Skip to content
Back to search

papr

A fast, native RSS reader — plus an agent-facing CLI so your AI agent can read, search and triage your feeds from the shell.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/l0ng-ai--papr/badge.svg)](/listings/l0ng-ai--papr)

HTML

<a href="/listings/l0ng-ai--papr"><img src="/api/listings/l0ng-ai--papr/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

| Platform | How | | --- | --- | | **macOS** | `brew install --cask l0ng-ai/papr/papr` — or grab the `.dmg` | | **Windows** | Download the `.msi` installer | | **Linux** | Download the `.AppImage` or `.deb` |

All packages live on the **[latest release](https://github.com/l0ng-ai/papr/releases/latest)**. The macOS builds are Developer ID signed and notarized.

---

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 96 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. <div align="center">
  2. <img src="docs/logo.svg" alt="Papr" width="96" height="96" />
  3. # Papr
  4. **A fast, native RSS reader — and a CLI your AI agent can actually drive.**
  5. <img src="docs/screenshot.webp" alt="Papr" width="820" />
  6. </div>
  7. Papr is two front-ends over **one local database**:
  8. - **A desktop reader** — fast, native, offline-first. No account, no cloud.
  9. - **`papr`, an agent-facing CLI** — so an autonomous agent (Claude Code, Codex,
  10. OpenCode…) can read, search and triage your feeds straight from the shell.
  11. [Jump to it ↓](#papr--your-feeds-handed-to-your-agent)
  12. Both read the same database through the shared `papr-core` crate, so the app and
  13. the CLI can never drift apart.
  14. ---
  15. ## The desktop app
  16. - **Feeds & folders** — subscribe, organize, and import/export OPML.
  17. - **Smart views** — All, Unread, Starred, and Read Later, with live counts.
  18. - **Tags & rules** — color-coded tags and rules that tag new articles automatically.
  19. - **Full-text** — fetch and clean the complete article when a feed ships only a summary.
  20. - **AI** — summaries, ask-the-article Q&A, and digests. Bring your own API key.
  21. - **Audio** — a built-in player that follows you from article to article.
  22. - **FreshRSS sync** — keep read state in step with a FreshRSS server.
  23. - **Local-first** — everything stays on your machine. No account, no cloud.
  24. - **Localized** — English, Japanese, and Simplified Chinese.
  25. ### Install
  26. | Platform | How |
  27. | --- | --- |
  28. | **macOS** | `brew install --cask l0ng-ai/papr/papr` — or grab the `.dmg` |
  29. | **Windows** | Download the `.msi` installer |
  30. | **Linux** | Download the `.AppImage` or `.deb` |
  31. All packages live on the **[latest release](https://github.com/l0ng-ai/papr/releases/latest)**.
  32. The macOS builds are Developer ID signed and notarized.
  33. ---
  34. ## `papr` — your feeds, handed to your agent
  35. This is what makes Papr different. `papr` is a command-line companion built **for
  36. autonomous agents** to drive over the shell. Point your agent at it and it can
  37. work your feeds with no GUI:
  38. - **Read** — `feeds`, `list`, `read`, full-text `search`
  39. - **Triage** — `mark` read/star/later, `extract` full text, `refresh`
  40. - **Manage** — subscriptions, folders, tags, rules, highlights, OPML
  41. - **Sync** — FreshRSS / Miniflux
  42. Run bare `papr` and it prints your unread dashboard *plus the next useful
  43. commands*, so the agent orients with zero manual. Output is
  44. [TOON](https://toonformat.dev) — ~40% fewer tokens than JSON — with definitive
  45. counts and structured exit codes.
  46. ```console
  47. $ papr
  48. unread: 206 starred: 17 later: 0 feeds: 15
  49. articles[10]{id,feed,title,flags,date}:
  50. 3664,V2EX,[Java] 使用 kkRepo 搭建 Maven 私服,unread.star,"2026-06-25"
  51. ...
  52. help[4]: Run `papr read <id>` to read an article's full text, ...
  53. ```
  54. ### Hand it to your agent — one line
  55. The bundled **[`papr-rss` skill](skills/papr-rss/SKILL.md)** loads *on demand*
  56. when an agent recognizes a feed-related task, so it costs nothing until you use
  57. it. Install it with [`skills`](https://github.com/vercel-labs/skills):
  58. ```sh
  59. npx skills add https://github.com/l0ng-ai/papr/tree/main/skills/papr-rss
  60. ```
  61. Want the agent *proactively* aware of your feeds every conversation? `papr setup`
  62. wires up an ambient SessionStart hook (Claude Code, Codex, OpenCode).
  63. ### Install the CLI
  64. | Platform | How |
  65. | --- | --- |
  66. | **macOS / Linux** | `brew install l0ng-ai/papr/papr-cli` |
  67. | **Windows** | Download `papr-x86_64-pc-windows-msvc.zip`, unzip, drop `papr.exe` on your `PATH` |
  68. | **Any** | Prebuilt `papr-<target>.tar.gz` from the [latest release](https://github.com/l0ng-ai/papr/releases/latest), or `cargo build --release -p papr-cli` |
  69. > **Full command reference, agent setup, and install options → [docs/cli.md](docs/cli.md)**

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.