Show HN: HN Wrapped 2025 - an LLM reviews your year on HN
9 by hubraumhugo | 3 comments on Hacker News.
I was looking for some fun project to play around with the latest Gemini models and ended up building this :) Enter your username and get: - Generated roasts and stats based on your HN activity 2025 - Your personalized HN front page from 2035 (inspired by a recent Show HN [0]) - An xkcd-style comic of your HN persona It uses the latest gemini-3-flash and gemini-3-pro-image (nano banana pro) models, which deliver pretty impressive and funny results. A few examples: - dang: https://ift.tt/UGT3bsZ - myself: https://ift.tt/v6nK0jC Give it a try and share yours:) [0] https://ift.tt/GltEwDA
Saturday, December 20, 2025
Friday, December 19, 2025
New top story on Hacker News: Show HN: Linggen – A local-first memory layer for your AI (Cursor, Zed, Claude)
Show HN: Linggen – A local-first memory layer for your AI (Cursor, Zed, Claude)
9 by linggen | 5 comments on Hacker News.
Hi HN, Working with multiple projects, I got tired of re-explaining our complex multi-node system to LLMs. Documentation helped, but plain text is hard to search without indexing and doesn't work across projects. I built Linggen to solve this. My Workflow: I use the Linggen VS Code extension to "init my day." It calls the Linggen MCP to load memory instantly. Linggen indexes all my docs like it’s remembering them—it is awesome. One click loads the full architectural context, removing the "cold start" problem. The Tech: Local-First: Rust + LanceDB. Code and embeddings stay on your machine. No accounts required. Team Memory: Index knowledge so teammates' LLMs get context automatically. Visual Map: See file dependencies and refactor "blast radius." MCP-Native: Supports Cursor, Zed, and Claude Desktop. Linggen saves me hours. I’d love to hear how you manage complex system context! Repo: https://ift.tt/bi7RZdC Website: https://linggen.dev
9 by linggen | 5 comments on Hacker News.
Hi HN, Working with multiple projects, I got tired of re-explaining our complex multi-node system to LLMs. Documentation helped, but plain text is hard to search without indexing and doesn't work across projects. I built Linggen to solve this. My Workflow: I use the Linggen VS Code extension to "init my day." It calls the Linggen MCP to load memory instantly. Linggen indexes all my docs like it’s remembering them—it is awesome. One click loads the full architectural context, removing the "cold start" problem. The Tech: Local-First: Rust + LanceDB. Code and embeddings stay on your machine. No accounts required. Team Memory: Index knowledge so teammates' LLMs get context automatically. Visual Map: See file dependencies and refactor "blast radius." MCP-Native: Supports Cursor, Zed, and Claude Desktop. Linggen saves me hours. I’d love to hear how you manage complex system context! Repo: https://ift.tt/bi7RZdC Website: https://linggen.dev
Thursday, December 18, 2025
New top story on Hacker News: Show HN: Paper2Any – Open tool to generate editable PPTs from research papers
Show HN: Paper2Any – Open tool to generate editable PPTs from research papers
5 by Mey0320 | 0 comments on Hacker News.
Hi HN, We are the OpenDCAI group from Peking University. We built Paper2Any, an open-source tool designed to automate the "Paper to Slides" workflow based on our DataFlow-Agent framework. The Problem: Writing papers is hard, but creating professional architecture diagrams and slides (PPTs) is often more tedious. Most AI tools just generate static images (PNGs) that are impossible to tweak for final publication. The Solution: Paper2Any takes a PDF, text, or sketch as input, understands the research logic, and generates fully editable PPTX (PowerPoint) files and SVGs. We prioritize flexibility and fidelity—allowing you to specify page ranges, switch visual styles, and preserve original assets. How it works: 1. Multimodal Reading: Extracts text and visual elements from the paper. You can now specify page ranges (e.g., Method section only) to focus the context and reduce token usage. 2. Content Understanding: Identifies core contributions and structural logic. 3. PPT Generation: Instead of generating one flat image, it generates independent elements (blocks, arrows, text) with selectable visual styles and organizes them into a slide layout. Links: - Demo: http://dcai-paper2any.cpolar.top/ - Code (DataFlow-Agent): https://ift.tt/H60ROgZ We'd love to hear your feedback on the generation quality and the agent workflow!
