explainx / blog
Jul 14, 2026: screenpipe relaunches on X — local-first screen+audio memory, searchable SOPs, MCP for Claude/Codex. ~20K GitHub stars, 1,956 forks. explainx.ai maps install, privacy filters, pipes, and vs Limitless.
Jul 12, 2026
@wonderwhy-er's Desktop Commander turns Claude into a full OS agent — terminal sessions, fuzzy edit blocks, in-memory Python, and subscription pricing instead of API burn. explainx.ai setup, security, and vs Cursor/Windsurf.
Jul 9, 2026
Stanford's 2026 AI Index shows entry-level developer roles shrinking while agent benchmarks climb. Here's the six-stage AI skills roadmap — prompting to MCP to agents to RAG — that keeps engineers ahead of that curve instead of behind it.
Jul 7, 2026
Cloudflare's Monetization Gateway uses the open x402 protocol to settle per-request stablecoin payments at the edge — no signup, no API key, no checkout redirect. explainx.ai breaks down the 402 flow, MCP monetization, Pay Per Crawl lineage, and what X discourse got right and wrong.
On July 14, 2026, screenpipe (@screenpipe) posted a launch thread that reframed the product in one line: record how you work → searchable memory, SOPs, and AI agents. The pitch — open source, local-first, npx screenpipe record, ~20K GitHub stars — cleared 260K+ views in hours.
The idea is not a new chat window. It is a continuous work ledger on your machine: screen + audio → local SQLite → MCP/API → agents. Developers already report piping that ledger into Codex and Claude for continual memory; skeptics ask whether always-on capture is compatible with real privacy.
explainx.ai verifies GitHub stats, walks install + MCP wiring, and maps exclude-app controls, Pipes, and how this differs from Limitless/Rewind — without treating a marketing thread as a security audit.
| Item | Detail |
|---|---|
| Company | screenpipe (Mediar, Inc.) · YC S26 (joined May 14, 2026 per README) |
| Jul 14 thread | Work memory + SOPs + agents · local-first · npx screenpipe record |
| GitHub (Jul 15) | screenpipe/screenpipe · 19,992 stars · 1,956 forks |
| Contributors | ~139 on GitHub API (Jul 15); launch thread cited 130+ |
| Capture | Event-driven screen + accessibility tree · OCR fallback · local Whisper audio |
| Agent bridge | MCP (screenpipe-mcp) · Pipes (markdown-scheduled agents) · REST :3030 |
| Claimed load | 5–10% CPU · ~5–10 GB/mo storage · 8 GB RAM recommended |
| License | Source-available — personal non-commercial OK; commercial use needs license |
| Desktop app | Subscription from $25/mo; lifetime licenses grandfathered |
The README architecture is straightforward:
screen + audio → local storage → AI
Event-driven capture is the technical bet. Instead of saving every second of video, screenpipe listens for app switches, clicks, typing pauses, scrolls, and grabs a screenshot + accessibility tree when something changes. Text comes from the OS accessibility layer first; OCR (Apple Vision, Windows native, Tesseract on Linux) fills gaps for games, RDP, or broken a11y.
Audio uses local Whisper Large-V3-Turbo by default, with optional Deepgram cloud transcription. System and mic audio can be transcribed with speaker diarization.
Storage lands in local SQLite with FTS5 plus JPEG frames on disk. The project claims ~300 MB per 8 hours vs ~2 GB for naive continuous recording — a meaningful difference if you leave capture on for weeks.
explainx.ai read: This is closer to structured activity logging than DVR screen recording. That design choice is why MCP integration matters — agents query events and text, not raw multi-hour MP4s.
Two entry points:
CLI (fastest trial):
npx screenpipe record
Desktop app: screenpi.pe/onboarding — signed builds, auto-updates, subscription features.
MCP hook for Claude-family hosts:
claude mcp add screenpipe -- npx -y screenpipe-mcp@latest
Then ask in-session: "what did I see in the last 5 mins?", "summarize today conversations", or "create a pipe that updates Linear every time I work on task X".
For protocol background, see explainx.ai's MCP guide. For permission boundaries when agents read personal context, pair with context-mode MCP sandboxing thinking — screenpipe is powerful precisely because it is broad.
Pipes are markdown files (pipe.md) with prompts and schedules. screenpipe runs an agent (pi, Claude Code, etc.) against your local timeline and can call APIs, write files, or patch records.
Built-ins listed in the README include:
| Pipe | Output |
|---|---|
| meeting-summary | Recap when a meeting ends |
| day-recap | Accomplishments + open threads |
| standup-update | Yesterday / today / blockers |
| time-breakdown | Time by app and project |
| ai-prompt-journal | Prompts sent to AI tools → Obsidian/markdown |
| video-export | Highlight reel of recent screen activity |
Custom pipes live in ~/.screenpipe/pipes/. That is the SOP automation layer the Jul 14 tweet highlights — not just search, but recurring agent outputs grounded in what you actually did.
