
Explore the hottest developer projects on Show HN for 2025-01-29. Dive into innovative tech, AI applications, and exciting new inventions!
Summary of Today's Content
Today's Product Highlights
- Product Name: Open-Source Alternative to OpenAI Platform
- Highlight: A Mozilla-supported UI for training, tuning and testing local LLMs, making LLM development more accessible and transparent
Quick Summary
- Most Hot Category: AI/ML Development Tools
- Top Keywords: LLM, Open Source, AI Development, Voice AI
- Most Popular Product: Open-Source OpenAI Alternative (78 points)
Technology Trends
- LLM Development & Testing
- Voice AI & Speech Processing
- Code Analysis & Manipulation
- Privacy-focused Data Sharing
- AI-powered Education
Project Distribution
- AI/ML Tools: 35%
- Developer Tools: 25%
- Web Applications: 20%
- Privacy/Security: 15%
- Others: 5%
Trend Insights
- Strong focus on making AI development more accessible through open-source tools
- Growing emphasis on privacy-preserving AI applications
- Increasing demand for specialized AI tools in education and language learning
- Rise of voice-based AI applications and tools
- Trend toward self-hosted and local AI solutions over cloud-based services
The analysis shows a clear trend toward democratizing AI development while maintaining privacy and control. The high engagement with open-source AI tools suggests a strong developer interest in alternatives to proprietary AI platforms.
Today's Top 10 Trending Products
Top 1. An open-source platform offering a powerful alternative to OpenAI, designed for running local models efficiently and effectively. (Likes: 78, Comments: 19)
Top 2. Mcp-Agent: Harness the power of Model Context Protocol to create efficient and intelligent agents. (Likes: 66, Comments: 22)
Top 3. Vogent: Advanced Building Blocks for Voice AI, enhancing development efficiency and user interaction. (Likes: 22, Comments: 4)
Top 4. Introducing Gemini 2: Experience unparalleled flexibility with unrestricted code execution, enhancing your development capabilities and unlocking new possibilities for innovation. (Likes: 22, Comments: 0)
Top 5. Discover the ultimate price aggregator designed to help you uncover the best deals on PC parts from eBay, ensuring you never miss out on great savings for your next build! (Likes: 13, Comments: 8)
Top 6. Codegen is an open-source Python library designed for advanced code manipulation, enabling developers to enhance their coding efficiency and streamline workflows with powerful tools and features. (Likes: 13, Comments: 2)
Top 7. A powerful landing page builder that enables you to capture leads in minutes, streamlining your marketing efforts with ease and efficiency. (Likes: 5, Comments: 8)
Top 8. Revolutionize your healthcare experience with Emmo, an advanced AI tool designed to provide smarter health insights and comprehensive blood test analysis, empowering you to take control of your health like never before. (Likes: 8, Comments: 4)
Top 9. Distr is an open-source distribution platform designed for seamless on-prem deployments, offering flexibility and control for organizations looking to manage their own infrastructure efficiently. (Likes: 10, Comments: 0)
Top 10. Revolutionary open-source compliance solution offering a compelling alternative to Vanta and Drata, designed to streamline your compliance processes and enhance transparency. Perfect for organizations seeking cost-effective, customizable compliance management. (Likes: 3, Comments: 6)
1. Show HN: Open-Source Alternative to OpenAI Platform, for Local Models
URL: https://github.com/transformerlab/transformerlab-app
Author: aliasaria
Description: Hi everyone, we’re a small team, supported by Mozilla, who are working on re-imagining a UI for training, tuning and testing local LLMs. Everything is open source. If you’ve been training your own LLMs or have always wanted to, we’d love for you to play with the tool and give feedback on what the future development experience for LLM engineering could look like.
Popularity: 78 points | 19 comments
2. Show HN: Mcp-Agent – Build effective agents with Model Context Protocol
URL: https://github.com/lastmile-ai/mcp-agent
Author: saqadri
Description: Hey HN, I spent my xmas break building an agent framework called mcp-agent [1](https://github.com/lastmile-ai/mcp-agent) for Model Context Protocol [2]. It makes it easy to build AI apps with MCP servers, and implements every pattern from the popular Building Effective Agents blog [3] as well as OpenAI’s Swarm [4]. I’m sharing it early to get community feedback on where to take it from here, and to ask for contributions.
For those who aren’t familiar with MCP, I think of it as a standardized interface to let AI communicate with software via tool calls, resources and prompts.
mcp-agent provides a higher level interface to build apps with MCP. It handles the connection management of MCP servers so you don’t have to. It also implements the Building Effective Agents patterns:
- Augmented LLM (an LLM with access to one or more MCP servers)
- Router, Orchestrator-Worker, Evaluator-Optimizer, and more
- Swarm
The key design principles are composability and reusability – every pattern is an AugmentedLLM itself, so you can chain them into more complex workflows.
Some background: I worked on LSP [5] and language servers at Microsoft, and saw firsthand how standards and protocols can revolutionize developer workflows. Before LSP every IDE had its own esoteric ways of providing language services. LSP changed all that, and arguably made every language server better, since they can focus on improving a single implementation for all clients.
I think AI development is in a similar pre-LSP space right now. There are tons of frameworks [6], every model provider has its own way of handling messages, tool calls, streaming, etc. I really think we need a protocol to standardize these patterns.
Pretty soon every service is going to expose an MCP interface, and mcp-agent is about letting developers orchestrate these services into applications (i.e. build “MCP apps”). This can cover any use of an AI model that needs to interact with the world around it:
- RAG pipelines and Q&A chatbots
- Process automation via AI workflows/async tasks
- Multi-agent orchestration, with human in the loop
The repo contains examples [7] to build RAG agents, streamlit apps and more. There’s a lot left to build, like streaming support, server auth and tighter integration with MCP clients.
But I wanted to share early in the hopes that you can guide me:
- If you find this useful, please let me know. If it’s useful to you, I will dedicate all my time to improving it.
- I really welcome contributions. If you want to collaborate, please reach out on github to help take this forward.
I want to help standardize AI development, so developers a few years from now can look back with horror at the pre-MCP days.
[1] - https://github.com/lastmile-ai/mcp-agent
[2] - https://modelcontextprotocol.io/introduction
[3] - https://www.anthropic.com/research/building-effective-agents
[4] - https://github.com/openai/swarm
[5] - https://microsoft.github.io/language-server-protocol/
[6] - https://xkcd.com/927/ (I understand the irony)
[7] - https://github.com/lastmile-ai/mcp-agent/tree/main/examples
Popularity: 66 points | 22 comments
3. Show HN: Vogent – Better Building Blocks for Voice AI
Author: jag729
Description: Hi HN! Excited to share some stuff we’ve been building.