5 by Mey0320 | 0 comments on Hacker News.
Hi HN, We are the OpenDCAI group from Peking University. We built Paper2Any, an open-source tool designed to automate the "Paper to Slides" workflow based on our DataFlow-Agent framework. The Problem: Writing papers is hard, but creating professional architecture diagrams and slides (PPTs) is often more tedious. Most AI tools just generate static images (PNGs) that are impossible to tweak for final publication. The Solution: Paper2Any takes a PDF, text, or sketch as input, understands the research logic, and generates fully editable PPTX (PowerPoint) files and SVGs. We prioritize flexibility and fidelity—allowing you to specify page ranges, switch visual styles, and preserve original assets. How it works: 1. Multimodal Reading: Extracts text and visual elements from the paper. You can now specify page ranges (e.g., Method section only) to focus the context and reduce token usage. 2. Content Understanding: Identifies core contributions and structural logic. 3. PPT Generation: Instead of generating one flat image, it generates independent elements (blocks, arrows, text) with selectable visual styles and organizes them into a slide layout. Links: - Demo: http://dcai-paper2any.cpolar.top/ - Code (DataFlow-Agent): https://ift.tt/H60ROgZ We'd love to hear your feedback on the generation quality and the agent workflow!
Wednesday, December 17, 2025
Tuesday, December 16, 2025
New top story on Hacker News: Show HN: Zenflow – orchestrate coding agents without "you're right" loops
Show HN: Zenflow – orchestrate coding agents without "you're right" loops
11 by andrewsthoughts | 4 comments on Hacker News.
Hi HN, I’m Andrew, Founder of Zencoder. While building our IDE extensions and cloud agents, we ran into the same issue many of you likely face when using coding agents in complex repos: agents getting stuck in loops, apologizing, and wasting time. We tried to manage this with scripts, but juggling terminal windows and copy-paste prompting was painful. So we built Zenflow, a free desktop tool to orchestrate AI coding workflows. It handles the things we were missing in standard chat interfaces: Cross-Model Verification: You can have Codex review Claude’s code, or run them in parallel to see which model handles the specific context better. Parallel Execution: Run five different approaches on a backlog item simultaneously—mix "Human-in-the-Loop" for hard problems with "YOLO" runs for simple tasks. Dynamic Workflows: Configured via simple .md files. Agents can actually "rewire" the next steps of the workflow dynamically based on the problem at hand. Project list/kanban views across all workload What we learned building this To tune Zenflow, we ran 100+ experiments across public benchmarks (SWE-Bench-*, T-Bench) and private datasets. Two major takeaways that might interest this community: Benchmark Saturation: Models are becoming progressively overtrained on all versions of SWE-Bench (even Pro). We found public results are diverging significantly from performance on private datasets. If you are building workflows, you can't rely on public benches. The "Goldilocks" Workflow: In autonomous mode, heavy multi-step processes often multiply errors rather than fix them. Massive, complex prompt templates look good on paper but fail in practice. The most reliable setups landed in a narrow “Goldilocks” zone of just enough structure without over-orchestration. The app is free to use and supports Claude Code, Codex, Gemini, and Zencoder. We’ve been dogfooding this heavily, but I'd love to hear your thoughts on the default workflows and if they fit your mental model for agentic coding. Download: https://ift.tt/izQZ07A YT flyby: https://www.youtube.com/watch?v=67Ai-klT-B8
11 by andrewsthoughts | 4 comments on Hacker News.
