anotherCodder
- Karma
- 25
- Created
- 2 years ago
About
Solo engineer. I build memra, an LLM inference engine in Rust and CUDA for RTX Blackwell: https://github.com/avifenesh/memraI also run a hosted inference API on it: https://inference.tiyuvta.ai
Recent Submissions
- 1. ▲ Show HN: Linubot – like Grok bot and Hermes had a kid (github.com)
- 2. ▲ Show HN: Qwen3.8-27B API, 140 tok/s on one GPU (inference.tiyuvta.ai)
- 3. ▲ Bw24 – from scratch rust+CUDA inference, every kernel tuned for sm_120a (github.com)
- 4. ▲ Node.js io_uring over napi-rs, more then 2x performance (github.com)
- 5. ▲ Agent-workspace-Linux An isolated Linux desktop that an AI agent control (github.com)
- 6. ▲ Computer-Use-Linux
- 7. ▲ Glide-mq high performance, features rich, message queue based on valkey glide
- 8. ▲ Show HN: I maintain Valkey GLIDE – built a Node queue doing 48k jobs/s (github.com)
- 9. ▲ Show HN: Agnix – lint your AI agent configs (Claude.md, skills, MCP, hooks) (github.com)
- 10. ▲ Show HN: My way – 18-agent autonomous workflow for ClaudeCode – issues to deploy (github.com)