We spent the last year building voice agents to automate individual call tasks for companies with large call centers. The STT-LLM-TTS-VAD cycle is mostly solved at this point, but the last-mile problem for making these agents performant was frustrating. We ended up building a lot of band-aids, and we decided to put them together into their own end-to-end product.
Vogent is a platform for building and serving Voice AI agents, with a focus on providing higher-level building blocks that make it easy to get a voice agent working quickly. You can check out the docs at https://docs.vogent.ai
It supports the typical design process of a voice agent (choosing/prompting a model, selecting a voice, and hosting on a phone number or accessing via API), but it has additional pieces that make voice agents performant quickly, like (among other things):
- A drag-and-drop agent builder
Under the hood, this involves feeding the model only context relevant to the goals of the current node (e.g., asking a particular question and probing conversationally for the answer), while giving it the ability to call a function with the outcome once the goal is achieved to transition to the appropriate next node. This makes it easy to build voice agents that need the structure of a multi-step talk track with the flexibility of accomplishing each task conversationally.
- Voices that are trained to spell
Off-the-shelf voices (e.g. Eleven, Cartesia) sound much more artificial when they spell. It might sound like an edge case, but this killed almost every engagement we had. We ended up recruiting Upworkers with different accents, having them spell a few thousand phrases, and training our own voices by modifying open-source architectures. Choose “Carlos” for a spelling-optimized voice right now; we’re adding a lot more soon.
- An IVR detection model
This detector uses the audio stream to predict whether a line came from an IVR or a human, and switches between different LLMs based on the result (so you can have independent IVR navigation and conversational models).
- Model versioning and counterfactuals
Vogent enables model versioning and testing against past dials within the product.
Any feedback would be appreciated. Please also feel free to join our Discord: https://discord.gg/JmThYcyG
Popularity: 22 points | 4 comments
4. Show HN: Gemini 2 with unrestricted code execution
URL: #
Author: krasserm
Description: I recently experimented using Gemini 2 Flash and Gemini 2 Flash Thinking with unrestricted code execution in a local sandbox and open sourced the results: https://github.com/gradion-ai/freeact. Here's an example that uses Gemini 2 Flash Thinking as agent that acts via code, executed in a sandbox based on IPython and Docker: https://gist.github.com/krasserm/dcdae47f85ee9922e3284953d07...
Gemini's code execution environment is restricted to selected Python libraries like NumPy or SymPy and prevents the model from installing new packages, besides other limitations. While this may be useful for agentic applications in restricted environments, it may prevent agents from adapting to new environments, especially agents that write their actions in code (see CodeAct paper https://arxiv.org/abs/2402.01030).
Has anyone else experimented with Gemini 2 as a CodeAct agent? I'd be particularly interested in hearing about approaches to unrestricted code execution.
Popularity: 22 points | 0 comments
5. Show HN: I made a price aggregator to find the best PC parts deals across eBay
URL: https://www.pcprice.watch/
Author: tzoSkatzo
Description: Started PC flipping as a hobby (buying used parts, building PCs, and selling them for a small profit). Found that focusing on used parts on eBay gives the best margins - like finding a GPU 20% below market, pairing it with other deals, and selling the complete build locally.
I discovered that eBay marketplaces (.com, .de, .co.uk etc.) often have different prices for the same items! Or just completely different items.
So I built an eBay price scanner for PC components. It scans listings across different Ebay markets, calculates median prices, and flags anything selling below market (including shipping costs to your location). It basically finds the best deal that is specific to your location.
It currently tracks GPUs, CPUs, RAM and motherboards across 6 eBay markets, updating every 8 hours.
Been using it myself for and it actually works!
Let me know, what you think. Would love to hear your feedback on making it more useful.
Popularity: 13 points | 8 comments
6. Show HN: Codegen – OSS Python Library for Advanced Code Manipulation
URL: https://docs.codegen.com/introduction/overview
Author: jayhack
Description: Hey HN! We've just open-sourced Codegen (https://github.com/codegen-sh/codegen-sdk), a Python library for manipulating Python + JS/React codebases.
Codegen was engineered backwards from real-world, large-scale codebase analysis + refactors we performed on multi-million-line enterprise codebases. It provides a scriptable interface to a powerful, multi-lingual language server built on Tree-sitter.
We realized that many code transformation tasks that impact large teams - refactors, enforcing patterns, analyzing control flow - are fundamentally programmatic operations. Yet existing tools like LibCST and Jscodeshift often require you to think in terms of ASTs and parser internals rather than the high-level changes you want to make.
Therefore, we built Codegen to match how developers actually think about code changes:
# Move a symbol to a new file
Handles imports, references, dependencies
function.move_to_file("new_file.py")
Rename across the codebase
class_def.rename("NewName") # Updates all usages, preserves formatting
Analyze call patterns
for usage in function.usages:
print(f"Used in {usage.file.name}")
Codegen handles the edge cases automatically - updating imports, preserving dependencies, maintaining references, and resolving naming conflicts. You focus on intent, we handle the details.Under the hood, Codegen performs static analysis to build a rich graph representation of your code. This enables:
- Versatile and comprehensive operations
- Built-in visualization capabilities
- Blazing fast execution of large-scale refactors
We've seen a wide variety of advanced code manipulation programs emerge, including:
- Mining codebases for LLM pre-training data
- Analyzing security vulnerabilities
- Large-scale API migrations
- Enforcing code patterns
We're excited to share this with the community and look forward to your feedback. Give it a spin and let us know what you think!
uv tool install codegen
codegen notebook --demo
Docs: https://docs.codegen.com
GitHub: https://github.com/codegen-sh/codegen-sdk
Community: https://community.codegen.comLet us know if you have any questions or interesting use cases you'd like to explore.
Popularity: 13 points | 2 comments
7. Show HN: I built a landing page builder so you can capture leads in minutes
URL: https://www.validado.app/create
Author: trevzerocap
Description:
Popularity: 5 points | 8 comments
8. Show HN: Emmo - AI for Smarter Health Insights and Blood Test Analysis
URL: https://emmo.ai
Author: stellamettifogo
Description:
Popularity: 8 points | 4 comments
9. Show HN: Distr – open-source distribution platform for on-prem deployments
URL: https://github.com/glasskube/distr
Author: louis_w_gk
Description: Distr is designed to help software engineers distribute and manage their applications or agents in customer-controlled or shared-responsibility environments. You only need a Docker Compose file or Helm chart—everything else for on-prem is handled by the platform.