Hi HN, I’m Andrew, Founder of Zencoder. While building our IDE extensions and cloud agents, we ran into the same issue many of you likely face when using coding agents in complex repos: agents getting stuck in loops, apologizing, and wasting time. We tried to manage this with scripts, but juggling terminal windows and copy-paste prompting was painful. So we built Zenflow, a free desktop tool to orchestrate AI coding workflows. It handles the things we were missing in standard chat interfaces: Cross-Model Verification: You can have Codex review Claude’s code, or run them in parallel to see which model handles the specific context better. Parallel Execution: Run five different approaches on a backlog item simultaneously—mix "Human-in-the-Loop" for hard problems with "YOLO" runs for simple tasks. Dynamic Workflows: Configured via simple .md files. Agents can actually "rewire" the next steps of the workflow dynamically based on the problem at hand. Project list/kanban views across all workload What we learned building this To tune Zenflow, we ran 100+ experiments across public benchmarks (SWE-Bench-*, T-Bench) and private datasets. Two major takeaways that might interest this community: Benchmark Saturation: Models are becoming progressively overtrained on all versions of SWE-Bench (even Pro). We found public results are diverging significantly from performance on private datasets. If you are building workflows, you can't rely on public benches. The "Goldilocks" Workflow: In autonomous mode, heavy multi-step processes often multiply errors rather than fix them. Massive, complex prompt templates look good on paper but fail in practice. The most reliable setups landed in a narrow “Goldilocks” zone of just enough structure without over-orchestration. The app is free to use and supports Claude Code, Codex, Gemini, and Zencoder. We’ve been dogfooding this heavily, but I'd love to hear your thoughts on the default workflows and if they fit your mental model for agentic coding. Download: https://ift.tt/izQZ07A YT flyby: https://www.youtube.com/watch?v=67Ai-klT-B8
Monday, December 15, 2025
New top story on Hacker News: Show HN: A pager
Show HN: A pager
38 by keepamovin | 22 comments on Hacker News.
Hello HN, I basically don't use notifications for anything. The noise is too much. Slack is too loud. Email is too slow. But sometimes you do need a note in your face. I found myself missing 1990s pagers. I wanted a digital equivalent - something that does one thing: beep until I ack it. So I built UDP-7777. Concept: - 0% Cloud: It listens on UDP Port 7777. No accounts, no central servers. You don't need Tailscale/ZeroTier/WG/etc, it's just easy for device sets. - CAPCODES: It maps your IP address (LAN or Tailscale) to a retro 10-digit "CAPCODE" that looks like a phone number (e.g., (213) 070-6433 for loopback). - Minimalism: Bare-bones interface. Just a box, a few buttons, and a big red blinker. The Tech: It's a single binary written in Go (using Fyne). It implements "burst fire" UDP (sending packets 3x) to ensure delivery without the handshake overhead of TCP. New in v2.2.7: - Frequency Tuning: Bind specifically to your Tailscale/ZeroTier interface. - Squelch: Optional shared-secret keys to ignore unauthorized packets. - Heartbeat: Visual/Audio alerts that persist until you physically click ACK. I built this for anyone looking to cut through the noise—DevOps teams handing off the "on-call IP", or deep-work focus where you only want interruptions from a high-trust circle. I'd love to hear your thoughts on the IP-to-Phone-Number mapping logic (it's purely visual, but I'm really into it). Site & Binaries (Signed for Mac/Win): https://udp7777.com
38 by keepamovin | 22 comments on Hacker News.
Hello HN, I basically don't use notifications for anything. The noise is too much. Slack is too loud. Email is too slow. But sometimes you do need a note in your face. I found myself missing 1990s pagers. I wanted a digital equivalent - something that does one thing: beep until I ack it. So I built UDP-7777. Concept: - 0% Cloud: It listens on UDP Port 7777. No accounts, no central servers. You don't need Tailscale/ZeroTier/WG/etc, it's just easy for device sets. - CAPCODES: It maps your IP address (LAN or Tailscale) to a retro 10-digit "CAPCODE" that looks like a phone number (e.g., (213) 070-6433 for loopback). - Minimalism: Bare-bones interface. Just a box, a few buttons, and a big red blinker. The Tech: It's a single binary written in Go (using Fyne). It implements "burst fire" UDP (sending packets 3x) to ensure delivery without the handshake overhead of TCP. New in v2.2.7: - Frequency Tuning: Bind specifically to your Tailscale/ZeroTier interface. - Squelch: Optional shared-secret keys to ignore unauthorized packets. - Heartbeat: Visual/Audio alerts that persist until you physically click ACK. I built this for anyone looking to cut through the noise—DevOps teams handing off the "on-call IP", or deep-work focus where you only want interruptions from a high-trust circle. I'd love to hear your thoughts on the IP-to-Phone-Number mapping logic (it's purely visual, but I'm really into it). Site & Binaries (Signed for Mac/Win): https://udp7777.com
Subscribe to:
Comments (Atom)