Blog · English

Writing about a language for agents

Benchmarks, design decisions and how-tos: automatic HTTPS, installable apps, agentic servers, capability security. Every post is also Markdown — add .md to its URL.

2 results for local-inference

• September 22, 2026

  Run the judge locally with Laya

  The judge slot is a protocol, not a vendor. Since v0.6.27 a Laya checkpoint on disk — ModernBERT, Apache 2.0 — answers whether, choose and rate with no network, no secret and no cost per token, and the same block runs unchanged.

  • judge
  • laya
  • system-one
  • local-inference
  • open-source
• September 22, 2026

  A model you already have, and an architecture you can edit

  Since v0.6.27 the embedded local provider takes the name of a model already in your Ollama or Hugging Face cache — nothing is downloaded — and an architecture is a text file the compiled binary reads, so adding a model no longer waits for a release of ours.

  • local-inference
  • llm
  • gguf
  • engine
  • privacy

RSS · llms.txt