We’re are an open source dev tool company. Over the past couple of months, we’ve spoken with dozens of software companies to understand their challenges with on-prem deployments. We analyzed the internal tools they’ve built and the best practices from existing solutions, combining them into a prebuilt, Open Source solution that works out of the box and integrates seamlessly.
Distr consists of two key components:
1. Hub - Provides a centralized view of all deployments and controls connected agents. - Comes with a simple GUI but also supports API and SDK access for seamless integration. - Fully Open- Surce and self-hostable, or you can use our fully managed platform.
2. Lightweight Agents - Pre-built agents for Helm (Kubernetes) and Docker Compose (VM) that run alongside your application. - Handle lifecycle tasks like guided installation, updates, and rollbacks. - Provide basic metrics (health status, application version) and logs
If you already have a customer portal or self-service interface for on-prem deployments, you can seamlessly integrate all features into your existing portal or application using our API or SDK. Alternatively, you can use our pre-built, white-labeled customer portal.
Here’s what an integration into your existing customer portal could look like:
import {DistrService} from "@glasskube/distr-sdk";
const customerHasAutoUpdatesEnabled = false; // replace with your own logic
const deploymentTargetId = 'da1d7130-bfa9-49a1-b567-c49728837df7';
const service = new DistrService({
apiKey: 'distr-8c24167aeb5fd4bb48b6d2140927df0f'
});
const result = await service.isOutdated(deploymentTargetId);
if(result.deploymentTarget.deployment?.latestStatus?.type !== 'ok') {
// let the user decide whether to allow updates from an instable state, e.g. with:
if(!confirm('The deployment is not in a stable state. Do you want to update anyway?')) {
return;
}
}
if(result.outdated) {
if(customerHasAutoUpdatesEnabled) {
await service.updateDeployment({deploymentTargetId});
// notify customer about the update
} else {
const newerVersionsAvailable = result.newerVersions;
// notify customer about the newer versions, e.g. via email
}
}
With the SDK/API, you can:
- Display real-time deployed version and deployment status directly within the application, notifying customers when their deployed version is outdated.
- Allow customers to trigger updates from within your app using a simple API call
If you’re distributing software and want to streamline updates or enhance monitoring, we’d love your feedback and are here to answer any questions.
Getting started is easy—just bring your Docker Compose file or Helm chart, and we’ll guide you through the rest.
Check out the fully managed version (https://app.distr.sh/register) and explore our documentation (https://distr.sh/docs/) to learn more.
Popularity: 10 points | 0 comments
10. Show HN: Open-Source Compliance (Vanta and Drata Alternative)
URL: https://trycomp.ai
Author: lewisbuildsai
Description: Hey HN,
We're about to launch the first ever open source compliance platform as an alternative to companies like Vanta, Drata & Delve.
Ask us anything, we'll be answering questions over the next few hours!
Popularity: 3 points | 6 comments
11. Show HN: How I built a SaaS thanks to my wife
URL: https://pdfbolt.com/
Author: Ametrin
Description: I’m Michał, and I’d like to share with you the journey I went through with my wife and how, thanks to her, we built our first SaaS, PDFBolt (https://pdfbolt.com). I’ve been a developer for over 10 years. In 2020, I decided to build a side project to learn all aspects of app development—deployment, authentication, payments, frontend, landing pages, etc. While looking for project ideas, I came across the Indie Hackers community, where I found a simple HTML to PDF API project. The creator mentioned a lot of interest in it and that it was generating revenue. I thought I’d build something similar myself and learn a lot in the process. But it wasn’t easy at all. After working from 9 to 5, it’s hard to spend another few hours in front of the computer in the evening. What about other responsibilities? Groceries, cooking, cleaning, hobbies, spending time with my wife? Still, I tried, very slowly. I had breaks lasting several months, and at one point, due to mental health issues, I practically stopped working on the project altogether.
My wife worked as a physiotherapist but, due to difficulties in her job, decided to switch to IT with my help, starting as a manual tester. She did it very quickly (maybe six months) and immediately found a job. In mid-2024, she started asking about my old project and insisted that we finish it. Thanks to her enthusiasm, we managed to do it very quickly. I focused on the backend, and she, in addition to testing, handled the entire frontend and landing page. Around the same time, we also adopted a dog from a shelter, which added a lot of positive energy to our lives and helped us stay motivated. In early January 2025, we officially launched the project. It’s been a long journey, and we don’t have any customers yet—we don’t even know if we will, as we have no idea about marketing :) But we’ve learned a lot and are already happy with the journey itself.
As for the technical aspects, the app uses:
Backend: Kotlin, Spring Boot, Postgres, Redis
Frontend: React, Next.js, Docusaurus
Auth: Firebase
Hosting: Render (the app is Dockerized)
Cloudflare R2 for file storage
PDFs are generated using Chromium via Playwright.
If you have any questions about the tech stack or anything else, feel free to ask! I’ll be happy to answer. Any feedback or criticism will be greatly appreciated. Thank you! :)
Popularity: 9 points | 0 comments
12. Show HN: Creating flowing particle animations out of images (JS and WebGL)
URL: https://particular-drift.netlify.app/
Author: getToTheChopin
Description: Hi! I'm Alan, and I built a website that turns images into flowing particle animations.
This javascript / WebGL tool creates particle animations out of any image in real-time within the browser, with particles that dynamically respond to edge detection and flow fields.
It uses Sobel edge detection, a Perlin noise flow field, and webGL / GLSL for better performance.
The tool is completely free and open source (MIT license).
Github repo: https://github.com/collidingScopes/particular-drift
Let me know of any feedback or suggestions for improvement.
Popularity: 7 points | 1 comments
13. Show HN: SmartInbox – using DeepSeek R1 to reduce amount of Junk in Inbox
URL: https://loshadki.app/blog/2025-01-29-protect-inbox-with-deepseek/
Author: outcoldman
Description:
Popularity: 3 points | 5 comments
14. Show HN: TailwindResume – Modern Resume Builder for Tech Professionals
URL: https://tailwindresume.co
Author: vikingmute
Description: There are already many resume tools in the market. If you search for resume tools, you’ll find many similar ones. I’ve researched and used their features, but they don’t fully meet my needs. I believe that resumes for internet professionals should start to differ from resumes in other industries. They should reflect technical characteristics and rigor in both content and format.
So I made TailwindResume: A resume builder for tech professionals. All templates are crafted with Tailwind CSS, enhanced with DeepSeek LLM for content generation.
