louis030195

thanks, correct!

correct

claude and gpt do record manually a workflow and turn it into a skill

screenpipe is more focused on 1. building a 24/7 living memory layer for your agents and your company 2. building a living list of automation opportunities without having to click a button or having to be technical

yes we keep track of memories confidence level and timestamp,

we found that in order to find automation opportunities it's better to have agents segment, classify (for example personal vs pro), enrich (which customers/people are related to this workflow) and organize the data first, then it's much easier to find repetitive tasks

You can turn off screenshot recording and only capture accessibility data, it still captures most of the meaningful data

Otherwise we usually collaborate with the company to allow screenpipe

Can you expand on this? Usually 2fa allows you multiple options

Hey sorry about that, we made a lot of work on improving CPU usage, we benchmark it on $200 laptop now and it runs smoothly

You can also configure settings like changing transcription engine or only record meetings or turning off some features to reduce resource usage

We have a permission system that allows you to define rules in the markdown header, such as only allowing a time range to be queried, or modality

Hey I'm sorry that it's not convenient license for you, and you're right that we should have set this license early on instead of switching.

We're open to more feedback, things could change in the future

That's great. I like the comparison to Celonis etc. We're sort of offering a privacy-first alternative to them for Enterprise

Would love to get in a call and help you setup the privacy settings properly, although default are filtering API keys, my cal link if you want:

https://cal.com/team/screenpipe/chat

Feel free to configure local LLM like Ollama, btw

hehe, any color suggestions?

Interesting, I partly agree. It sounds like how the human brain works, but what nature learned is not necessarily what we should keep

We capture everything and gives you and option for a flexible data retention policy, so that you can prune mp4 files for example or verbose accessibility trees, while our agents generate high level memories referencing low level data

It still not perfect, but ideally Screenpipe would record forever so that you have infinite memory of every tiny details, while having high level structured memories for humans and agents, individually or as a company

We protect the Rust API by a token and the PII model redact information in the database. You can configure which categories to redact

We also have early support for encryption at rest through our CLI

Awesome thanks for sharing, will follow closely :)

Thanks! In fact most of AI apps today have a screen recording component, including Claude, Codex. There are even apps used by hundred of thousands that record your screen 24/7 in the cloud, to provide context, like Screenpipe does.

We're the only local-first, open source option

How much time do you spend explaining the context to your Claude? Or writing detailed prompts? Copy pasting documents into the prompt?

Can you expand on that? Would love to know more specifically

Fair concern but the risk is similar to any tool you give deep access to like Claude, Codex, or even your operating system

Ultimately, it’s up to you what you run and trust

Screenpipe is open source and local-first

You can inspect it and keep your data on-device, with encryption at rest

It's local, and for enterprise it runs on premise

Hey sorry about that, it's been a while ago, we didn't know that emails on Github were not allowed to be used (since I received many emails from startups that way). We apologized to our users and never did this again

Sorry about that and thanks for letting me know, fixing right now

That's interesting, thanks! Indeed we did a lot of work to optimize performance and reliability.

I'm curious what does your AI buddies do more specifically and how do you use them?

You can decide which AI provider you use, either local through Ollama for example, using your own cloud API key, or using Screenpipe cloud. We also support confidential inference through tinfoil.sh

Screenpipe captures accessibility tree and screenshot when you perform a meaningful action. It doesn't use AI at recording time (except PII removal and OCR infrequently). So it can be every few hundred milliseconds to few minutes or more (if screen idle or sleeping)

We usually benchmark CPU usage on $200 Windows/MacOS laptop

You can define websites or apps to filter out. You can also define a recording schedule, for example stop recording on weekend

great

we have more than 1500 paid users btw

i use dating skill to update my dating CRM (md notes) and my dating dashboard

recently i have been working on a dating skill so AI book the right place based on each other personality using computer use

Looks great. I don't use opencode myself but like a lot Claude skills, agents, I have like 50 different ones for personal life, work, dating, whatever Is there integration with Claude skills?

Have you considered using or integrating with ACP? https://zed.dev/acp

We use it in our desktop app IDE (mediar.ai) and it's pretty good

better ui: https://claude.ai/public/artifacts/2cb157a7-6262-4b70-912e-a...

screenpipe founder here, love to see more products in this area, ideally OSS, local, no lock in, API/MCP friendly

kind of sad it's macos only, i'm mostly windows user now :)

just changed to MIT: https://github.com/mediar-ai/terminator

enjoy!