llm-adaptive
by dylan121322 · dylan121322/llm-adaptive
★ 3 Stars
⑂ 0 Forks
Updated: Aug 14, 2026
MIT
JavaScript
Original language: English
About
Adaptive model routing: per-request complexity classification with automatic provider routing.
Similar plugins
LLM provider adapter that routes model calls through any ACP (Agent Client Protocol) server — Claude Code, Codex, Gemini CLI, Devin and more — with a registry browser, per-server settings UI, lazy aut
★ 0
dsh plugin --profile web add @deepseek-ai/dsh-llm-acpby cdxiaodong
Unified LLM request/response inspector: reasoning-effort tuning, external-think export, traffic & bundle analysis.
★ 3
JavaScript
Aug 15, 2026
dsh plugin --profile web add dsh-llm-inspectorRate-limits LLM requests per provider and per model using a reservation-based token bucket, with queue or reject modes, plus gateway identity rules that rewrite user-agent and inject custom headers.
★ 0
dsh plugin --profile web add dsh-provider-rate-limitRanked subagent delegation: role-based model routing with failover, per-route reasoning effort, model-transparent labels, fork delegation, and a visual route editor.
★ 0
dsh plugin --profile web add dsh-delegation-suiteby fuzz1og
DSH web plugin: per-model thinking-intensity tiers, modalities and gateway compat switches for custom llm-pi-ai providers, edited inside the official Models settings card
★ 0
MIT
JavaScript
Sep 10, 2026
dsh plugin --profile web add dsh-model-capabilitiesby BruceLanLan
Two-tier model routing: a strong tier plans, advises and reviews while a cheap tier implements, with plan-mode-aware auto routing, a high-impact escalation guard, failure auto-escalation, and subagent
★ 6
MIT
JavaScript
Sep 3, 2026
dsh plugin --profile web add dsh-tier-router