Link: https://tailwindresume.co Docs: https://docs.tailwindresume.co
Features:
- Clean, responsive templates built with Tailwind CSS
- AI resume generation using DeepSeek LLM
- Real tech resume examples (Frontend/Backend/DevOps)
- Export as PDF or share as web page
- Free resume writing guidelines
Looking forward to your feedback!
Popularity: 2 points | 4 comments
15. Show HN: My jQuery puzzle game won my school coding competition
URL: https://connect3.org
Author: pompomsheep
Description:
Popularity: 5 points | 0 comments
16. Show HN: Open Source AI Playground for Prompt Engineers
URL: https://playground.getsupernova.ai
Author: theanirudh
Description: Hi HN,
We're a small team building AI tutors out of India, and as you might guess, this means we spend a ton of time writing, testing, and refining prompts for LLMs. When we started out, we were using the OpenAI playground but things became tedious when we wanted to compare responses from different models. We tried a bunch of other playgrounds but found them lacking in some features so we built our own.
Quick Links:
Github: https://github.com/supernova-app/ai-playground
Hosted demo: http://playground.getsupernova.ai
Demo video: https://www.youtube.com/watch?v=I01_t75FT-c
TLDR:
Main features are:
- Monaco editor for writing prompts.
- Variable support in prompts {{}}.
- Syntax highlighting for tags like XML.
- Generate multiple completions with same model.
- Chat with multiple models simultaneously.
- Save prompt and conversations as JSON.
- Easy to self host.
Key Features:
1. Monaco Editor for Writing Prompts
When we were working on long, detailed prompts, writing them in plain text felt clunky and error-prone. Small issues—like missing a tag or having weird formatting—could break things.
So, we integrated the Monaco editor (used in VS Code). It gives us:
- Line numbers (so we don't get lost in long prompts).
- White space detection to catch formatting issues early.
- Syntax highlighting for tags like XML.
- Code folding to collapse parts of a prompt we're not actively working on.
These might sound like small things, but they've been a huge help when we're dealing with large, complex prompts that need constant tweaking.
2. Variable Support for Dynamic Prompts
You can define placeholders in your prompt using double curly braces ({{ }}) and fill them in via a friendly UI.
3. Testing for Consistency Across Completions
One of the hardest parts of building AI tutors has been ensuring reliable outputs. Even when a prompt seems fine, it can fail unexpectedly—or worse, it works sometimes but not always.
To address this, we made it easy to generate multiple completions from the same model at once. This lets us quickly see:
- If the prompt is consistently producing good results.
- Where the AI might misinterpret our intent.
For example, we'd often run 5–6 completions to see if the AI consistently understood our instructions, rather than getting lucky once or twice.
4. Comparing Models Side by Side
The main reason we built the playground in the first place. You can set up API keys for multiple providers and see how different models handle the same task. This helped us:
- Optimize prompts for specific models.
- Choose the best model for a particular use case.
5. Saving Conversations as Test Cases
Another pain point was testing how a prompt or conversation would evolve over time. Sometimes, we'd go back and forth with the AI to simulate real user interactions, but we had no way to save that conversation for future reference.
Now, with the playground, we can save these conversations as test cases. Here's how it works:
- We create a conversation (or simulate a long interaction).
- At any point, we can save it as a JSON file.
- The JSON includes the full conversation, the system prompt, and any variables we used.
We then use this JSON file and use it in our code for running test cases or run evals.
6. Simple Self-Hosting
Finally, we wanted to make sure the playground was easy for others to set up. The only dependencies are:
- A Postgres database.
- API keys for the AI providers you want to use.
It supports Google login, so you can setup OAuth and can restrict access to only your domain.
The app is open source and we are running a hosted version of it here: http://playground.getsupernova.ai.
You can check out the repo here: https://github.com/supernova-app/ai-playground. It's easy to self-host, and we're actively working on new features.
If you give it a try, let us know what you think! Feedback, feature ideas, and contributions are all welcome.
Popularity: 5 points | 0 comments
17. Show HN: Insert Coin: An iOS / Android / web app to locate arcade locations
URL: https://www.insert-coin.app
Author: Elitius
Description: Hello everyone!
Six months ago, I took over the the Pinmyballs app, which is mainly known in the French-speaking world for locating public places with pinball machines. Initially, I wanted to shut it down and transfer the data to Pinballmap, but I felt like doing something different. I love arcade games as much as pinball, and there was no app to track arcade locations. So I decided to continue developing Pinmyballs by adding arcade games, as well as darts, billiards, and foosball.
The app was rewritten from the ground up, using Ionic framework (will be rewritten in React Native by the end of the year), and Symfony as back-end. And for obvious reasons, I also renamed it to Insert Coin.
Everyone can contribute and add locations and their game to the app. As the app launched recently, it misses a lot of locations, so don't hesitate to contribute and share the app around you if you want to!
- The app is available in six languages (English, Dutch, French, German, Italian, Spanish) and is completely free (no ads, no subscriptions)
- You can easily add locations you know about, games and comment about their state / condition
- You can find places around you for a particular game
- The games database may not be complete, so if you notice any games missing, feel free to let me know, and I’ll add them!
- You can save your favorite locations and receive notifications when games are added or removed from them!
- And more features to come!
The app is available on:
- Web: https://www.insert-coin.app
- iOS: https://apps.apple.com/app/insert-coin/id6664072981
- Android: https://play.google.com/store/apps/details?id=com.insertcoin...
Currently, there are 2,700 locations and 12,000 games listed.
Popularity: 3 points | 2 comments
18. Show HN: Voz Translate – Clone your voice and use it in other languages
URL: https://www.voztranslate.com/
Author: nevermindllc
Description:
Popularity: 3 points | 2 comments
19. Show HN: Yet another LLM agent framework but minimal and just TypeScript
URL: https://axar-ai.gitbook.io/axar
Author: aksyam
Description: Most LLM agent frameworks feel like they were designed by a committee - either trying to solve every possible use case with convoluted abstractions or making sure they look great in demos so they can raise millions.
I wanted something lightweight, code-first, and TypeScript-native, so I built a new one. It’s a minimal, strongly-typed agent framework that lets you structure LLM-powered apps without unnecessary complexity.
Key ideas:
Minimal – No unnecessary complexity, just the essentials Code-first – Feels like normal TypeScript, not a magic black box Type-first – Structured inputs/outputs using Zod/@annotations Explicit control – You define how agents behave, no hidden surprises Model-agnostic – OpenAI, Anthropic, DeepSeek, etc.
Links: GitHub: https://github.com/axar-ai/axar Docs: https://axar-ai.gitbook.io/axar
Would love to hear thoughts, especially if you think this approach is flawed.
