Skip to content
RobothecaBeta

Software

GTSAM

By BORG Lab, from github.com/borglab/gtsam (opens in a new tab)

  • Navigation and mapping
  • Library
  • BSD-3-Clause

A C++ library for smoothing and mapping in robotics and vision, built on factor graphs and Bayes networks instead of sparse matrices. It includes MATLAB and Python wrappers.

Open on GitHub (opens in a new tab)

Facts

GitHub stars
3,777read on 6 Nov 2026
Last update
6 Nov 2026Newest commit on develop
Maintenance
Activea commit in the last 90 days
Difficulty
Advanced
Hardware it needs, as the project states it
Requires CMake 3.16 or newer and a C++17-capable compiler: GCC 11, 13, 14 or 15, or Clang 11, 14 or 16 on Linux; Xcode 16 on macOS; MSVC toolset 14.40 on Windows. Boost 1.70 or newer is needed only if its CMake options are enabled. oneTBB and Intel oneMKL are optional.

Checked on GitHub on 6 Nov 2026.

Licenses

Code
BSD-3-Clause (opens in a new tab)

Read by Robotheca from LICENSE (opens in a new tab) and LICENSE.BSD (opens in a new tab) (BSD-3-Clause) at commit ac0c523 (opens in a new tab), on 6 Nov 2026. A license text Robotheca's reader does not know: a person at Robotheca set it on 9 Nov 2026.

Commercial use
Yes

Overview

What it does: Robotheca's summary

  • Implements smoothing and mapping (SAM) using factor graphs and Bayes networks as its computing paradigm.
  • Provides a preintegrated IMU factor based on integration on the manifold, enabled by default in GTSAM 4.
  • Supports optimization with Expressions, which allow efficient automatic differentiation.
  • Offers MATLAB and Python wrappers in addition to the C++ library.
  • Includes optional CUDA linear solvers and optional oneTBB and Intel oneMKL support.
  • Uses CMake to build, with optional unit tests run through a check target.

Written by Robotheca from the project's README (opens in a new tab) at commit 14b00eb, not by its creator.

The README

Read the README on GitHub (opens in a new tab)

Files and versions

Facts read at commit ac0c523

Robotheca read the repository at two versions: the summary at 14b00eb and the facts at ac0c523 (read on 6 Nov 2026).

Robotheca never hosts the code: each link goes to the creator's own page.

Use it

How to install it, in the creator's words: The project's website (opens in a new tab)

Robotheca doesn't review code. Read it before running it.

Robotheca lists software as a reference: nothing is hosted or run here, and every fact links to where it was read.