n   ollama list\n   ```\n\n## Usage\n\n1. Run oneiromancer as follows:\n   ```sh\n   export OLLAMA_BASEURL=custom_baseurl # if not set, the default will be used\n   export OLLAMA_MODEL=custom_model # if not set, the default will be used\n   oneiromancer \u003ctarget_file\u003e.c\n   ```\n2. Find the improved pseudocode in `\u003ctarget_file\u003e.out.c`:\n   ```sh\n   vim \u003ctarget_file\u003e.out.c\n   code \u003ctarget_file\u003e.out.c\n   ```\n\n*Note: for best results, submit one function at a time to be analyzed by the LLM.*\n\n## Compatibility\n\nTested on:\n\n* Apple macOS Sequoia 15.2 with Ollama 0.13.5\n* Ubuntu Linux 24.04.2 LTS with Ollama 0.13.5\n* Microsoft Windows 11 23H2 with Ollama 0.13.5\n\n## Credits\n\n* Chris Bellows (@AverageBusinessUser) at Atredis Partners for his fine-tuned LLM `aidapal` \u003c3\n\n## Changelog\n\n* [CHANGELOG.md](CHANGELOG.md)\n\n## TODO\n\n* Improve output file handling with versioning and/or an output directory.\n* Implement other features of the IDAPython `aidapal` IDA Pro plugin (e.g., context).\n* Integrate with [haruspex](https://github.com/0xdea/haruspex) and [idalib](https://github.com/binarly-io/idalib).\n* Use custom types in the public API and implement a provider abstraction.\n* Implement a \"minority report\" protocol (i.e., make three queries and select the best responses).\n* Consider a refactor of variable renaming to prevent potential code corruption.\n* Investigate other use cases for the `aidapal` LLM and implement a modular architecture to plug in custom LLMs.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2F0xdea%2Foneiromancer","html_url":"https://awesome.ecosyste.ms/projects/github.com%2F0xdea%2Foneiromancer","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2F0xdea%2Foneiromancer/lists"}