Show HN: Evolving Agents Framework https://ift.tt/RnC5Z1w

Show HN: Evolving Agents Framework Hey HN, I've been working on an open-source framework for creating AI agents that evolve, communicate, and collaborate to solve complex tasks. The Evolving Agents Framework allows agents to: Reuse, evolve, or create new agents dynamically based on semantic similarity Communicate and delegate tasks to other specialized agents Continuously improve by learning from past executions Define workflows in YAML, making it easy to orchestrate agent interactions Search for relevant tools and agents using OpenAI embeddings Support multiple AI frameworks (BeeAI, etc.) Current Status & Roadmap This is still a draft and a proof of concept (POC). Right now, I’m focused on validating it in real-world scenarios to refine and improve it. Next week, I'm adding a new feature to make it useful for distributed multi-agent systems. This will allow agents to work across different environments, improving scalability and coordination. Why? Most agent-based AI frameworks today require manual orchestration. This project takes a different approach by allowing agents to decide and adapt based on the task at hand. Instead of always creating new agents, it determines if existing ones can be reused or evolved. Example Use Case: Let’s say you need an invoice analysis agent. Instead of manually configuring one, our framework: Checks if a similar agent exists (e.g., a document analyzer) Decides whether to reuse, evolve, or create a new agent Runs the best agent and returns the extracted information Here's a simple example in Python: import asyncio from evolving_agents.smart_library.smart_library import SmartLibrary from evolving_agents.core.llm_service import LLMService from evolving_agents.core.system_agent import SystemAgent async def main(): library = SmartLibrary("agent_library.json") llm = LLMService(provider="openai", model="gpt-4o") system = SystemAgent(library, llm) result = await system.decide_and_act( request="I need an agent that can analyze invoices and extract the total amount", domain="document_processing", record_type="AGENT" ) print(f"Decision: {result['action']}") # 'reuse', 'evolve', or 'create' print(f"Agent: {result['record']['name']}") if __name__ == "__main__": asyncio.run(main()) Next Steps Validating in real-world use cases and improving agent evolution strategies Adding distributed multi-agent support for better scalability Full integration with BeeAI Agent Communication Protocol (ACP) Better visualization tools for debugging Would love feedback from the HN community! What features would you like to see? Repo: https://ift.tt/T0C5E1Q https://ift.tt/T0C5E1Q March 9, 2025 at 10:21PM

Show HN: Math expressions and graph traversals of the Chinese language https://ift.tt/4QkEmHf

Show HN: Math expressions and graph traversals of the Chinese language I've been working on a free Chinese language learning tool for awhile now. The main insight is that Chinese characters are used together to form words, and that this allows for a way of quickly getting information about related words and characters. By learning words and characters in a chain in this way, I've found it easier not to get lost in the long list of characters. In addition, I've found it helpful to break down characters into their components to find pronunciation clues, which can sometimes be hidden in components of components. The math feature uses a similar tree traversal mechanism to allow expressions like 酒-氵+各 = 酪 or 亻+寸+广+仌+⺆ = 腐. As it's 2025, it also has some AI features. Notably: * allowlisted users can get Chinese or English text explanations that span more than just a word, but that integrate with the other features, like flashcard creation and in-browser text-to-speech. * files and images (using the browser's `capture` mechanism to operate cameras) can also be processed similarly. * example sentences were generated and cached using AI The site is a PWA built with vanilla JS (because I like pain), with Cytoscape and D3 for various rendering tasks. The backend was built with Firebase, with Genkit + Gemini 2.0 providing the AI integration. Feel free to check it out: https://hanzigraph.com https://ift.tt/qQRf0Kc March 9, 2025 at 12:30AM

Show HN: Simple Certificate Decoder Tool https://ift.tt/wXPp6nz

Show HN: Simple Certificate Decoder Tool Sometimes I need to quickly check certificates, especially key details like SANs, expiration dates, issuer info, etc. I know there are dozens (if not hundreds) of certificate decoders out there already, but I built my own—mostly for fun, but also because I prefer tools that are clean, simple, and straightforward to use. Would appreciate your feedback! https://ift.tt/e8vpGho March 8, 2025 at 11:09PM

