Reco
What it is
Reco is free, open-source software that combines two camera feeds into a panoramic sports view and uses AI to follow the play. Ball and player detection support configurable framing presets. Automatic calibration uses AKAZE feature matching, while temporal synchronization can use IMU data or audio cross-correlation. The project offers a desktop app, command-line interface, library, and OBS plugin built on the same engine. It accepts GStreamer camera input and can submit frames to OBS and live streams. Listed targets include Linux, macOS, Windows, NVIDIA Jetson Orin, and cloud workers. Reco runs on hardware you own, and its website says footage stays yours. It also says it collects no usage data, sends no telemetry, and makes no network requests unless you configure them. The engine uses the AGPL-3.0-only license and has no public paid tier. Coaches, parents, hardware builders, and developers are named as intended users. iOS and Android support points exist, but concrete implementations are still to come.
For and against
For
- Combines two feeds into a panoramic sports view
- Detects balls and players with configurable framing
- Offers desktop app, CLI, library, and OBS plugin
- Supports GStreamer, OBS, and live streams
- No telemetry or usage-data collection
Against
- iOS and Android implementations are not ready
- AGPL-3.0-only license applies
- No public paid tier is available
The verdict
Reco provides a local, open-source route to panoramic sports production with several integration options. Mobile support remains unfinished, so current use centers on listed desktop and hardware targets.
Who it suits
Reco suits coaches and parents creating panoramic sports views, hardware builders, and developers embedding the engine. It is also relevant to users who want local processing and OBS or live-stream workflows.
Plans and prices
Free and open source
Desktop app, CLI, Rust library, OBS plugin · two-camera panoramic sports filming · local processing
Read 15 Oct 2026 · github.com
On the record
- AI tracking
- AI tracking detects balls and players and applies automatic camera movement with lookahead smoothing.github.com · read 15 Oct 2026
- API and extensibility
- The Rust engine exposes StitchCore frame-submission methods and reusable library crates for applications and plugins.github.com · read 15 Oct 2026
- App and tools
- The project offers a desktop app, CLI, library, and OBS plugin built on the same engine.github.com · read 4 Oct 2026
- Architecture
- The repository is split into nine Rust crates covering core rendering, I/O, detection, autocamera logic, calibration, controls, CLI, GUI and OBS.github.com · read 15 Oct 2026
- Build requirements
- Building requires Rust 1.92 or newer, FFmpeg development libraries, pkg-config and Clang.github.com · read 15 Oct 2026
- Calibration
- Automatic calibration uses AKAZE feature matching, IMU or audio cross-correlation for synchronization, and Gyroflow lens profiles.github.com · read 15 Oct 2026
- Camera calibration
- Automatic calibration uses AKAZE feature matching and IMU or audio cross-correlation for temporal sync.github.com · read 4 Oct 2026
- Command line interface
- The CLI supports calibration, stitching, preview, camera capture, analysis and information commands.github.com · read 15 Oct 2026
- Commercial licensing
- The repository says commercial licensing questions should be directed to the maintainer and that no public paid tier exists.github.com · read 15 Oct 2026
- Community size
- The GitHub repository showed 56 stars, 19 forks and five watchers when opened.github.com · read 15 Oct 2026
- Company identity
- The public repository identifies the project under the reco-project GitHub organization and does not publish a legal company name, headquarters or founding year.github.com · read 15 Oct 2026
- Desktop application
- Reco provides a Slint desktop application with GPU preview and export controls.github.com · read 15 Oct 2026
- Detection backends
- Detection supports ONNX Runtime on CPU, CUDA and CoreML, NCNN, and native TensorRT engines.github.com · read 15 Oct 2026
- Documentation
- Documentation consists of README quick-start commands, build instructions, feature flags, generated Rust-doc guidance, contributing rules and a community forum.github.com · read 15 Oct 2026
- GPU support
- The renderer uses wgpu with Vulkan, Metal and DirectX 12 backends and is described as achieving more than 500 frames per second on modern desktop GPUs.github.com · read 15 Oct 2026
- Hardware
- The project lists Linux, macOS, and Windows desktops, NVIDIA Jetson Orin, and cloud workers as supported targets.github.com · read 4 Oct 2026
- Hardware decode
- Zero-copy decoding is available through NVDEC on Linux and Windows and VideoToolbox on macOS.github.com · read 15 Oct 2026
- Intended users
- The website presents Reco for coaches and parents, hardware builders, and developers embedding the engine in their own tools.reco.cam · read 4 Oct 2026
