Your personal news anchor.
On your machine.

Tell Pepper what you care about, in plain words. She researches it around the clock, writes the bulletin with an on-device model, and presents it from her own studio โ€” with her own voice. No cloud, no accounts, no telemetry.

Open source, AGPL-3.0 ยท Benchmarked, not vibes ยท Full on-device brain on Apple Silicon

Pepper presenting at the MNN research desk

Install โ€” thirty seconds to air

curl -fsSL pepper.software | sh
pepper start

Prefer npm? npm i -g @pepperchan/pepper ยท Node 18.17+ ยท everything lives in ~/.pepper ยท her voice tier: pepper voice install

01

Tell her your beats

"Watch open-source robotics and GPU prices for me." Plain words in her studio โ€” she works out the rest and starts sweeping the wire every fifteen minutes.

02

She writes the bulletin

An on-device model turns the wire into a sourced broadcast โ€” vendor claims labeled, rumors kept off the air, nothing invented. Your reading interests never leave the machine.

03

She goes on air

A 3D newsroom in your browser: chyron, ticker, her designed voice, deep-dive reports on demand โ€” and a one-command export that puts your station on the public web.

Benchmarked, not vibes

Best in her weight class โ€” and honest about the ceiling above it.

MoltBench scores wire-to-report work: grounding, attribution, and adjudication of deliberately contaminated bundles, under blind judges. Pepper's first model failed it โ€” that failure became the release gate. Her current desk model cleared it: +23 grounding points over its own untuned base, 10/12 blind wins against Qwen3-4B-2507, 11/12 against Qwen2.5-7B. Models 6ร— and 13ร— her size still out-broadcast her โ€” 10/12 and 11/12 โ€” and those rows are published too, because a leaderboard that hides its ceiling isn't one. The judge column is the claim; regex grounding is only the screening metric (it rewards terseness โ€” a lesson this benchmark learned in public). Protocol and bundles โ†’

ModelBlind judges vs pepper-deskRegex grounding (screening)
pepper-desk-e2b (2B active)โ€”88.6%
Qwen3-4B-Instruct-2507 (same class)she wins 10 / 1288.3%
Qwen2.5-7B-Instructshe wins 11 / 1277.5%
gemma-4-12b (her family, 6ร— the size)she loses 2 / 1274.3%
Qwen3.8-27B (13ร— the size)she loses 1 / 1280.9%
gemma-4-e2b (her untuned base)โ€”65.2%

Run a station of your own

Three ways to put a Pepper on the web.

Watch this one

The reference station at pepper.watch โ€” served static from Cloudflare Pages, her voice included.

Export yours

Run Pepper locally, then pepper export โ†’ npx wrangler pages deploy pepper-site. Your beats, your bulletins, your voice files โ€” a complete station from your own desk.

One-click start

Deploy the station template straight to your Cloudflare account, then feed it from your desk whenever you like.
Deploy to Cloudflare