Popularity: 4 points | 0 comments
20. Show HN: Coherence – Generate synthetic data for LLM testing 10x faster
URL: https://www.withcoherence.com/
Author: zoomzoom
Description: We've built a data generation studio that helps engineering teams create robust test datasets for their LLM applications in a fraction of the time it usually takes. While working with hundreds of engineering teams on DevOps automation, we discovered a critical gap: everyone wants to build AI products, but acquiring, labelling, and organizing test data for tasks is a massive challenge.
The current approaches to creating "golden datasets" for LLM testing are either infrastructure-heavy (observability-based) or time-consuming (manual creation). Many teams end up relying on intuition-based development, which leaves crucial questions unanswered about model selection, edge cases, and performance optimization.
Our solution generates comprehensive, realistic test datasets tailored to your specific use cases. You provide context (existing examples, domain information, or system prompts), and it creates robust test data that helps you:
- Balance distribution across your test suite including edge cases
- Evaluate prompt effectiveness across various scenarios
- Compare and optimize model selection
- Identify and handle edge cases systematically
- Assess performance across diverse use cases
- Support rapid R&D experimentation with different data shapes
We're launching this as the first data studio focused on giving AI engineers both speed and precision in their development workflow. If you're building AI products, we'd love your feedback on our approach to making LLM testing more reliable and efficient.
Check out what we’re building at https://www.withcoherence.com/
Popularity: 4 points | 0 comments
21. Show HN: We built this free tool for IT teams to customize employee offboarding
URL: https://offboarding.stitchflow.io/
Author: lurkervizzle
Description: OffboardIT is dead simple:
- Start with our pre-built templates for any department or role (based on 100s of IT teams' best practices)
- Customize it for your departing employee's specific needs
- Download your checklist instantly
That's it. No signup, no complexity - just a practical tool to make your offboarding process smoother.
Popularity: 4 points | 0 comments
22. Show HN: MVIII – Fastest Private Search Engine
URL: https://mviiii.searchall.site/search/?q=apple
Author: vednig
Description: Hey HN, I'm thrilled to announce MVIII, a new private search initiative to redesign the web for human generated content and authenticity.
Don't get me wrong I'm a huge fan of AI and the recents developments, that have made it look more natural. But overall the need for original and authentic connection has increased over the last few years,especially after covid-19, AI models are good at generating summaries and explaining a concept but fail to connect with readers. And the presence of bad actors utilizing AI to generate spam content over the internet has impacted the quality of searches. Which I believe is only going to increase, see the reports available here https://en.wikipedia.org/wiki/Dead_Internet_theory
Due to which the internet as a source for information and it's basic mission seem to be sidelined https://www.google.com/search?q=why+was+arpanet+created I've designed MVIII for searches to be more content focused and accurate to the terms you're searching for than Google, they're independent of classic page rank(in terms of backlink, domains among others etc.), which means, whether you have more backlinks or not, you don't have to compete for ranking with established brands or big tech companies, all you have to do is focus on your content and it's relationship to the query;
Currently the website index database is only 72k website paths which for reference is a lot smaller than any other search engine
some samples searches I've tested on:
https://mviiii.searchall.site/search/?q=hacker%20news
https://mviiii.searchall.site/search/?q=github%20awesome%20l...
https://mviiii.searchall.site/search/?q=keywords
Thank you for reading till the end, I'd like to hear your feedback with the service.Feature requests or new ideas are also appreciated.
The stack(if anyone's interested):
- VanillaJS (Frontend)
- MongoDB (Backend)
- FastAPI (Python/Backend)
- Firebase and Sevalla for Hosting
Also API is simple and available for free for anyone to use at https://hopp.sh/r/hJ89W515UFb8
Popularity: 1 points | 2 comments
23. Show HN: HackerNewsPro – Just Another Open-Source Modern UI for Hacker News
URL: https://hackernewspro.netlify.app/
Author: JoyboyisAlive
Description:
Popularity: 1 points | 2 comments
24. Show HN: TUI Bluetooth Connector for Mac
URL: https://github.com/Zaloog/blueutil-tui
Author: Zaloog
Description: Hi, since sometimes my AirPods didn't autoconnect to my Macbook and I didn't want my hands to leave the keyboard. I looked for alternative solutions to quickly connect devices.
Found [blueutil] for MAC, but was not happy with writing long commands, so I build a pretty minimal inline TUI application on a beautiful saturday to:
- display paired devices
- pair/unpair devices
- connect/disconnect devices
- search devices
Ive used [textual], a very nice framework to create TUIs with python.
You can find the gh-repo here: https://github.com/Zaloog/blueutil-tui
Direct use with uv via:
uvx --from blueutil-tui btui
[blueutil]: https://github.com/toy/blueutil
[textual]: https://textual.textualize.io
Popularity: 3 points | 0 comments
25. Show HN: AI-Generated App Store
URL: https://aigeneratedapp.store
Author: DotSauce
Description:
Popularity: 2 points | 1 comments
26. Show HN: I built an OSS abstraction over Stripe to embed any pricing model
URL: https://github.com/johnyeocx/autumn
Author: netswift
Description: Hey HN,
We just finished the YC batch and saw how long founders spent implementing pricing.
A few years ago SaaS pricing was just a monthly subscription. But AI companies today have many pricing options they want to experiment with: eg credit systems, usage based systems, top ups etc.
Building this in-house, with upgrades, downgrades, pro-ration, free trials, just sucks.
Similar to how Clerk 'solved' Auth for people that don't want to waste time building non-core features, I think we can do something similar for pricing.
I built an abstraction over Stripe to create any price model (subscriptions, usage-based, credits, trials etc), then embed it in a couple lines of code.
1. use /attach when a customer purchases a plan. A Stripe checkout URL is returned if needed.
- use /entitled to check if a customer has access to a plan or specific features.
This means no more dealing with webhooks, syncing subscription states etc. It's all open source and I'd love to hear your feedback!
Popularity: 3 points | 0 comments
27. Show HN: State Sandbox – An AI-powered political simulation game
Author: sshh12
Description: Hi all, I built a political simulation game that uses AI reasoning models to let you run a country through arbitrary executive actions. Think of it as an "executive order simulator" inspired by games like Civilization and NationStates, but where you can take any action you want - even copying real executive orders into the game.
The game generates a unique country for you with detailed characteristics (culture, economy, crime rates, etc). Each turn, you face natural events like protests, sanctions, or disasters, and can respond with any policy decisions via free-form text. The AI then simulates complex ripple effects - for example, a policy promoting domestic oil might affect your CO2 emissions, international trade relations, and even traffic fatality rates.