Show HN: Open-Source DocumentAI with Ollama https://ift.tt/QVyxmT0

Show HN: Open-Source DocumentAI with Ollama https://rlama.dev/ March 8, 2025 at 07:42AM

Show HN: Ming-wm: A 100% keyboard-operated desktop environment in Rust https://ift.tt/nKBse0A

Show HN: Ming-wm: A 100% keyboard-operated desktop environment in Rust https://ift.tt/PwaNXUk March 8, 2025 at 12:24AM

Show HN: I Built a Telegraph Simulator https://ift.tt/WBRqdeL

Show HN: I Built a Telegraph Simulator https://ift.tt/DZIwsMT March 5, 2025 at 03:30AM

Show HN: Ask AI Paul Graham (Open Sourced) https://ift.tt/csQo2pI

Show HN: Ask AI Paul Graham (Open Sourced) https://ift.tt/VCordRU March 8, 2025 at 12:10AM

Show HN: Open-source, native audio turn detection model https://ift.tt/Rclh9tS

Show HN: Open-source, native audio turn detection model https://ift.tt/5I1dz47 March 6, 2025 at 11:50PM

Show HN: DataBridge: Rule-Based Metadata Extraction, PII Redaction, and More https://ift.tt/LfJwoKi

Show HN: DataBridge: Rule-Based Metadata Extraction, PII Redaction, and More https://ift.tt/J2ijNop March 6, 2025 at 08:12PM

Show HN: I made an app to like or dislike famous quotes https://ift.tt/9w5Ukct

Show HN: I made an app to like or dislike famous quotes https://ift.tt/ORzD1kt March 4, 2025 at 03:25AM

Show HN: Bayleaf – Building a low-profile wireless split keyboard https://ift.tt/xAXGj4u

Show HN: Bayleaf – Building a low-profile wireless split keyboard Hey HN, I built a wireless, split, ultra-low profile keyboard from scratch called Bayleaf. As a beginner I learned all things electronics, PCB-building, designing for manufacturing, and many other hardware-related skills to put this together. This case study dives into the build process and of course the final result, hope you enjoy! https://ift.tt/abm7zeq March 4, 2025 at 08:30PM

Show HN: We created a music MMO that can scale 10x of Roblox https://ift.tt/4vruF0I

Show HN: We created a music MMO that can scale 10x of Roblox https://ift.tt/zdQA3oG March 5, 2025 at 12:35AM

Show HN: Time travel debugging AI for more reliable vibe coding https://ift.tt/pFtTuwo

Show HN: Time travel debugging AI for more reliable vibe coding Hi HN, I'm the CEO at https://replay.io . We've been building a time travel debugger for web apps for several years now (previous HN post: https://ift.tt/IOSDfjP ) and are combining our tech with AI to automate the debugging process. AIs are really good at writing code but really bad at debugging -- it's amazing to use Claude to prompt an app into existence, and pretty frustrating when that app doesn't work right and Claude is all thumbs fixing the problem. The basic reason for this is a lack of context. People can use devtools to understand what's going on in the app, but AIs struggle here. With a recording of the app its behavior becomes a giant database for querying using RAG. We've been giving Claude tools to explore and understand what happens in a Replay recording, from basic stuff like seeing console messages to more advanced analysis of React, control dependencies, and dataflow. For now this is behind a chat API ( https://ift.tt/mhbc7CV ). We recently launched Nut ( https://nut.new ) as an open source project which uses this tech for building apps through prompting (vibe coding), similar to e.g. https://bolt.new and https://v0.dev . We want Nut to fix bugs effectively (cracking nuts, so to speak) and are working to make it a reliable tool for building complete production grade apps. It's been pretty neat to see Nut fixing bugs that totally stump the AI otherwise. Each of the problems below has a short video but you can also load the associated project and try it yourself. - Exception thrown from a catch block unmounts the entire app: https://ift.tt/1dycGAE - A settings button doesn't work because its modal component isn't always created: https://ift.tt/tzpombc - An icon is really tiny due to sizing constraints imposed by other elements: https://ift.tt/BSVG39g - Loading doesn't finish due to a problem initializing responsive UI state: https://ift.tt/mQdhjcs - Infinite rendering loop caused by a missing useCallback: https://ift.tt/xA9P16D Nut is completely free. You get some free uses or can add an API key, and we're also offering unlimited free access for folks who can give us feedback we'll use to improve Nut. Email me at hi@replay.io if you're interested. For now Nut is best suited for building frontends but we'll be rolling out more full stack features in the next few weeks. I'd love to know what you think! https://nut.new March 5, 2025 at 12:23AM

