Screenpipe records your screen locally to give AI agents searchable memory
louis030195 · hn · 2026-07-24
Louis launches Screenpipe (YC S26), an app that records screen and audio locally and turns them into searchable memory for AI agents.
- The goal is to give agents context about what you’ve seen, said, and heard so they can automate repetitive work and generate SOPs.
- He argues that past approaches—fine-tuning, tool calling, MCP—still left agents without enough context or were too brittle for non-technical users.
- The post connects Screenpipe to his earlier work on RAG, Obsidian AI plugins, and Embedbase.
- He also points to a newer pattern: agents that incrementally maintain a persistent wiki/Markdown knowledge base that compounds over time.
More from coding & agent
- Tweaked orchestration skill turns agents into self-policing workflow — pvncher · 2026-07-27
- A practical map of 11 protocols in the modern AI agent stack — TheTuringPost · 2026-07-27
- Qwen Code nightly adds Goal v3 orchestration and workspace channel controls — qwen-code-ci-bot · 2026-07-27
- NVIDIA says Nemotron 3 Ultra hit 97.1% on agentic RTL chip-design tasks — NVIDIAAI · 2026-07-27
- Tokyo Agent Forge hackathon shipped production-ready AI agents in one day — DavidBennett__ · 2026-07-27
- Long-running agents will need immutable event logs, this thread argues — sebpaquet · 2026-07-27