PulseAugur
EN
LIVE 14:56:54

llm-cli-gateway 2.9.0 adds multi-user HTTP access with enhanced security

The llm-cli-gateway has released version 2.9.0, introducing the capability to serve multiple users over HTTP with robust authentication. This update significantly alters the trust boundary by moving from local pipes to a networked port, addressing seventeen security findings from a multi-LLM red-team exercise. The gateway acts as a Model Context Protocol server, wrapping CLIs from five different LLM providers including Claude Code, Codex, Google's Antigravity, Grok, and Mistral. AI

IMPACT Enhances LLM orchestration by enabling secure, multi-user remote access to various models, facilitating collaborative or segmented AI agent tasks.

RANK_REASON This is a software release for a tool that orchestrates multiple LLMs, not a release of a new frontier model or a significant industry-wide event.

Read on dev.to — LLM tag →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

COVERAGE [1]

  1. dev.to — LLM tag TIER_1 English(EN) · Werner Kasselman ·

    Going Remote, Without Going Reckless: Multi-LLM Orchestration and the New Front Door in llm-cli-gateway 2.9.0

    <p>The earlier posts in this series were about what the gateway lets you call (cache-aware spawning across five providers, the Codex review gate, the CLI-versus-API argument) and the one before this was about the parts that do not show up as a tool, the upstream-tracking and the …