Alternatives
Products that do what Slupe lets web LLMs safely edit local files does
Slupe lets you use web-based LLMs to modify local files without leaving the browser. npx slupe --clipboard It's a CLI tool that watches for LLM commands and executes them on your computer. Key features: - Custom syntax (NESL) designed for LLM reliability - fewer search/replace failures than existing approaches - Clipboard mode: copy from browser → Slupe executes → paste results back to clipboard - Generates instructions for LLMs based on your allowed actions - Sandboxed filesystem operations with configurable permissions + automatic git backups Motivation: I wanted to use web based Opus…
- 1
- 2CC
We are longtime members of HN and this is our only submission requesting feedback from the HN community on our product, Clipboard which we have been developing for the past year. Clipboard is a service to save anything online using a bookmarklet or browser extension (think Dropbox for content on the web). Clipboard is built using open source technologies, including Riak, Redis, NGINX, Node.js, and jQuery. One of our core differentiators is how we preserve the visual look and functionality of the original source, which is evident in the sample clips from github here:…
2012
- 3
- 4
- 5
- 6
- 7
- 8EL
Instead of giving LLM tools SSH access or installing them on a server, the following command: $ promptctl ssh user@server makes a set of locally defined prompts "magically" appear within the remote shell as executable command line programs. For example, I have locally defined prompts for `llm-analyze-config` and `askai`. Then on (any) remote host I can: $ promptctl ssh user@host # Now on remote host $ llm-analyze-config /etc/nginx.conf $ cat docker-compose.yml | askai "add a load balancer" the prompts behind `llm-analyze-config` and `askai` execute on my local computer (even though…
Mar 2026 · docs.promptcmd.sh
- 9NL
Hey folks, I just wanted to share a quick script I threw together called notational ls. One of the big problems of any code base (or any filesystem) is that it's hard to tell what's what - folder and file names often trade brevity for clarity. So I thought about a version of `ls` that works like this: > nls web: Where python web server files are stored ad_hoc: One time scripts ios: Our IOS code images Adding descriptions is really easy too: > nls images Images SHARED between both ios and web web: Where python web server files are stored ad_hoc: One time scripts ios: Our IOS code…
2011
- 10GA
2023 · github.com
- 11UL
Hi everyone, Just wanted to share a use case where local LLMs are genuinely helpful for daily workflows: file organization. I've been working on a C++ desktop app called AI File Sorter – it uses local LLMs via `llama.cpp` to help organize messy folders like `Downloads` or `Desktop`. Not sort files into folders solely based on extension or filename patterns, but based on what each file actually is supposed to do or does. Basically: what would normally take me a great deal of time for dragging and sorting can now be done in a few. It's cross-platform (Windows/macOS/Linux), and fully…
2025 · github.com
- 12FL
2025 · firstrowchat.com
- 13LF
Hey HN, I built SWE-Kit, LLM toolkit (Function callable tools) which makes building agents specialised in coding like Devin very easy. I noticed a typical pattern while building local agents: creating & perfecting LLM tools to interact with system or codebase was the repeated and time-consuming. We created a layer that simplifies building agents that can interact with code, file system, git, shell and allows you to quickly solve for a wide variety of coding agent use cases. Aren’t there open coding agents already? Well, yes, but most folks would want to solve their specific use case like a…
2024 · swekit.dev
- 14PU
After seeing a cool demo of a hack on Twitter, I built a cross platform version of it that works well and uses streaming. From anywhere on Mac and Linux, trigger Ollama and optionally feed it your clipboard. I built it yesterday and it's already very useful to me. I'm pretty excited about it and wanted to share!
2024 · github.com
- 15LC
2023 · simonwillison.net
- 16IM
Hey HN, Clipboard managers handle sensitive data such as passwords, personal notes, API keys, etc. To trust one you need to be sure that it doesn't send your data to third parties or store it on remote servers. With closed-source apps, you have to take the developer’s word for it. As a software engineer, I don't like that. Transparency matters. So, I decided to make my commercial clipboard manager open source. Anyone can inspect the source code, verify that data stays local and never leaves the user's device. Anyone can build the app from source and use it. At the same time, the app is still…
2025
- 17AM
I recently saw a post from the Vercel CEO pointing out that LLMs understand websites much better when they can request: `Accept: text/markdown` Most websites today are built for humans. When AI agents try to consume them, they get complex HTML instead of clean, structured content. So I built *accept-md* – a simple open-source package for Next.js that helps solve this. Getting started is intentionally minimal: ``` npx accept-md init ``` After that, your existing Next.js routes can automatically respond with Markdown whenever an AI agent (or any client) requests it. No redesigns, no CMS…
Feb 2026 · accept.md
- 18DS
Oct 2025 · substack.com
- 19SO
SURF (Search Utility & Reading Framework) is an open-source API that bridges LLMs with the web. It provides a standardized interface for web search and content processing that preserves formatting of tables, code, and complex layouts. Key features: - Multiple search providers (SearXNG, DuckDuckGo, Brave) - HTML cleaning and smart content extraction - Model Context Protocol (MCP) integration for Claude and other AI assistants - Self-deployable with minimal setup (Docker, bare metal, cloud) - API key authentication I built this to make it easier to add web capabilities to LLM applications…
2025 · github.com
- 20IL
2025 · github.com
- 21AB
All LLM user interfaces I've seen so far are somewhat frustrating: * ChatGPT web requires a lot of copy-paste, it rewrites whole document even if you need to update a part of it, etc. * Github Copilot completions are rather unreliable and do not leave an option to specify what you want; Copilot's chat sidebar is little more than ChatGPT integrated into the IDE * Google Docs have right UI for non-code text, but they use really dumb model (not Gemini 1.5 Pro). Also won't work for code. So... I wrote a Emacs Lisp function which calls LLM with contents of the buffer to generate text according to…
2024 · x.com
- 22GL
Hi HN, still working on this gptme LLM CLI/agent that's getting really good. Past attempts at submitting to Show HN haven't led to any feedback, so giving it another try!
2024 · github.com
- 23LA
You build LLM applications with YAML files, that define an execution graph. Nodes can be either LLM API calls, regular function executions or other graphs themselves. Because you can nest graphs easily, building complex applications is not an issue, but at the same time you don't lose control. The YAML basically states what are the tasks that need to be done and how they connect. Other than that, you only write individual python functions to be called during the execution. No new classes and abstractions to learn.
2024 · github.com
- 24LG
LLM Globber is a command-line utility written in Rust for collecting files from various locations, filtering them, and outputting their contents to a single text file. This tool is designed to prepare local files for analysis by Language Learning Models (LLMs). Criticism welcome.
2025 · github.com
Ranked by how close each launch is in meaning, then by votes. Refine with a description →