cosmo-edge
by cosmo-wander-ai (organization)
Production-grade C++ edge AI engine for video analytics and on-device VLM across Sophon, Rockchip RKNN, and x86, with visual orchestration, real-time OSD, events, and reproducible benchmarks. (description from the project’s GitHub page)
Repository facts
- Stars
- 1,802
- Forks
- 311
- Open issues and pull requests
- 21
- Primary language
- C
- License
- Apache License 2.0 (Apache-2.0)
- Owner
- cosmo-wander-ai · Organization
- Created
- Jun 9, 2026
- Last push
- Oct 16, 2026
Topics
Related projects
Projects that share this one’s GitHub topics.
Rank 3,761: NVIDIA-AI-Blueprints/video-search-and-summarization
NVIDIA AI Blueprint for video search and summarization (VSS) is a GPU-accelerated reference architecture for building video analytics agents with real-time verified alerts, visual…
1,931 starsPythonApache-2.0Last push Oct 18, 2026
Rank 4,044: software-mansion/react-native-executorch
High-performance, privacy-first on-device AI inference library for React Native, powered by PyTorch's ExecuTorch runtime
1,766 starsTypeScriptOther licenseLast push Oct 16, 2026
Rank 8,365: NotPunchnox/rkllama
Ollama alternative for Rockchip NPU: An efficient solution for running AI and Deep learning models on Rockchip devices with optimized NPU support ( rkllm )
616 starsPythonGPL-3.0Last push Aug 25, 2026
Rank 9,207: LSH9832/edgeyolo
an edge-real-time anchor-free object detector with decent performance
531 starsPythonApache-2.0Last push Apr 20, 2026
Rank 914: dusty-nv/jetson-inference
Hello AI World guide to deploying deep-learning inference networks and deep vision primitives with TensorRT and NVIDIA Jetson.
9,018 starsC++MITLast push Oct 16, 2025
Rank 8,629: gokayfem/ComfyUI_VLM_nodes
ComfyUI nodes for vision-language models: Qwen3-VL, Moondream 3, Florence-2, SmolVLM2, InternVL, Gemma 3, MiniCPM-V. Plus open-vocabulary detection, SAM2/SAM3 segmentation, video…
589 starsPythonApache-2.0Last push Aug 8, 2026