Harshil Parekh
@harshilparekh874saas
Founder-ish.
Project
SnipAgentsnipagent.app
Capture anything on screen and get AI-powered insights instantly.
Founder-ish.
Hi! Good to see this platform growing as always. I had shared this earlier in the Strivle days, but I’ve since shipped a more complete version with a landing page and public release.
I built a desktop snipping tool that turns screenshots into structured AI input instead of static images. After taking a snip, it runs OCR to extract text and opens an action layer where you can send the context to a local model or external APIs like OpenAI, Claude, or Gemini.
The goal is to close the gap between seeing something on your screen and being able to immediately reason or act on it. I’ve also been experimenting with scrolling capture, screen recording, and step-by-step workflow documentation that can export into structured files with screenshots and actions.
It’s still early, but I’d love feedback from anyone interested in this kind of workflow or building tools around it.
heres the link: snipagent.app
Founder-ish.
Thanks! So initially this was designed for dev teams as they are already in the habit for screenshots and sending to llms, cursor or any other ai source and sometimes even StackOverflow for older legacy codebases or something and its currently being used by a dev team that has a legacy codebase and since its much cheaper than the snipping tool they were using earlier its becoming a good fit for their team but for non-technical pms or teams they would need a more polished ux and some more guided prompts but would love to make it more accessible for them too once I get more paying customers.
Founder-ish.
Hi! Good to see this platform growing as always. I had shared this earlier in the Strivle days, but I’ve since shipped a more complete version with a landing page and public release.
I built a desktop snipping tool that turns screenshots into structured AI input instead of static images. After taking a snip, it runs OCR to extract text and opens an action layer where you can send the context to a local model or external APIs like OpenAI, Claude, or Gemini.
The goal is to close the gap between seeing something on your screen and being able to immediately reason or act on it. I’ve also been experimenting with scrolling capture, screen recording, and step-by-step workflow documentation that can export into structured files with screenshots and actions.
It’s still early, but I’d love feedback from anyone interested in this kind of workflow or building tools around it.
heres the link: snipagent.app
Founder-ish.
Yeah, the idea space has definitely existed in some form for a while. This is a desktop app though, not an extension. The main focus is making the flow immediate after a screenshot. OCR + action layer + model routing in one place, plus a few workflow tools like scrolling capture and step-by-step recording. Still early, so I’m mostly trying to see what actually feels useful in practice. Theres actually a competitor that only does the premium screenshotting option that a lot of corporate places actually use called SnagIt and they charge 48/month so I wanted to make it better with some more features + ai and charge 5x as less initially.
Researcher | SaaS Founder | Building in public — follow the journey
How many ideas did you have before settling on the one or two you are currently building?
Founder-ish.
This year probably about 9 different ones
Stayed up until 8am shipping on Strivle.
Haven't even hit 24 hours yet and the traction has been insane. Founders pouring in, real posts, real conversations, DMs full of builders wanting in.
Huge things coming. This is just the start.
Founder-ish.
This is great! Keep moving forward and this just gonna get better!
Founder-ish.
Currently building SnipAgent, a desktop snipping tool that combines screenshots with AI. After taking a snip, it uses OCR to read text (and now images), then lets users run prompts through either a local LLM (currently Qwen 1.5 Coder because thats what my machine can currently handle locally) or their own Claude, Gemini, or OpenAI API keys. Workflow: Snip → Action Menu with preset/custom prompts → AI-generated response.
Founder-ish.
Im not completely familiar with Focalboard, so not entirely sure but firstly planning to at least have it be able to connect to company tools that already have existing company data like Drive, Notion, Slack, Confluence/Jira and Github (for dev support) using their respective API's +Oauth and companies can sync their data in that procedure. I assume focalboard would be similar if i just use the API/export, sync the boards and index them so they searchable
Founder-ish.
Currently building SnipAgent, a desktop snipping tool that combines screenshots with AI. After taking a snip, it uses OCR to read text (and now images), then lets users run prompts through either a local LLM (currently Qwen 1.5 Coder because thats what my machine can currently handle locally) or their own Claude, Gemini, or OpenAI API keys. Workflow: Snip → Action Menu with preset/custom prompts → AI-generated response.
Founder-ish.
There are currently 26 users, all from a parent’s workplace who sort of bought in as a group after seeing it as a useful productivity tool. They paid informally via e-transfer for lifetime access to the premium version, and they’re also acting as the first testers
hey guys! im a 12yo founder, js launched waitlist for early access for my agentic startup, go check it out at getvoxa.co :)
Founder-ish.
This is insane! Wish you the best of luck on your journey ahead!