1.OpenSparX / MasterAgent
Build AI agents that run 100% on-device. Sub-100ms latency on Qualcomm NPU. Zero cloud dependency.
- agent-framework
- ai-agent
- automotive
- edge-ai
- embedded
- iot
- +4 more
Ranked by Attention Score: stars gained over the last 30 complete days
8 repositories by Attention Score · Oct 5, 2026 – Nov 3, 2026 (UTC)
Build AI agents that run 100% on-device. Sub-100ms latency on Qualcomm NPU. Zero cloud dependency.
Loopcut: an AI agent that works inside Blender. A fork of Blender (GPL).
Your agents don’t hand off the work. Kungfu keeps the same Work moving across Codex, Claude, OpenCode, and your own execution surface.
The fastest unified streaming SQL Engine in a single C++ binary. ⚡ Millisecond latency. 100+ GB/s throughput. Continuously compute stateful context from streams, logs, metrics, events, and CDC.
Translated【A common used C++ & Python DAG framework】 A general-purpose, third-party-dependency-free, cross-platform parallel computing framework based on flow graphs, listed in awesome-cpp. Welcome to star & fork & discuss
AI Game Developer for Unreal Engine — MCP plugin (C++ editor plugin + .NET bridge), unreal-cli, connects Unreal Editor to AI agents via ai-game.dev or a local MCP server
An implementation of Actor, Publish-Subscribe, and CSP models in one rather small C++ framework. With performance, quality, and stability proved by years in the production.