Technical details:
- Built with Next.js + FastAPI
- Uses OpenAI's reasoning models (o1 and o1-mini) to handle simulation
- Structured as a multi-agent system where o1 orchestrates key changes and o1-mini handles detailed updates
- Everything including the country flags is AI generated
The source code is available at: https://github.com/sshh12/state-sandbox
I wrote up my learnings about working with reasoning models and the technical challenges in building this at: https://blog.sshh.io/p/socioeconomic-modeling-with-reasoning
Popularity: 2 points | 1 comments
28. Show HN: Self-hosted server to find and fix risks in your CI/CD pipelines
URL: https://r2devops.io
Author: thomasboni
Description: We are building a self-hostable server that analyzes all your GitLab CI/CD pipelines to find security and compliance issues. Installation doc: https://docs.r2devops.io/docs/self-managed
Popularity: 3 points | 0 comments
29. Show HN: Pgchat – One command to chat with any Postgres database
URL: https://github.com/inferablehq/pgchat
Author: johnjcsmith
Description: Hey HN,
Sharing a project we have been working on which provides an LLM-powered chat experience for querying Postgres databases (local or remote).
pgchat takes a Postgres connection string and spawns a terminal UI for the chat:
npx pgchat postgresql://xxxx
It is built on top of our other project Inferable [1] which handles the LLM requests (open source / self hostable).
Database queries are issued from the pgchat process to the connection string which allows for use with local Postgres instances.
Keen to hear your thoughts!
[1] https://github.com/inferablehq/inferable
Popularity: 3 points | 0 comments
30. Show HN: Instantly listen to highlighted text on macOS
URL: https://github.com/soheil/tts
Author: soheil
Description:
Popularity: 1 points | 2 comments
31. Show HN: Inline Annotation for Rare Terms
URL: https://chromewebstore.google.com/detail/innline-annotation/fpflneflpoifekjpaphnkhglfklemogf
Author: mad_eye
Description:
Popularity: 1 points | 1 comments
32. Show HN: Mandarin Communication Board
URL: https://memalign.github.io/m/mandarin/index.html
Author: memalign
Description: Hi HN! Happy Lunar New Year!
My son recently started showing interest in learning Mandarin thanks to some singing books sent by a friend of ours.
I made this tool to help us expand our vocabulary and enable us to communicate about every day stuff.
My favorite part as I dabble in Mandarin is that there is no verb conjugation! Grammar tends to be fairly simple, too, which means that you can start saying intelligible sentences quickly by picking up common words.
The toughest part so far is hearing and producing words with the right tones. To my untrained American ears, I often can't tell the difference between words that differ only in their tone. It's been helpful to see the words written in pinyin and spoken aloud using this communication board.
I shared some technical details here:
https://memalign.github.io/p/mandarin.html
Popularity: 1 points | 1 comments
33. Show HN: AI Personal Financial Advisor – TestFlight Beta Available
URL: https://testflight.apple.com/join/T8fKTfmG
Author: solosquad
Description: I’m a solo developer on a mission to create an AI-powered personal financial advisor that’s accessible to everyone and provides real value. This is the MVP version, and I’d love to get your feedback!
Test the App: The app is available on TestFlight, and anyone can try it out now. Feedback Matters: Your insights will help me refine and improve the app. As a thank you, testers will receive lifetime access plus future rewards. Contact Me: If you have any feedback or questions, feel free to reach out at aymanov913@gmail.com.
Looking forward to your thoughts—every bit of feedback is incredibly helpful!
Popularity: 2 points | 0 comments
34. Show HN: Breadcrumbs – A Genuine Indie App to Help You Nurture Your Relationship
URL: https://breadcrumbs.today/
Author: CorbenDallas
Description: Hey everyone! Longtime reader here, but this is my first time posting — because, honestly, I’m confused. I always believed that if you build something great, the right customers will find you. But now that I’m actually trying to sell something for the first time, I’m realizing that might not be true.
I poured a lot into this project—it’s personal, and I genuinely believe it’s better than some of the top apps in this space (yes, competitors are making serious money). And yet… no one is even downloading it.
So, is the indie dev era over? Do you need a massive marketing budget just to get a foot in the door? Or did I just spend all this time building something nobody actually wants?
Would genuinely love to hear your thoughts!
Popularity: 1 points | 1 comments
35. Show HN: A Free Online Deepseek Janus Pro Website
URL: https://www.janusproai.net/
Author: gavinguang
Description: I modified the Janus Pro API using the source code and created this website, which is available for everyone to use for free.
Popularity: 2 points | 0 comments
36. Show HN: vet – Adding Support for Open Source Package Malware Scanning
URL: https://github.com/safedep/vet
Author: abhisek
Description: vet now supports scanning OSS package code for malicious behaviour.
Popularity: 2 points | 0 comments
37. Show HN: Europa – A self-hosted, encrypted file sharing service
URL: https://github.com/Migairu/europa
Author: jgiraldo29
Description: Hi HN,
I'm excited to introduce Europa (https://europa.migairu.com), a file sharing service focused on privacy and security. This is my first entrepreneurial project as I wait to begin college, so it's my first time launching something beyond the scope of a personal project.
Europa helps protect sensitive files by encrypting them in your browser before upload. The encryption keys come from your passphrase and stay on your device - we never see or store them. This means your files remain private since only people with the passphrase can decrypt them.
The service is simple to use: Upload a file, choose when it expires (up to 7 days), and share the download link with the passphrase. There's no need to create an account. Europa can handle files up to 2GB by splitting them into encrypted pieces during upload and putting them back together when downloaded.
Since Europa is open source under the GPL v3 license, you can run it on your own systems. The code and setup instructions are available at https://github.com/Migairu/europa. The service uses C# ASP.NET Core for the backend, Azure Blob Storage for files, and Web Crypto APIs for encryption.
I designed the interface to be straightforward, with helpful visuals showing how the encryption keeps files secure. My goal is to make strong encryption accessible while keeping the service easy to use.
I would appreciate hearing your thoughts on Europa. What features would you find most helpful? How could the self-hosting experience be improved? As a first-time entrepreneur, I also welcome advice from others who have launched similar ventures - your experience and insights would be invaluable.
You can learn more at europa.migairu.com or check out the code on GitHub. I look forward to your feedback and suggestions for making Europa better serve users' needs.
