zdzhaoyong/GSLAM

Health v2 · maintenance only

Adoption not part of the score

1058 stars · 270 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

GSLAM is a general Simultaneous Localization and Mapping (SLAM) framework and benchmark written in C++. It provides a unified plugin-based API so SLAM implementations (feature-based or direct method, using monocular, RGB-D, or other sensors) can be loaded at runtime without recompilation.

Use cases

• build a custom SLAM system on a common framework
• benchmark and compare different SLAM algorithms
• run SLAM with monocular or RGB-D camera input
• load SLAM implementations as runtime plugins
• evaluate SLAM pipelines on standard datasets
• develop robotics localization and mapping research prototypes

When to choose

• you need a unified API to swap between multiple SLAM implementations
• you want to benchmark SLAM algorithms on datasets
• you are developing a SLAM system and want plugin-based distribution
• you work with heterogeneous sensors like monocular or RGB-D cameras

When to avoid

• you need a production-ready, actively maintained SLAM solution with recent updates
• you want a turnkey SLAM application rather than a development framework
• your project requires a license or ecosystem outside BSD-2-Clause C++ tooling
• you need deep learning based SLAM out of the box

Facets

framework · maturity maintenance

simulation computer-vision plugin-system middleware benchmarking robotics computer-vision simulation developer-tools cpp cross-platform slam visual-odometry rgb-d monocular-camera mapping localization benchmark runtime-plugins linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="zdzhaoyong/GSLAM")