[{"_1":2,"_169":-5,"_170":-5},"loaderData",{"_3":4,"_13":14,"_21":22,"_146":147},"root",{"_5":-5,"_6":-7,"_7":8,"_9":-7,"_10":11,"_12":-7},"currentUser","primaryEmail","siteVerification","6LeIxAcTAAAAAJcZVRqyHh71UMIEGNQ_MXjiZKhI","toast","enableDev",false,"incidentStatus","routes/_layout",{"_15":-5,"_16":17,"_18":17,"_19":11,"_20":11},"username","isAskGordonEnabled",true,"isUsingNewTemplate","showMinimalLanding","showHoneypotTrap","routes/_layout.r.$namespace.$reponame",{"_23":24,"_25":-5,"_26":11,"_27":11,"_28":29,"_30":31,"_32":-5,"_33":11,"_34":35,"_88":-5,"_89":90,"_137":-5,"_138":11,"_139":17,"_140":11,"_141":-5,"_142":11,"_143":-5,"_144":145},"canonicalUrl","https://hub.docker.com/r/apurvsg/robin/tags","mcpServer","canSeeDockerfile","canSeeAutobuilds","namespace","apurvsg","reponame","robin","cloudBuildSource","isAutobuildsAvailable","repo",{"_36":37,"_43":44,"_46":47,"_48":49,"_50":11,"_51":52,"_53":54,"_55":56,"_39":31,"_28":29,"_58":59,"_60":-5,"_61":62,"_63":62,"_64":65,"_66":-5,"_67":68,"_69":70,"_71":11,"_72":29,"_73":74,"_79":11,"_80":81,"_85":29,"_86":87},"categories",[38],{"_39":40,"_41":42},"name","Security","slug","security","content_types",[45],"image","date_registered","2025-11-17T20:12:55.938051Z","description","Robin is an AI-powered tool for conducting dark web OSINT investigations","is_private","last_updated","2026-09-11T04:23:43.371146Z","last_modified","2026-09-11T04:57:11.112065Z","media_types",[57],"application/vnd.oci.image.index.v1+json","pull_count",56722,"repository_type","star_count",1,"status","status_description","active","source","collaborator_count",0,"full_description","\n

\n $\"Star$ $\"GitHub$ \n

Robin: AI-Powered Dark Web OSINT Tool

\n\n

Robin is an AI-powered tool for conducting dark web OSINT investigations. It leverages LLMs to refine queries, filter search results from dark web search engines, and provide an investigation summary.