Popularity: 2 points | 0 comments
38. Show HN: So, I have written mini-progress bar feature for AOSP
URL: https://imgur.com/a/knVzKCb
Author: 0xf104a
Description:
Popularity: 1 points | 1 comments
39. Show HN: Navigating the Challenges of Quarantine Life
URL: https://github.com/karantina-2025-izle
Author: ithilda
Description:
Popularity: 2 points | 0 comments
40. Show HN: Build a Visual Novel with AI
Author: masterspy7
Description: Hey HN, I built a simple visual novel creator using a combination of tools such as Flux, LLM APIs and three.js. You can describe your game concept ("I am a knight sitting in a bar with a mysterious witch who only speaks in riddles") and mangobox will generate the characters, plot, environment, etc.
Current solutions to build VNs such as Ren'Py involve using a python library and distributing an executable. It requires a decent amount of technical knowledge which makes building VNs difficult unless you are a programmer. While my MVP doesn't cover even a small fraction of what Ren'Py does, my hope is to slowly achieve feature parity.
After an early access launch, my average session time across all users is ~1 hour. Hope you enjoy!
Popularity: 2 points | 0 comments
41. Show HN: Curatee, a minimalistic social bookmarking app
Author: hetdv
Description:
Popularity: 2 points | 0 comments
42. Show HN: I created an AI app that creates endless language learning scenarios
URL: https://www.lingualearn.ai
Author: tradesight
Description: I created LinguaLearn.ai to solve the repetitiveness of traditional language learning methods. It generates dynamic conversation practices across 30+ languages (including less common pairs like Korean→Spanish), with customizable scenarios and difficulty levels (A1-C2) delivered in WAV format accompanied by a transcript. The courses are similar to those produced by the Foreign Services Institute in the mid-20th century, which are very effective.
Tech stack highlights:
- Natural conversation generation in any scenario
- Cross-language learning support (learn any language from any language)
- Infinite number of scenarios (you can be really specific and i.e. try "restoring antique barometers from the Victorian era" or for a laugh you can try "falling out of plane and encountering amazon women").
- High-quality audio generation
- Difficulty-aware content generation (CEFR levels A1-C2)
- Full transcript generation
Currently in beta, offering 5 free lessons/month.
Here is an English -> Latin American Spanish HackerNews themed example:
https://ia600108.us.archive.org/3/items/tech-news_202501/tec...
Popularity: 2 points | 0 comments
43. Show HN: Tidyparse – Real-time context-free syntax repair
URL: https://tidyparse.github.io/
Author: bmc7505
Description:
Popularity: 2 points | 0 comments
44. Show HN: A Tool to Automatically Convert Shopify Products into Facebook Posts
Author: emaclean03
Description: When my wife started her Shopify store, I saw how much time and effort went into running a small business—managing products, customers, and orders left her with little time for social media. But we both knew how important it was to stay active on Facebook to reach more customers.
That’s why I built PulsePosty!
PulsePosty connects directly to your Shopify store and automates your Facebook posts, making it effortless to share your products. Whether you’re launching a new item or scheduling posts in advance, PulsePosty takes the hassle out of social media so you can focus on growing your business.
Here’s what PulsePosty offers: Seamless integration with your Shopify store and Facebook business page Automated product posts—no more manual uploads AI-powered descriptions that tweak your product details for Facebook audiences Scheduling tools to plan posts ahead and save time
Try it for free! All users get 5 free posts per month—perfect for many small businesses. Need more? For just $6.99/month, you get unlimited posts plus 500 AI-enhanced product descriptions for Facebook.
We’re currently in beta and looking for real user feedback. As a thank-you, early adopters get 75% off for life!
- Check us out at https://PulsePosty.com
Let PulsePosty handle your social media while you focus on what you do best—growing your business!
Popularity: 2 points | 0 comments
45. Show HN: Colider – a new programming language powered by tcc
URL: https://codeberg.org/samedev/colider
Author: samedev
Description: I've been working on colider for 9 months almost done programming it. This is the 2nd post about colider the first one got one person, now i'm making another one. Try it out. Compilation not done yet.
Popularity: 2 points | 0 comments
46. Show HN: HackerTyping – Hack the planet using a fun browser hacking emulator
URL: https://www.hackertyping.com/
Author: mjmj
Description: If you hack to the EOF then you'll be greatly rewarded. Hope you guys enjoy my side project and I'm happy to take feature requests.
Popularity: 2 points | 0 comments
47. Show HN: I made a tool to help test responsive designs on my laptop
URL: https://github.com/danielaweston/paneful
Author: itsdanweston
Description: I do all my work from a laptop with no external monitors, and testing responsive designs is a massive pain. Every change meant either resizing my browser window over and over, or clicking through different devices in the dev tools.
Modern websites need to work on everything from phones to massive desktop screens. Trying to catch all those layout bugs by checking one size at a time is tedious and you'll probably miss something. Browser dev tools are great, but flipping between different device sizes is cumbersome, and it's can be hard to spot when something breaks.
So I built Paneful to scratch my own itch. Now I can see my site on a phone, tablet, and desktop all at once. No more tedious resizing or device-switching - just instant feedback when something looks off. Plus, being able to arrange the viewports however I want means I can set up the perfect testing layout for whatever I'm building.
It made my life easier, I hope it does the same for you.
Popularity: 1 points | 0 comments
48. Show HN: Comfy-table, a Rust library for building beautiful terminal tables
URL: https://github.com/Nukesor/comfy-table
Author: tison
Description: I've used it for generating the table format output of our database. And it's impressive that the Rust community has unicode-rs which handles all the dirty works.
Popularity: 1 points | 0 comments
49. Show HN: Struggling with gift ideas? This AI finds the best one for you
Author: nicola_alessi
Description:
Popularity: 1 points | 0 comments
50. Show HN: Chorus – a Chrome extension to compare LLM responses
URL: https://chromewebstore.google.com/detail/chorus-compare-llms/opedkjbjehljdkjahbingfncglipdeif
Author: rishicomplex
Description: I’ve found myself frequently copy-pasting queries between different chatbots, so I wrote a little Chrome extension that automates this. You can type "ch <space>" in the address bar followed by your prompt, and it opens Claude, ChatGPT, DeepSeek, Gemini in separate tabs.
Popularity: 1 points | 0 comments
51. Show HN: Dbfunctions.js – SQL Functions in JavaScript
URL: https://www.ddginc-usa.com/dbFunctions.htm
Author: ddgflorida
Description: I've always liked SQL date and string functions so I made a library for Javascript with most of your favorite databases' Date and String functions. There is also a Playground to try each function and see the documentation.
