Technology
Designed at the protocol level, accelerated on the GPU, and extended with AI
Core technology areas where TSoft goes deep
TSoft builds its own AI infrastructure instead of relying on external AI SaaS
Remote Desktop Technology
Designed at the protocol level, accelerated on the GPU
Direct design and implementation at the protocol level
High-performance, low-latency transmission technology
AI / RAG
Search, understand, and respond
Self-built RAG pipeline in operation
Automation
See the screen, make decisions, and execute
ai-crawler, T-Cafe agent runtime
Systems Programming
From kernel to app, built in-house
Virtual HID driver built in-house
Remote Desktop Protocol
Direct design and implementation at the protocol level, achieving high-performance low-latency communication
Kernel Driver
Virtual HID driver built in-house at the KMDF kernel-mode level
Hardware Encoding
Native integration per GPU vendor with direct NVENC/AMF/QSV wrapper implementation
AI/RAG
Self-built RAG pipeline combining hybrid search and LLM pipeline in operation
Browser Automation
Deterministic execution based on Playwright powering ai-crawler and T-Cafe agent runtime
Cross-Platform
Flutter multi-platform supporting iOS/Android/Windows/macOS
TSoft builds its own AI infrastructure instead of relying on external AI SaaS
RAG (Retrieval-Augmented Generation)
rag-serviceAI-powered Q&A service
AI Crawling
ai-crawlerAutomated game news collection
Vector Search
Vector DB-based searchSemantic search
Hybrid Search
Keyword + semantic integrated searchHigh-accuracy information retrieval
LLM Pipeline
LLM-based response generationNatural language Q&A
Protocol-Level Depth
Not just using APIs, but understanding and implementing at the protocol level
Full-Stack Hardware Integration
Direct development of the entire pipeline from GPU encoding to kernel drivers
AI Internalization
Self-built RAG, crawling, and vector search instead of depending on external SaaS
Product Ecosystem Design
Building an interconnected product ecosystem, not isolated products