{"slug": "deadline-extractor", "title": "Deadline Extractor", "summary": "A developer built Deadline Extractor, an open-source tool that processes exported group chat files with a local Llama 3.2 3B model via Ollama to separate real submission requirements from casual chatter, anchor colloquial dates to exact timestamps, detect deadline extensions that overwrite earlier ones, and export the results as an .ics calendar file. The Python and Streamlit tool, which also offers a CLI, runs entirely offline so private student conversations never leave the user's machine, and the model can be swapped for Mistral or Gemma through a configuration flag.", "body_md": "*This is a submission for the [Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady](https://dev.to/challenges/hacktoberfest-week3-2026-10-19)*\n\nThe Problem: As students, our class group chats are flooded with hundreds of messages daily: jokes, memes, discussions, and random chatter. Somewhere in that noise, a professor or class rep drops: \"Submit DBMS assignment by Friday 5pm\", followed 6 hours later by \"Deadline extended to Sunday 8pm\". We miss deadlines simply because we don't have the energy to manually scroll back through 500 messages every evening.\n\nThe Sloth Solution: Instead of manually tracking tasks, Deadline Extractor does the heavy lifting while you chill. You feed it an exported group chat, and it uses an open-weight local model to:\n\nSeparate real submission requirements from casual banter.\n\nAnchor colloquial dates (\"Monday\", \"tomorrow by midnight\") to exact timestamps.\n\nDetect deadline updates/extensions and overwrite earlier ones.\n\nExport everything into a .ics calendar file ready for Google Calendar, Apple Calendar, or Outlook.\n\nZero Data Leaves Your Machine: Group chats contain deeply private conversations, student banters, and personal contact info. Sending this data to proprietary cloud APIs is a privacy violation. Running open weights via Ollama keeps 100% of the data on your laptop.\n\n100% Free & Offline: A student on a train or in a hostel with poor internet can still extract their syllabus and deadlines without paying for API subscriptions.\n\nOpen Weight Flexibility: Powered by Meta's open llama3.2:3b, swappable for Mistral or Gemma with a single configuration flag.\n\nTech Stack:\n\nAI Engine: Llama 3.2 3B via Ollama\n\nBackend: Python, dateparser, ics\n\nFrontend: Streamlit & CLI\n\nDemo Video Youtube Link:\n\nGit Hub Link:\n\nEvery student knows the pain. Your class WhatsApp group has 500+ unread messages, and somewhere in the avalanche of memes, random polls, and \"who has the notes?\" threads, the class rep posted an assignment deadline — **three days ago**. You only find out when your friend casually asks, \"Did you submit the compiler design assignment?\" and your stomach drops. That dreaded *\"Wait, THAT was due today?!\"* moment hits different at 11:47 PM.\n\nClass reps shouldn't have to be human reminder bots. Students shouldn't have to archaeologically dig through chat histories to find what's due. There has to be a better way.\n\n**Deadline Extractor** takes your exported chat file, runs it through a **local open-weight AI model**, and produces:", "url": "https://wpnews.pro/news/deadline-extractor", "canonical_source": "https://dev.to/rohitpd/deadline-extractor-23nd", "published_at": "2026-10-25 07:32:00+00:00", "updated_at": "2026-10-25 07:42:43.788925+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-tools", "ai-products", "natural-language-processing"], "entities": ["Deadline Extractor", "Ollama", "Meta", "Llama 3.2 3B", "Mistral", "Gemma", "Streamlit", "Hacktoberfest"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/deadline-extractor", "markdown": "https://wpnews.pro/news/deadline-extractor.md", "text": "https://wpnews.pro/news/deadline-extractor.txt", "jsonld": "https://wpnews.pro/news/deadline-extractor.jsonld"}}