Servedeck
Runs local LLMs on one GPU workstation, switching models with one command behind one OpenAI-compatible endpoint, with a live dashboard.
- Projects and tools
- Independent
- Aug 2026 – now
- Live
- short entry
Born as a tool for RL Alpha Labs: systemd units, one /v1 gateway and a dashboard for native vLLM, and it restarts a
model whose engine died, which vLLM's exit code would otherwise hide.
More in projects and tools
- RL Alpha LabsMay 2025 – now
Automated trading on Indian stocks, where a strategy counts only if it beats an index fund after real costs and tax. · Independent · Research
- PorchlampApr 2026 – now
Shows which open-source projects reply to, review and merge a stranger's pull request, so contributors spend their effort where it will land. · Independent · Live
- hostopsOct 2026
Drops a GPU's power limit the second the UPS reports battery, never fails open, and logs every mains cut. · Independent · Published
- flakehoundJul 2026
Static checks that find flaky pytest tests by their pattern, with rules for JAX, PyTorch and NumPy. · Independent · Published