Free, open-source screenshots, screen recording and audio recording, with local AI captions,
transcripts, meeting minutes and speaker labels, and every feature available to AI agents
through MCP and a CLI.

Features

✓ works, — not available. Notes in brackets name the limit. Current versions and downloads are on the
releases page; what each platform has been tested on is
in the release notes and in verification/.

Models download only when you press Download. Speaker labels run on two small models that ship inside the app; tell
the app which languages you speak (for example vi, en) so a short recording is not heard as a related language.
Private by design: no telemetry, and no network traffic unless you connect a destination or download a model; you
bring your own Google credentials. Actions of a recording that start, publish or delete need your confirmation.

Find personal data before you share a screenshot

Auto-redact reads the text in a screenshot with the recognizer built into your Mac (Apple Vision) and
proposes blur rectangles over the personal data and secrets it finds. You review the proposals
(masked previews, dashed boxes) and accept them one by one or all at once; nothing is applied
automatically. It runs on your computer and uses no network. The same function is available to agents
(MCP suggest_redactions, which only proposes) and to the command line
(capturemann annotate <id> --suggest-redactions). The user guide has the details:
Auto-redact.

It finds formats and checksums, not meaning: a payment card number (Luhn check and issuer prefix), a
Social Security number in an issuable range, a routing number with a valid checksum, a private-key block, a
PASSWORD=... line. It does not find names, addresses or dates. The kinds, generated from the rule data
(a test fails when this table and the code differ):

The "Standards that name it" column maps each kind to the public lists that mention that kind of data
(NIST SP 800-122, HIPAA Safe Harbor identifiers, PCI DSS, GLBA and state breach-notification laws). This
is a mapping of kinds, not a compliance claim: CaptureMann is not a compliance tool, and using it does not
make a screenshot compliant with any of them.

How well it works (measured, synthetic data)

All numbers below come from a stored report and are measured on synthetic screenshots made by this project
(300 images, fixed seed 20261030, 13 screen layouts, light and dark, 1x and 2x, some degraded): 211 images from
9 layouts (dev, where the rules were tuned) and 89 images from 4 other layouts (held_out, read once after
everything was fixed). The images contain made-up data whose formats the rules know, so these figures are an
upper bound for real screenshots, not a measure of real-world accuracy. Recognizer: Apple Vision, on an Apple
M4 Pro, macOS 26.6.2. Date: 2026-10-30.

The old and new columns score different sets of items (the old detector knew 4 of the 20 default kinds), so the
"found" rows are not like for like. With perfect text instead of Apple Vision (this separates rule errors from
recognizer errors) the 0.2.5 rules find 99.2 % at 98.5 % precision on dev and 100 % at 95.9 % on held_out.
Report: 0.2.5 final run (it includes the 0.2.3
detector on the same held-out layouts), with the earlier
0.2.3 baseline and
interim 0.2.5 run; per-kind, per-layout,
per-font-size and per-language tables and the lookalikes that raised false alarms are in them.

What the numbers say plainly. The false-alarm target is not met: the goal was below 0.2 false alarms per
image with nothing to find and 0.2.5 shows 0.746 (dev) and 0.889 (held_out). The generic long-token rule
(unchanged from 0.2.3 and kept on) is the main cause, for example by proposing full git hashes. npi is off by
default because only 30 % of its proposals were real. Private-key blocks are the weakest default kind with
Apple Vision (65.5 % of key lines covered, 15.5 % still readable after the blur, dev only: the held-out layouts
contain no keys or secret URLs). Nothing here has been checked on real screenshots yet (that is the
maintainer's manual cross-check, tests/manual/RED-1.md).

To reproduce on your own Mac (builds the synthetic set from the seed, no network; run uses the system
recognizer):

cargo run -p cm-render --example redaction_bench --release --locked -- gen --out /tmp/redaction-set
cargo run -p cm-render --example redaction_bench --release --locked -- run --set /tmp/redaction-set --detector-only --split dev
cargo run -p cm-render --example redaction_bench --release --locked -- run --set /tmp/redaction-set --recognizer system --split dev

What it does not do

• It finds formats and checksums only. Names, street addresses and dates are not found, and there are no
  label-based kinds: a CVV or an expiry date with no card number on the screen is not proposed, and a bare
  value under a "Password" or "SSN" label is not found by the label (a NAME=value pair with a
  secret-looking name is).
• Text the recognizer cannot read stays. Small, low-contrast or unusual text can be missed, which is what
  the leak rate measures. Private-key blocks are the weakest default kind with Apple Vision.
• Bare ten-digit Vietnamese mobile numbers (0934851497) are not found, and passwords made only of letters
  (letmein) are not proposed.
• Some lookalikes are proposed anyway (in the dev split: hash strings, timestamps, ten-digit ids, tracking
  numbers); that is why you review.
• On Windows Auto-redact uses the recognizer built into Windows (0.2.8); on Linux it uses the system tesseract program (recall is lower than Apple Vision's). The numbers below are for Apple Vision on macOS only; neither of the others has been measured.
• It is not a compliance tool. A blurred screenshot is not proof that nothing sensitive remains: look at
  the result before you share it.

Install

Pick your system: macOS (below), Windows or Linux.

macOS

Requires a Mac with macOS 13 or later, Apple Silicon or Intel (Apple menu > About This Mac shows the chip). There is one download per chip. The Intel build (0.2.1 and later) is built and checked on Apple Silicon. It installs and opens on a real Intel Mac, but starting a screen recording crashed a MacBook Pro 16" 2019 in 0.2.2 (issue 16); 0.2.3 catches the error and retries with simpler settings, which is not confirmed on that Mac yet. The speech and text models may be slow on older Intel Macs. Please report problems. The app is about 180 MB (Apple Silicon) or 190 MB (Intel). The AI models are not in it: they download only when you press Download (about 4.4 GB for the recommended speech model, Large v3 Turbo, plus the recommended text model, Gemma 4 E2B). The two small speaker models are inside the app.

