Show HN: Git for LLMs – a context management interface https://ift.tt/ph0M2wd

Show HN: Git for LLMs – a context management interface Hi HN, we’re Jamie and Matti, co-founders of Twigg. During our master’s we continually found the same pain points cropping up when using LLMs. The linear nature of typical LLMs interfaces - like ChatGPT and Claude - made it really easy to get lost without any easy way to visualise or navigate your project. Worst of all, none of them are well suited for long term projects. We found ourselves spending days using the same chat, only for it to eventually break. Transferring context from one chat to another is also cumbersome. We decided to build something more intuitive to the ways humans think. We started with two simple ideas. Enabling chat branching for exploring tangents, and an interactive tree diagram to allow for easy visualisation and navigation of your project. Twigg has developed into an interface for context management - like “Git for LLMs”. We believe the input to a model - or the context - is fundamental to its performance. To extract the maximum potential of an LLM, we believe the users need complete control over exactly what context is provided to the model, which you can do using simple features like cut, copy and delete to manipulate your tree. Through Twigg, you can access a variety of LLMs from all the major providers, like ChatGPT, Gemini, Claude, and Grok. Aside from a standard tiered subscription model (free, plus, pro), we also offer a Bring Your Own Key (BYOK) service, where you can plug and play with your own API keys. Our target audience are technical users who use LLMs for large projects on a regular basis. If this sounds like you, please try out Twigg, you can sign up for free at https://twigg.ai/ . We would love to get your feedback! https://twigg.ai October 23, 2025 at 08:42PM

Show HN: Pg_textsearch – BM25 Ranking for Postgres https://ift.tt/Mx16juK

Show HN: Pg_textsearch – BM25 Ranking for Postgres I built pg_textsearch, a Postgres extension that brings proper BM25 ranking to full-text search. It's designed for AI/RAG workloads where search quality directly impacts LLM output. Postgres native ts_rank lacks corpus-aware signals (no IDF, no TF saturation, no length normalization). This causes mediocre documents to rank above excellent matches, which matters when your LLM depends on retrieval quality. Quick example: CREATE EXTENSION pg_textsearch; CREATE INDEX articles_idx ON articles USING bm25(content); SELECT title, content <@> to_bm25query('database performance', 'articles_idx') AS score FROM articles ORDER BY score LIMIT 10; Works seamlessly with pgvector or pgvectorscale for hybrid search. Fully transactional (no sync jobs). Preview release uses in-memory architecture (64MB default per index); disk-based segments coming soon. I love ParadeDB's pg_search but wanted something available on our managed Postgres. You can try pg_textsearch free on Tiger Cloud: https://ift.tt/vxnq5JW Blog: https://ift.tt/wbWUchk... Docs: https://ift.tt/x51eOyE... Feedback welcome, especially from folks building RAG systems or hybrid search applications. https://ift.tt/eBOsKJr October 23, 2025 at 10:55PM

Show HN: Middlerok – reduces front end-back end integration from weeks to hours https://ift.tt/tnuKGEQ

Show HN: Middlerok – reduces front end-back end integration from weeks to hours Generate production-ready OpenAPI specs, frontend & backend code and documentation with AI https://ift.tt/Wt3bxgQ October 22, 2025 at 11:05PM

Show HN: Incremental JSON parser for streaming LLM tool calls in Ruby https://ift.tt/SRuDqWH

Show HN: Incremental JSON parser for streaming LLM tool calls in Ruby Built this for streaming AI tool calls. LLMs stream function arguments as JSON character-by-character. Most parsers reparse from scratch each time - O(n²) behavior that causes UI lag. This maintains parsing state, processing only new characters. True O(n) performance that stays imperceptible throughout the entire response. Ruby gem, MIT licensed. Would love feedback. https://ift.tt/Hk4xgqy October 23, 2025 at 01:02AM

Show HN: Create interactive diagrams with pop-up content https://ift.tt/1quRdat

Show HN: Create interactive diagrams with pop-up content This is a recent addition to Vexlio which I think the HN crowd may find interesting or useful. TL;DR: easy creation of interactive diagrams, meaning diagrams that have mouse click/hover hooks that you can use to display pop-up content. The end result can be shared with a no-sign-in-required web link. My thought is that this is useful for system docs, onboarding or user guides, presentations, etc. Anything where there is a high-level view that should remain uncluttered + important metadata or details that still need to be available somewhere. You can try it out without signing up for anything, just launch the app here ( https://app.vexlio.com/ ), create a shape, select it with the main pointer tool and then click "Add popup" on the context toolbar. I'd be grateful for any and all feedback! https://ift.tt/QqSpVPt October 22, 2025 at 08:15PM

Show HN: MTOR – A free, local-first PWA to automate workout progression https://ift.tt/SyrHEmq

Show HN: MTOR – A free, local-first PWA to automate workout progression Hi HN, My motivation for this came from frustration with existing workout trackers. Most felt clunky, hid core features like performance graphs behind a paywall, or forced a native app download. A few people close to me who take their training seriously shared the same sentiment, so I decided to build my own. I'm working on mTOR, a free, science-based workout tracker I built to automate progressive overload. It's a local-first PWA that works completely offline, syncs encrypted between your devices using passwordless passkeys, and allows for plan sharing via a simple link. The core idea is to make progression easier to track and follow. After a workout, it analyzes your performance (weight, reps, and RIR), highlights new personal records (PRs), and generates specific targets for your next session. It also reviews your entire program to provide scientific analysis on weekly volume, frequency, and recovery for each muscle group. This gets displayed visually on an anatomy model to help you learn which muscles are involved, and you can track your gains over time with historical performance charts for each exercise. During a workout, you get a total session timer, an automatic rest timer, and can see your performance from the last session for a clear target to beat. It automatically advances to the next incomplete exercise, and when you need to swap an exercise, it provides context-aware alternatives targeting the same muscles. It's also deeply customizable: * The UI has a dark theme, supports multiple languages (English, Spanish, German), lets you adjust the UI scale, and toggle the visibility of detailed muscle names, exercise types, historical performance badges, and a full history card. * You can set global defaults for weight units (kg/lbs), rest times, and plan targets, or enable/disable metrics like Reps in Reserve (RIR) and estimated 1-Rep Max. The exercise library can be filtered by your available equipment, you can create your own custom exercises with global notes, and there's a built-in weight plate calculator. * The progression system lets you define default rep ranges and RIR targets, or create specific overrides for different lifts (e.g., a 3-5 rep range for strength, 10-15 for accessories). * Editing is flexible: you can drag-and-drop to reorder days, exercises, and sets, duplicate workout days, track unilateral exercises (left/right side), and enter data with a quick wheel picker. I'll be here all day to answer questions. I'm also thinking about making the project open-source down the line and would be curious to hear any thoughts on that. Thanks for checking it out! https://mtor.club/ October 22, 2025 at 12:04AM

Show HN: bbcli – A TUI and CLI to browse BBC News like a hacker https://ift.tt/49gD8v7

Show HN: bbcli – A TUI and CLI to browse BBC News like a hacker hey hn! I (re)built this TUI tool for browsing BBC News in the terminal, it uses an RSS feed for getting headlines and previews and you can read articles too. Try it out and let me know what you think! :) https://ift.tt/rlFWcHY October 19, 2025 at 04:28PM