Every company wants to be AI-first
But your AI has no idea how your company actually works
So we fixed it. Record how your team actually works and turn it into a brain your AI can use
It writes down how everything gets done. Then it turns that work into agents
Introducing: the most secure way to build a company brain
screenpipe records everyone's screen in your company
redacts sensitive information on device with state of the art performance
and turn you into an AI native company powered by an AI brain continuously updating
your memory forgets. Screenpipe doesn't.
GitHub Repo of The Day for Creators - Day 8
name : ππ€π³π¦π¦π―π±πͺπ±π¦
β what it does
a local AI-powered memory system that continuously records your screen activity and transcribes audio running through your computer.
it automatically:
- reads on-screen text with OCR
- transcribes meetings and conversations
- indexes everything locally
- creates a searchable history of your digital life
think of it as search for your past.
β why creators care
everyone has experienced this.
you saw an article.
a tweet.
a metric.
a code snippet.
a client message.
then three days later you need it again and have absolutely no idea where you found it.
@screenpipe solves that problem.
instead of relying on bookmarks, screenshots, or memory, you can simply search for a keyword and jump back to the exact moment it appeared on your screen.
β creators that need it
- founders
- freelancers
- researchers
- developers
- operators
- content creators
- consultants
anyone who constantly switches between tabs, meetings, documents, and tools.
β what problem it solves
- forgotten client requests
- lost articles and websites
- scattered research
- missed meeting notes
- untracked work sessions
- context switching overload
it creates a searchable record of what you've seen and heard.
β how creators actually use it
- search old client meetings for exact quotes
- recover websites they forgot to bookmark
- find metrics they saw days ago
- locate code snippets from previous sessions
- generate end-of-day work summaries automatically
- connect local AI models to analyze work history
β why this repo stands out
most tools that promise "perfect memory" come with privacy tradeoffs.
Screenpipe takes a different approach.
it's:
- open source
- local-first
- private
- self-hostable
- searchable
- AI-ready
your data never has to leave your computer.
for many people, it replaces:
- note-taking apps
- meeting transcription services
- memory tools
- expensive productivity subscriptions
β best use case
perfect for:
- founders drowning in context switching
- freelancers managing multiple clients
- developers researching across dozens of tabs
- operators generating automated work reports
- creators collecting ideas and references
β founder
@louis030195
β extra proof
- actively maintained
- growing plugin ecosystem ("Pipes")
- recent releases and commits in 2026
- community-built automations already connecting Screenpipe to tools like Notion, Salesforce, and HubSpot
this is one of those repos that feels unnecessary until you use it.
then you start wondering how you ever worked without it.
meta started to record all their employee
it's the gold rush of human data
AI has no idea what people are doing
it's really hard to have very reliable, low CPU, cross-platform way to capture this
that's why we released screenpipe SDK: build AI apps that have the full context
Imagine recording the screen of every single team member 24/7
Then handing it off to AI agents working your entire Google Workspace - with the full context of the company in hand.
Comment if you want your company to enter the autonomous company era
Introducing spii-45: a privacy foundation model
It removes PII from text and images with near-frontier model performance at 9ms inference time on consumer device
Outperforms by far PII-specialized model from Google, OpenAI, Microsoft
read more: https://t.co/YDDfyJZJqG
one week after getting into YC S26 @screenpipe weekly active users more than tripled π₯²
A year from now, working without giving AI access to everything you do all day will look insane.
Every company will ingest what every employee does, 24/7, into the brain of their AI.
one of the reason I built @screenpipe is because I'm a heavy @obsdmd user - I have a personal second brain that captures everything I've thought, written, decided for years. But Obsidian only knows what you type into it
screenpipe knows everything you've seen, said, or heard - automatically
And when you point that at a company instead of a person, you get the institutional second brain: every workflow, every decision, every departing employee's tacit knowledge - captured, queryable, and convertible into SOPs and agents
When I applied to YC a few years ago for the first time I had built a GPT2 powered Discord bot that was animating communities with thousands of people π₯²
I was running GPT2 when it came out with RAG powered by a FAISS vector search index with thousands of rows I had labelled manually through a UI I built to do some kind of RLHF
I had no business notion though π₯² pure yolo mode
Introducing screenpipe SDK: capture high fidelity human workflows in a one liner
Meta started recording 70k employees for computer use data.
Amazon started recording all their employees for computer use data.
Everyone's trying to transition into the AI era. But first you need to understand the bottleneck, which are what people are doing, the processes inside companies.
screenpipe SDK is battle tested on 250k+ installs, cross platform, highly optimized.
Try today π
@screenpipe is in YC S26
hiring our first technical customer success manager
someone who's sold enterprise software, can read code, lives in claude/codex with 20+ agents a day
the job: put screenpipe on every enterprise laptop on earth
DM me