\n Installation • Troubleshooting • Contributing • Acknowledgements

\n\n\n---\n\n## Features\n\n- ⚙️ **Modular Architecture** – Clean separation between search, scrape, and LLM workflows.\n- 🤖 **Multi-Model Support** – OpenAI, Claude, Gemini, Mistral, OpenRouter, Ollama, or any OpenAI-compatible API (LM Studio, llama.cpp, Groq, etc.).\n- 🔄 **Live Model List** – Models are discovered from each provider at startup, so new releases appear on their own and retired ones disappear. No hardcoded list to go stale.\n- 🎚️ **Tunable Depth** – Sidebar controls for how many results to filter, how many pages to scrape, and how much of each page the model reads, with the token cost shown before you run.\n- 🌐 **Web UI** – Streamlit-based interface for interactive investigations.\n- 💬 **Conversational Follow-ups** – Ask grounded follow-up questions about an investigation without re-running the search — answered from that investigation's own data.\n- 🔀 **One-Click Pivots** – Suggested follow-up queries surfaced from the findings; click one to launch a fresh investigation.\n- 🐳 **Docker-Ready** – Recommended Docker deployment for clean, isolated usage.\n- 🔍 **Honest Results** – When nothing relevant is found, Robin says so instead of summarizing whatever it happened to scrape.\n- 📝 **Custom Reporting** – Save investigation output to file for reporting or further analysis.\n- 🧩 **Extensible** – Easy to plug in new search engines, models, or output formats.\n\n---\n\n## ⚠️ Disclaimer\n> This tool is intended for educational and lawful investigative purposes only. Accessing or interacting with certain dark web content may be illegal depending on your jurisdiction. The author is not responsible for any misuse of this tool or the data gathered using it.\n>\n> Use responsibly and at your own risk. Ensure you comply with all relevant laws and institutional policies before conducting OSINT investigations.\n>\n> Additionally, Robin leverages third-party APIs (including LLMs). Be cautious when sending potentially sensitive queries, and review the terms of service for any API or model provider you use.\n\n## Installation\n> [!NOTE]\n> The tool needs Tor to do the searches. You can install Tor using `apt install tor` on Linux/Windows(WSL) or `brew install tor` on Mac. Once installed, confirm if Tor is running in the background.\n\n> [!TIP]\n> Provide your API key either in a `.env` file (copy [`.env.example`](.env.example)) or as environment variables. One key is enough: Robin lists models for whichever providers it finds. Supported keys are `OPENAI_API_KEY`, `ANTHROPIC_API_KEY`, `GOOGLE_API_KEY`, `MISTRAL_API_KEY` and `OPENROUTER_API_KEY`.\n>\n> For Ollama, nothing goes in your `.env`. Robin defaults to `http://host.docker.internal:11434`, which is what the recommended Docker install needs. Two things are still on you:\n>\n> 1. Run the container with `--add-host=host.docker.internal:host-gateway` (the README command already does).\n> 2. Make Ollama listen on all interfaces, since it binds to `127.0.0.1` by default and a container cannot reach that. If you start it yourself, `OLLAMA_HOST=0.0.0.0 ollama serve &`. If it runs under systemd, `sudo systemctl edit ollama.service`, add `[Service]` and `Environment=\"OLLAMA_HOST=0.0.0.0\"`, then `sudo systemctl daemon-reload && sudo systemctl restart ollama`.\n>\n> Running Robin directly with Python instead of Docker? Add `OLLAMA_BASE_URL=http://127.0.0.1:11434` to override the default. See [TROUBLESHOOTING.md](TROUBLESHOOTING.md) if it still doesn't appear.\n>\n> For any other OpenAI-compatible provider (LM Studio, llama.cpp, Groq, etc.), use the **🔌 Custom API Provider** expander in the sidebar — no `.env` changes required. Enter the base URL, an optional API key, and optionally a model name if the provider doesn't expose `/v1/models` for auto-discovery.\n\n### Docker [Recommended]\n\n- Pull the latest Robin docker image\n```bash\ndocker pull apurvsg/robin:latest\n```\n\n- Run the docker image as:\n```bash\ndocker run --rm \\\n -v \"$(pwd)/.env:/app/.env\" \\\n --add-host=host.docker.internal:host-gateway \\\n -p 8501:8501 \\\n apurvsg/robin:latest\n```\n\n> [!TIP]\n> To persist saved investigations across Docker restarts, mount a local directory:\n> ```bash\n> docker run --rm \\\n> -v \"$(pwd)/.env:/app/.env\" \\\n> -v \"$(pwd)/investigations:/app/investigations\" \\\n> --add-host=host.docker.internal:host-gateway \\\n> -p 8501:8501 \\\n> apurvsg/robin:latest\n> ```\n> Investigations are saved to the `investigations/` folder in your working directory and can be loaded from the **Past Investigations** panel in the sidebar.