borglab/gtsam

Health v2 · maintenance only

Flags: no_license

Adoption not part of the score

3734 stars · 1006 forks observed · 2026-10-09

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

GTSAM is a C++ library implementing smoothing and mapping (SAM) for robotics and vision using factor graphs and Bayes networks as its core computing paradigm. It includes Python and MATLAB wrappers and supports GPU-accelerated linear solvers via CUDA.

Use cases

• estimate robot trajectories from IMU and GPS sensor data
• build SLAM systems with factor graph optimization
• fuse multi-sensor measurements for state estimation
• solve visual SLAM and structure-from-motion problems
• perform incremental smoothing for real-time navigation
• prototype estimation algorithms in Python or MATLAB

When to choose

• you need factor-graph-based state estimation or SLAM in C++ or Python
• you want mature, well-tested algorithms for smoothing and mapping in robotics
• you need Bayes network inference rather than raw sparse matrix solvers

When to avoid

• you need a general-purpose sparse linear algebra library rather than estimation
• you require a stable API on the develop branch, which is pre-4.3 with breaking changes
• you need Windows Python wheels, which are not published

Facets

library · maturity active

machine-learning simulation math sdk robotics computer-vision autonomous-vehicles cpp python windows cross-platform factor-graphs bayes-networks slam sensor-fusion state-estimation smoothing-and-mapping matlab-wrapper cuda algorithms linux macos

Member repositories

For agents

markdown · JSON · MCP: product_card(name="borglab/gtsam")