Popularity: 1 points | 0 comments
52. Show HN: All-in-One Social Media Profile Preview Tool
URL: https://www.previewmyprofile.com/
Author: fer_momento
Description: Over the years, through my experience in the internet and tech space, I’ve seen how personal branding has evolved.
What was once mainly a focus for companies is now a crucial element for individuals, whether you're aiming for your dream job, building an audience, or growing a business.
That’s why I created PreviewMyProfile.com.
Preview your profile, bio, cover photo, and feed for Instagram, LinkedIn, YouTube, TikTok, X, and beyond, all in one place.
No more jumping between multiple sites, checking desktop and mobile versions separately, or worrying about consistency.
Would love to hear your thoughts!
Popularity: 1 points | 0 comments
53. Show HN: Kubernetes History Inspector from Google
URL: https://github.com/GoogleCloudPlatform/khi
Author: gabe_monroy
Description:
Popularity: 1 points | 0 comments
54. Show HN: I've build an app to create Vision Datasets and fine-tune VLMs
URL: https://www.picsellia.com/community
Author: thibautlucas
Description: Try it and let me know what you think, pro tips, you can try dark mode by running :localStorage.setItem(“picsellia-theme”, “dark”) and refreshing the page in your js console
Popularity: 1 points | 0 comments
55. Show HN: I built a tool to help SEOs stop copy-pasting SERP data
URL: https://seobrief.co
Author: ivanramos
Description: Hi HN! I'm a 6+ years SEO who got tired of spending hours analyzing every keyword's SERP data. So I built SEOBrief to do it in 25 seconds.
It automates what SEOs do manually:
- Analyzing the top 10 ranking pages
- Extracting all SEO elements (titles, meta, headings)
- Understanding content structure patterns
- Creating outlines based on what's actually ranking
I focused on making it simple and accessible:
- 25-second analysis (vs 30min manual work)
- CSV exports for your workflows
- No hidden API costs (I handle that)
- Pay per use, no subscriptions
Would love feedback from anyone who's dealt with the pain of manual SERP analysis.
Popularity: 1 points | 0 comments
56. Show HN: Pocket Log – macOS app to transcribe many short audio notes [video]
URL: https://www.youtube.com/watch?v=AThJa7SW-ro
Author: emadda
Description: This is a macOS app that transcribes audio notes from any directory or from the Voice Memos app.
See the video for more details, Thanks!
Popularity: 1 points | 0 comments
57. Show HN: Bidcliq – Cheapest Self Serve Prebid Wrapper for In-House Ads Setup
URL: https://bidcliq.com/
Author: ysharad
Description: Self-serve ad monetization platform built for publishers who want full control and transparency over their ad operations. With Bidcliq, publishers can set up and manage their ad stack in under 10 minutes, with integrated support for Prebid, Google Ad Manager, and multiple demand partners.
Popularity: 1 points | 0 comments
58. Show HN: The Art of Companion Creation
URL: https://github.com/la-acompaante-2025-pelis
Author: ithilda
Description:
Popularity: 1 points | 0 comments
59. Show HN: MultiTrack – Revolutionary Music Making
URL: https://apps.apple.com/us/app/multitrack/id1006315999?mt=12
Author: akaz333
Description:
Popularity: 1 points | 0 comments
60. Show HN: TinyJS – A Minimalist Front End Framework with Managed State
URL: #
Author: atum47
Description: Hey HN! I’ve been working on TinyJS, a small framework designed for managing state and components in a lightweight way. To illustrate its usage, I built TinyApp, a simple example that showcases its capabilities. TinyJS is designed to be minimal but still powerful for small-scale projects.
Would love to get your thoughts on it!
https://github.com/victorqribeiro/tinyapp
Popularity: 1 points | 0 comments
61. Show HN: Podseo – Growth and competitive intelligence for Podcasts
URL: https://podseo.com
Author: thebask
Description: We've recently launched Podseo, a product designed to optimize SEO specifically for podcasts. Instead of focusing on traditional search engines, Podseo enhances visibility on platforms like Apple Podcasts, Spotify, YouTube Music, and Amazon Music.
Despite the growth of podcasting, marketing and promotion for podcasts often lag behind other industries. Podseo aims to bridge that gap by providing competitive intelligence, improving rankings, and uncovering growth opportunities for podcast creators.
Would love to hear your thoughts, feedback, and suggestions!
Popularity: 1 points | 0 comments
62. Show HN: Hashtable – Generate precomputed hash tables from large wordlists
URL: https://github.com/ibnaleem/hashtable
Author: ibnaleem
Description:
Popularity: 1 points | 0 comments
63. Show HN: Hacker News Discussions Narrated by AI
URL: #
Author: qbqetell
Description: HNbyAI takes top HackerNews discussions, then narrates them in paragraphs using AI. To conclude, it injects a question that playfully challenges the intelligence of the participants
HNbyAI is a project from DOrch, meant to demonstrate how much could be done with little container resources. This project is powered by $1 container cloud hosting at DOrch. It runs on 128 MHz of AMD EPYC CPU and 256 MB or RAM. It comfortably handles 450,000 requests / hour
Link: https://hnbyai.prjct.cloud/
Popularity: 1 points | 0 comments
64. Show HN: KaChiKa App – Learning Languages Through Life
URL: https://kachika.app/
Author: xcc3641
Description: On my journey of language learning, I deeply understand the challenge of memorizing words - learning and forgetting, wanting to speak but unable to start. As a learner who relies on visual memory techniques, I know the power of visualizing abstract concepts. This experience inspired the idea of "integrating languages into life, learning through life" - this is the original intention behind developing this app.
KaChiKa
Smart Image Analysis We analyze image content to generate multiple words and create everyday sentences based on these words. Word tags on images are clickable with pronunciation features, making them incredibly convenient learning companions.
Share Cards You can save your created images to your album for easy access and share them on any social media platform. View all words at a glance and learn vocabulary based on different scenarios.
History Review We prioritize privacy - all your images are stored locally without any data uploading. Through history, we can easily review word cards for repeated learning sessions.
I hope this app can help learners who share similar struggles, enabling us to master new languages effortlessly in our daily lives!
Popularity: 1 points | 0 comments
65. Show HN: The Art of People Creation of the Gods
Author: chandadakn
Description:
Popularity: 1 points | 0 comments
Conclusion
Today's Show HN roundup showcases a diverse range of innovative projects. From AI-powered tools to creative coding solutions, these projects reflect the dynamic nature of our tech community. Which project caught your attention the most? Let us know in the comments!
Tags: #ShowHN #TechInnovation #DeveloperProjects #AI Applications #Open Source Software