Skip to main content
screenpipe cannot restore an AI model’s hidden context. it can give the next session a local record of recent work: what changed, what was decided, what remains open, and where the evidence came from.

​
two ways to start

​
build a context file

1

choose one destination

Start with one Markdown file in a private project folder, wiki, or Obsidian vault. avoid creating several competing memory stores on day one.
2

define the schema

Keep current objectives, recent changes, decisions, open loops, blockers, and source time ranges. separate durable facts from short-lived activity.
3

generate it manually

Ask screenpipe or your MCP-connected agent to review a bounded period and update the file. require it to preserve still-valid entries and mark missing evidence.
4

review the first updates

Remove secrets and irrelevant personal detail. confirm that decisions were accepted rather than merely discussed.
5

teach agents how to use it

Add one line to the project’s agent instructions telling tools to read the file at the start of relevant work and update it only under your chosen policy.
6

schedule only after it is stable

Once manual updates are reliable, run the pipe hourly or daily. keep a last-updated time and an explicit “no new evidence” state.

​
starter schema

​
update prompt

a memory file concentrates context. keep it local or in an access-controlled repository, exclude secrets, and define retention before scheduling recurring updates.