Anything AI – A local Zapier (like) AI tool written in Rust
Hey HN! I really like local apps for their simplicity and privacy and hate paying Saas bills and I wanted a way to start automating my life with AI so I started building Anything. Anything is built on Tauri so the front end is React and the "backend" is Rust. It's 100% local & 100% doesn't ask you to spin up docker to use. Another core goal of the app is to get away from "package bloat" you see in other general purpose AI oss projects where they have a package.json that is 300 lines long ( more on that later. ) Oh btw I suck at Rust! I learned Rust while building this so the code is _not…
What it does
In the maker’s words, at launch
Hey HN! I really like local apps for their simplicity and privacy and hate paying Saas bills and I wanted a way to start automating my life with AI so I started building Anything. Anything is built on Tauri so the front end is React and the "backend" is Rust. It's 100% local & 100% doesn't ask you to spin up docker to use. Another core goal of the app is to get away from "package bloat" you see in other general purpose AI oss projects where they have a package.json that is 300 lines long ( more on that later. ) Oh btw I suck at Rust! I learned Rust while building this so the code is _not good_ yet. Be warned! >> The app is 3 core pieces wysiwyg editor -> react, react-flow work queue, db -> sqlite flow execution -> triggers, actions, etc >> Everything is just a file - All automation configuration state is "just a file" so you can persist your work and changes in git and share it easily over any medium.* An important side effect of state being "just a file" is it makes it easy to let LLM's write and update the config automatically with very little added complexity. >> More on execution system and package bloat Using Zapier as the example easily groked Anything has Triggers and Actions. Each Action is paired 1:1 with an extension. Think of extension like in VScode but instead of changing your UI or linting your code they execute an action. Since extensions power the app you only need to bring the extensions you want. Package bloat destroyed! When you download an extension it "publishes" a configuration object to your file system that makes it available in the UI to be configured and added to an automation flow. The UI reads directly from file system to show available triggers, actions etc. Each extension is a dynamic Rust library that can be loaded at runtime. In the future it will all be WASM but my noob Rust skills have kept this from being done yet. Since we are in Rust land we can also use lots of different languages to create extensions and as configuration in actions to run ad-hoc JS, Python, etc like you might be used to doing in Pipedream etc. Basically anyone can create an extension that runs an action if they want to do somethings special not yet built. This is also a really nice escape hatch to let people have custom looping, forking or decisions which is a common hard spot in wysiwyg logic editors. Along with registering an execute function, and a config object, each extension will also register a validation function. * This lets us do what I call "deterministic magic" where no matter how much LLM's or users are hallucinating while they are trying to configure actions on the fly they can get repeat deterministic feedback from the extension until the action configuration is valid. Currently I have built two triggers and 2 actions: Triggers: Manual Cron Actions: CLI HTTP To Use AI Locally so far I have just connected it to LM studio via HTTP vs spending a week trying to get a bad implementation done of a local AI extension. Would love your feedback! Carl Demo Video: https://www.loom.com/share/c71dc4d5a07c4424b3f6d5bbe218549f?... Github: https://github.com/tryanything-ai/anything Download Links: https://github.com/tryanything-ai/anything/releases/tag/app-... Website: https://tryanything.xyz * ok part of this isn't done. It's been in and removed again and will come back
Does a similar job
all alternatives →
- AOAnythingLLM – Open-Source, All-in-One Desktop AI Assistant2024 · github.com · ▲368
Hey HN! This is Tim from AnythingLLM (https://github.com/Mintplex-Labs/anything-llm). AnythingLLM is an open-source desktop assistant that brings together RAG (Retrieval-Augmented Generation), agents, embeddings, vector databases, and more—all in one seamless package. We built AnythingLLM over the last year iterating and iterating from user feedback. Our primary mission is to enable people with a layperson understanding of AI to be able to use AI with little to no setup for either themselves, their jobs, or just to try out using AI as an assistant but with *privacy by…
- NONous – Open-Source Agent Framework with Autonomous, SWE Agents, WebUI2024 · github.com · ▲155
Hello HN! The day has finally come to stop adding features and start sharing what I've been building the last 5-6 months. It's a bit of CrewAI, OpenDevon, LangFuse/Cloud all in one, providing devs who prefer TypeScript an integrated framework thats provides a lot out of the box to start experimenting and building agents with. It started after peeking at the LangChain docs a few times and never liking the example code. I began experimenting with automating a simple Jira request from the engineering team to add an index to one of our Google Spanner databases (for context I'm the…
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 19d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