With Homebrew:

brew install --cask craft-mann/tap/capturemann

Homebrew picks the right build for your chip. This also links the capturemann command line into Homebrew's bin. Update with
brew upgrade --cask capturemann.

From the release page:

1. Download CaptureMann-v<version>-macos-arm64.dmg (Apple Silicon) or
   CaptureMann-v<version>-macos-x86_64.dmg (Intel) and its .sha256 file from
   Releases.
2. Check the download (in the folder with both files):
   shasum -a 256 -c <the DMG's name>.sha256 must print OK.
3. Open the DMG and drag CaptureMann to Applications.

The release DMG is signed with a Developer ID certificate and notarized by Apple, so it opens
normally. A build you make yourself from source is signed locally or ad hoc and is not
notarized: Gatekeeper blocks it at first launch, so right-click the app and choose Open, or run
xattr -dr com.apple.quarantine /Applications/CaptureMann.app. Updates are manual: download the new
DMG. The capturemann command line is inside the app; to use it as capturemann, link it once:
sudo ln -s /Applications/CaptureMann.app/Contents/MacOS/capturemann /usr/local/bin/capturemann.
To build it yourself instead, see building from source. More on verifying a
download: docs/development/releasing.md.

Windows

Windows 11 (x64). From Releases download
capturemann-<version>-windows-x64-setup.exe (a per-user installer, no administrator rights) or
capturemann-<version>-windows-x64.zip (unpack anywhere and run cm-desktop.exe; capturemann.exe is the command
line). Check the download with its .sha256 file (certutil -hashfile <file> SHA256) or the release's SHA256SUMS.txt.
A winget package (winget install CaptureMann.CaptureMann) is submitted (pull request)
and works only after it is accepted.
The files are not signed, so Windows SmartScreen warns before the first run (More info, then Run anyway).
From 0.2.8 the Windows build records (screen, microphone, system audio, camera), and has screenshots, the editor, the
library, local AI with the speaker and text models bundled, Auto-redact with the recognizer built into Windows, the CLI
and the MCP server. It was checked on one lab laptop (Windows 11, Intel graphics), see the reports
verification/L1-windows-0.2.8-*.md (PARTIAL). Not tested:
Windows 10, NVIDIA and AMD hardware encoders, a second monitor with mixed scaling, SmartScreen on a real download. The
older 0.2.6 Windows files have no recording.

_{Screenshots from the 0.2.8 Windows build on the lab laptop, with sample content only. More are in the release notes.}

Linux

Ubuntu 24.04 or later, Debian 13, or another distribution with glibc 2.39 or newer; x86_64 and aarch64. From
Releases:

sudo apt install ./capturemann_<version>_amd64.deb      # or _arm64.deb; Ubuntu and Debian

Other distributions: unpack capturemann-<version>-linux-<arch>.tar.gz, run ./check-runtime.sh (it names missing
libraries), then ./install.sh. Every file has a .sha256 and a minisign signature
(minisign -Vm <file> -P RWTeQv8ogB2CCuZ7j0rr3MovdHod4QATmVn+I329YC8pomOC6R9Rxc2k; the key is
packaging/linux/minisign.pub). 0.3.0 works like the other systems for: screenshots (region, window and display on X11;
region, display and, through the desktop's picker, window on GNOME Wayland), screen recording (on by default; GNOME records
without a share dialog, other desktops use the portal), microphone, system audio and camera, import and export (VA-API
H.264, or labelled software VP9 without a GPU encoder), the editor, the library, local AI, Auto-redact with
sudo apt install tesseract-ocr, the CLI and the MCP server. Differences by design: no live webcam bubble during a take (the
camera is a track, composited at export), a banner instead of a floating HUD, no per-app exclusion; window recording, global
shortcuts and the cursor track are X11 only. Details, the list of what was not run and the known gaps are in the release
notes and in specs/plans/linux-parity-matrix.md.

Quick start

make run-bundle                 # builds, signs and opens target/bundle/CaptureMann.app
# the CLI and MCP server are inside the bundle, in Contents/MacOS
target/bundle/CaptureMann.app/Contents/MacOS/capturemann capture screenshot

Connect an AI agent over MCP (stdio):

{ "mcpServers": { "capturemann": { "command": "/path/to/CaptureMann.app/Contents/MacOS/capturemann", "args": ["mcp"] } } }

See specs/02-agent-interface.md for the tools, permission tiers and
the CLI.

Build from source

Rust 1.95, Xcode command line tools and cmake:

cargo test --workspace --locked
make bundle

Full instructions, the bundled LGPL FFmpeg and macOS permissions: docs/.

Documentation

• docs/: building, permissions, plan, design, spikes
• specs/: product spec, technical design, agent interface, integrations, features
• CONTRIBUTING.md, SECURITY.md, CODE_OF_CONDUCT.md,
  CHANGELOG.md

Contributing

Contributions are welcome, especially new storage providers, publishing platforms and translations.
Read CONTRIBUTING.md first. Security problems: please report them privately, see
SECURITY.md.

Links

CaptureMann is a CraftMann app.
Contact ·
Privacy policy ·
Source

License

Apache-2.0, see LICENSE. Third-party notices: NOTICE and
THIRD_PARTY_LICENSES.md. The bundled FFmpeg is an unmodified LGPL build.

The Apache-2.0 licence covers the code. It does not grant rights to the CaptureMann or CraftMann names or logos (design/brand); forks should use their own name and marks.