Call MCPs via TypeScript, masquerading as simple TypeScript API. Or package them as cli.

This repository contains various advanced techniques for Retrieval-Augmented Generation (RAG) systems.

First gitlab mcp for you

Open Source Implementation of Alita: Generalist Agent Enabling Scalable Agentic Reasoning with Minimal Predefinition and Maximal Self-Evolution

A beautiful stack trace pretty printer for C++

HybVIO visual-inertial odometry and SLAM system

GNSS-Free drone navigation and localization in the wild

Provide mapping and localization pipelines based on kapture format

graph-theoretic framework for robust pairwise data association

A nonlinear Kalman Filter based ROS package that allows to estimate inertia and geometric parameters of multirotors in-flight and re-estimates them online

An efficient and robust multisensor-aided inertial navigation system with online calibration that is capable of fusing IMU, camera, LiDAR, GPS/GNSS, and wheel sensors. Use cases: VINS/VIO, GPS-INS,…

Gaussian-SLAM: Photo-realistic Dense SLAM with Gaussian Splatting

[ICLR 2024 Oral] Generative Gaussian Splatting for Efficient 3D Content Creation

[3DV 2024 Oral] DeDoDe 🎶 Detect, Don't Describe --- Describe, Don't Detect, for Local Feature Matching

Official repository for the ICLR 2024 paper "Towards Seamless Adaptation of Pre-trained Models for Visual Place Recognition".

Visual-SLAM based on COLMAP API

edition 2 of the slambook

Fast C++ logging library.

State Machine Design in C++ (Compact)

State Machine Design in C++

An experimental web based map display for MAVProxy based on Cesium

Precise localization based on GNSS and IMU.

Chat with your documents on your local device using GPT models. No data leaves your device and 100% private.

The official implementation of CEASC

⚡ A newly designed ultra lightweight anchor free target detection algorithm， weight only 250K parameters， reduces the time consumption by 10% compared with yolo-fastest, and the post-processing is …

⚡ Based on Yolo's low-power, ultra-lightweight universal target detection algorithm, the parameter is only 250k, and the speed of the smart phone mobile terminal can reach ~300fps+

⚡ Based on yolo's ultra-lightweight universal target detection algorithm, the calculation amount is only 250mflops, the ncnn model size is only 666kb, the Raspberry Pi 3b can run up to 15fps+, and …

YOLOv5 Series Multi-backbone(TPH-YOLOv5, Ghostnet, ShuffleNetv2, Mobilenetv3Small, EfficientNetLite, PP-LCNet, SwinTransformer YOLO), Module(CBAM, DCN), Pruning (EagleEye, Network Slimming), Quanti…