YAML frontmatter supports deterministic data permissions: allow-apps, deny-apps, deny-windows, content-type gates, time ranges, and endpoint blocks (allow-raw-sql: false). Enforcement is three-layer (skill gating, agent interception, server middleware with per-pipe tokens) — closer to policy-as-code than "please don't look at my bank tab."
This overlaps conceptually with agent skills (how agents behave) but adds OS-level capture as the data plane. Loop engineering is the natural orchestration layer for nightly standup pipes or verification gates on generated SOPs.
The launch thread split reactions:
| Camp | Argument |
|---|---|
| Privacy skeptics | Always-on capture normalizes surveillance — "privacy is a farce" |
| Pragmatists | Exclude-any-app + local storage makes it installable |
| Power users | Two weeks always-on → feed Codex/Claude for continual memory |
| Hardware worry | Mac fans / CPU — vendor claims 5–10%; verify locally |
Filters documented in README: window, app, browser extension, password fields, optional Screenleak PII model (May 2026 alpha). Audio exclusions on macOS 14.4+:
{ "excluded_apps": [{ "bundle_id": "com.spotify.client", "name": "Spotify" }] }
File: ~/.screenpipe/audio-exclusions.json (hot-reloads; override path via SCREENPIPE_AUDIO_EXCLUSIONS_PATH).
Telemetry caveat: README FAQ states PostHog analytics and Sentry are on by default; disable under Settings → Privacy → Analytics. Local capture does not mean zero network — only that frames and transcripts stay on disk by default.
OpenClaw angle: README lists OpenClaw among integrations. explainx.ai covered OpenClaw harness risks separately — if you route screenpipe MCP + OpenClaw messaging, treat OAuth and third-party harness bans as live policy, not solved problems. See OpenClaw safety analysis.
Use this table as a buyer/engineer checklist, not a scorecard — features shift quarterly.
| Dimension | screenpipe | Limitless (Rewind successor) | Microsoft Recall |
|---|---|---|---|
| Code audit | Source-available | Proprietary cloud stack | OS-bundled, closed |
| Default data plane | Local SQLite | Cloud-centric history | Local on Copilot+ PCs |
| Platforms | macOS, Windows, Linux | macOS, Windows (vendor scope) | Windows 11 |
| Multi-monitor | All monitors | Active window only (per README comparison) | Vendor-dependent |
| Developer API | REST + JS SDK + MCP | Limited | Minimal |
| Agent plugins | Pipes (markdown agents) | No equivalent listed | No equivalent listed |
| Audio | Local Whisper default | Vendor pipeline | Not focus |
Limitless question from X: "How's this different besides local storage?" — screenpipe's answer in docs is API + Pipes + permissions YAML + Linux + multi-monitor, not storage alone.
Claude Code /rewind note: Anthropic's /rewind restores session context after /clear — different problem from weeks of desktop memory. See Claude Code 2.1.191 changelog for harness-level rewind vs capture tools.
| Claim (Jul 14 thread) | Verified (Jul 15, 2026) |
|---|---|
| 20K+ stars | 19,992 — rounds to 20K; one reply sniped "less than 20k" |
| 1,900+ forks | 1,956 forks |
| 130+ contributors | ~139 per GitHub contributors API (Jul 15) |
| Open source | Source-available commercial license — inspectable, not MIT |
Repo URL: github.com/screenpipe/screenpipe (org migration from mediar-ai/screenpipe). Stars prove developer interest, not enterprise readiness — read LICENSE.md before shipping capture inside a commercial product.
npx screenpipe record on a non-production machine; measure CPU/disk for your monitor layout.claude mcp add screenpipe -- npx -y screenpipe-mcp@latest; test narrow queries ("last 5 minutes in VS Code only").REST smoke test (default port):
GET http://localhost:3030/search?q=meeting+notes&content_type=all&limit=10
JS SDK entry point: @screenpipe/js with pipe.queryScreenpipe({ q, contentType, limit, startTime }).
screenpipe's July 14, 2026 thread repositioned a mature repo (~20K stars, ~1.9K forks) as local work memory for agents: capture screen+audio locally, search with FTS5, expose context through MCP, automate with Pipes. npx screenpipe record plus screenpipe-mcp is the fastest Claude/Cursor integration path. Exclude-app controls and YAML pipe permissions address part of the privacy backlash, but always-on capture still demands explicit deny lists and telemetry choices. vs Limitless/Rewind, screenpipe sells auditability, API surface, and scheduled agents — not just local disk.
Sources: screenpipe README · docs.screenpi.pe · GitHub API — screenpipe/screenpipe, Jul 15, 2026 · screenpipe X launch thread, Jul 14, 2026
Star counts, pricing, and telemetry defaults are accurate as of July 15, 2026. Verify license terms and capture settings before deploying on managed or regulated devices.