\n\n- Open your browser and navigate to `http://localhost:8501`\n\n### Using Python (Development Version)\n\n- With `Python 3.10+` and Tor installed, run the following:\n\n```bash\npip install -r requirements.txt\nstreamlit run ui.py\n```\n\n- Open your browser and navigate to `http://localhost:8501`\n\n---\n\n## Troubleshooting\n\nEmpty model dropdown, Ollama not showing up, Tor `resolve failed` errors, 401s,\nor \"no results found\"? See **[TROUBLESHOOTING.md](TROUBLESHOOTING.md)** before\nopening an issue.\n\n---\n\n## Contributing\n\nBugs go in [Issues](https://github.com/apurvsinghgautam/robin/issues). Questions\nand feature ideas go in\n[Discussions](https://github.com/apurvsinghgautam/robin/discussions). See\n**[CONTRIBUTING.md](CONTRIBUTING.md)** before opening a pull request.\n\n---\n\n## Acknowledgements\n\n- Idea inspiration from [Thomas Roccia](https://x.com/fr0gger_) and his demo of [Perplexity of the Dark Web](https://x.com/fr0gger_/status/1908051083068645558).\n- Tools inspiration from my [OSINT Tools for the Dark Web](https://github.com/apurvsinghgautam/dark-web-osint-tools) repository.\n- LLM Prompt inspiration from [OSINT-Assistant](https://github.com/AXRoux/OSINT-Assistant) repository.\n- Logo Design by my friend [Tanishq Rupaal](https://github.com/Tanq16/)\n","has_starred","hub_user","immutable_tags_settings",{"_75":11,"_76":77},"enabled","rules",[78],".*","is_automated","permissions",{"_82":17,"_83":11,"_84":11},"read","write","admin","user","storage_size",16937794460,"orgData","recentTags",[91],{"_92":45,"_93":94,"_95":96,"_97":98,"_99":100,"_101":102,"_51":125,"_126":94,"_127":29,"_128":57,"_39":129,"_130":131,"_132":133,"_134":125,"_135":65,"_136":17},"content_type","creator",38114863,"digest","sha256:850c70edd425ff1fbfa9eb1ed3c429cf798ccb1308cf00683cff27abfebcf22a","full_size",549778109,"id",1012953353,"images",[103,119],{"_104":105,"_95":106,"_107":108,"_109":110,"_111":112,"_113":114,"_115":108,"_116":-5,"_117":98,"_63":65,"_118":-5},"architecture","amd64","sha256:2df18a6b4448a67d7a058549bcf1e89c0216ea87cc40c89f5d67417a674421ab","features","","last_pulled","2026-09-24T20:14:55.975997533Z","last_pushed","2026-09-11T04:23:40.018511139Z","os","linux","os_features","os_version","size","variant",{"_104":120,"_95":121,"_107":108,"_109":122,"_111":123,"_113":114,"_115":108,"_116":-5,"_117":124,"_63":65,"_118":-5},"arm64","sha256:c5d19e2508ae2b252e5f695e8472c5d2d7165a622bf026dba844491f886a479e","2026-09-24T21:28:12.871572854Z","2026-09-11T04:23:41.376641954Z",528987163,"2026-09-11T04:23:42.646527Z","last_updater","last_updater_username","media_type","latest","repository",29181566,"tag_last_pulled","2026-09-24T21:42:22.395454593Z","tag_last_pushed","tag_status","v2","sbxKitMetadata","isPotentialSpam","isHubSbxKitsEnabled","showSbxLogoOverride","sbxTrademarkText","displaySecurityMetadata","tagAttestations","tagsHaveAttestations",[],"routes/_layout.r.$namespace.$reponame.tags",{"_34":148,"_156":157,"_144":167,"_168":11},{"_36":149,"_43":151,"_46":47,"_48":49,"_50":11,"_51":52,"_53":54,"_55":152,"_39":31,"_28":29,"_58":59,"_60":-5,"_61":62,"_63":62,"_64":65,"_66":-5,"_67":68,"_69":70,"_71":11,"_72":29,"_73":153,"_79":11,"_80":155,"_85":29,"_86":87},[150],{"_39":40,"_41":42},[45],[57],{"_75":11,"_76":154},[78],{"_82":17,"_83":11,"_84":11},"tags",{"_158":62,"_159":-5,"_160":-5,"_161":162},"count","next","previous","results",[163],{"_92":45,"_93":94,"_95":96,"_97":98,"_99":100,"_101":164,"_51":125,"_126":94,"_127":29,"_128":57,"_39":129,"_130":131,"_132":133,"_134":125,"_135":65,"_136":17},[165,166],{"_104":105,"_95":106,"_107":108,"_109":110,"_111":112,"_113":114,"_115":108,"_116":-5,"_117":98,"_63":65,"_118":-5},{"_104":120,"_95":121,"_107":108,"_109":122,"_111":123,"_113":114,"_115":108,"_116":-5,"_117":124,"_63":65,"_118":-5},[],"canDeleteTags","actionData","errors"]

Digest	OS/ARCH	Compressed size
2df18a6b4448	linux/amd64	524.31 MB
c5d19e2508ae	linux/arm64	504.48 MB

apurvsg/robin

Tags for apurvsg/robin