Show HN: FlakeUI https://ift.tt/43XkAHc

Show HN: FlakeUI https://ift.tt/UVsKTfo March 3, 2025 at 10:59AM

Show HN: Generating Random Art in Haskell https://ift.tt/3VszUda

Show HN: Generating Random Art in Haskell https://ift.tt/Rj8QSU4 March 3, 2025 at 11:53PM

Show HN: A Transformer model that preserves logical equivalence https://ift.tt/bwEX1x5

Show HN: A Transformer model that preserves logical equivalence https://ift.tt/cOGMVAR March 3, 2025 at 02:11AM

Show HN: Mmar – open-source, zero-dependancy, cross-platform HTTP tunneling https://ift.tt/b17Vf5W

Show HN: Mmar – open-source, zero-dependancy, cross-platform HTTP tunneling Hey HN! For the past couple of months, I've been working on and off on a cool project I'm excited to share. mmar (pronounced "ma-mar") is an open-source, zero dependency, cross platform and self-hostable HTTP tunnel built in Go. It allows you to easily expose your localhost to the world on a public URL. You can easily create an HTTP tunnel right away for free on a randomly generated subdomain on "*.mmar.dev" if you don't feel like self-hosting. This isn't something new, in fact there's quite a few of alternative HTTP tunneling tools out there. mmar is my attempt to optimize for a super easy developer experience and simplified implementation. None the less, I had a blast building it and I think developers could find it pretty useful. Additionally, I documented the whole process of building mmar through devlogs. You can read about the thought process and implementation details here ( https://ift.tt/pjOmFrs ). If I would suggest one devlog to read, I highly recommend devlog 5 ( https://ift.tt/CKxbHqX ). I describe how I built a (very) basic DNS server just to run simulation tests for mmar (a bit of an overkill, but a fantastic learning experience). I dive deep into the DNS protocol and explain why I needed to implement it. Finally, I would love to hear your thoughts and feedback. If you try mmar out, let me know! https://ift.tt/XKvp956 March 3, 2025 at 01:28AM

Show HN: Fast Transition from Firefox to Librewolf https://ift.tt/G3EVSZd

Show HN: Fast Transition from Firefox to Librewolf After looking at various browser alternatives to Firefox (my daily driver for years), I decided to try LibreWolf and the transition was trivial on a Debian based system (by HN standards). My extensions even ran without logging in (YMMV). First install LibreWolf: sudo apt update && sudo apt install extrepo -y sudo extrepo enable librewolf sudo apt update && sudo apt install librewolf -y Second: After closing Firefox, copy Firefox profile (in ~/.mozilla/firefox/) to Librevox profile (in ~/.librewolf/). Note: I copied the profile into the default profile (as seen in about:profiles) not default-default. I then launched the profile and all my tabs were restored, bookmarks, logins, etc. I will update if something seems broken. March 2, 2025 at 11:44PM

Show HN: Schedual https://ift.tt/cnlD8eb

Show HN: Schedual No nonsense tasks. https://schedual.app/ March 2, 2025 at 01:10AM

Show HN: LLM Token Visualizer – How big is 128k token input https://ift.tt/JtLbhYu

Show HN: LLM Token Visualizer – How big is 128k token input https://ift.tt/M62q9Hs March 2, 2025 at 01:14AM