TokenSpeed
LLM inference engine optimized for agentic workloads with compiler-backed
Visit lightseek.org ↗What is TokenSpeed?
TokenSpeed is an open-source LLM inference engine designed for agentic workloads like Claude Code and Cursor. It separates the control plane (C++ finite-state machine) from the execution plane (Python), enforcing safe KV cache management at compile time. Key features include a high-performance scheduler, pluggable kernel system supporting heterogeneous accelerators, SMG integration for low-overhead request handling, and one of the fastest MLA implementations for Blackwell GPUs. Built with Claude-code and backed by the LightSeek Foundation.
Momentum
Daily activity over the last 30 days: upvotes, unique visits, new GitHub stars and Hacker News points.
How do we know it's vibe coded?
vibetrend discovered TokenSpeed automatically. Evidence: Trending on gittrend.top: agent files (claude-code) in lightseekorg/tokenspeed. View source.
Similar vibe-coded apps
#1 this weekOpen-source local voice cloning, dubbing, transcription, and audiobook creation
#2 this week
#5 this weekSlash commands and agents for engineers using AI without compromising standards
#6 this week523 free lessons building AI systems from math and first principles
#8 this week
#10 this weekAI-powered design intelligence toolkit for building professional interfaces
Manage teams of AI agents to run your business from one dashboard
Persistent memory for AI agents across Claude Code, Cursor, and MCP clients