llm-routing repositories

Trending repositories tagged llm-routing, ranked by trending score. Updated daily.

  1. 1
    katanemo/plano

    Plano is an AI-native proxy server and data plane for agentic apps. Smart LLM routing, observability, agent orchestration, and guardrails so you stay focused on your agents core logic.

    GitHub · Rust · 7,118 stars · 499 forks · +19 stars in 24 hours · Trending score 2.28

  2. 2
    mozilla-ai/otari

    Open-source AI gateway you run yourself. One endpoint for 40+ providers, with virtual keys, budgets, and usage tracking.

    GitHub · Python · 959 stars · 141 forks · +6 stars in 24 hours · Trending score 1.98

  3. 3
    angel291592/Intent-Router

    Intent compiler for AI agents — converges vague requests into typed IntentSpec contracts (probe, ask, or halt before routing), the input layer for routers and typed-decision models like Jev & Laya

    GitHub · Python · 108 stars · 21 forks · +13 stars in 24 hours · Trending score 1.92

  4. 4
    Singularity-Compute/super-decider

    Decisions, not essays: a choice, a yes or no, or a score with a calibrated probability. Open weights, Jev-compatible API, adaptive thinking.

    GitHub · Python · 19 stars · 0 forks · +10 stars in 24 hours · Trending score 1.64

  5. 5
    Inebrio/Routerly

    Self-hosted LLM gateway that routes requests across AI providers (OpenAI, Anthropic, Gemini, Mistral, Ollama) using intelligent multi-policy scoring — including an LLM-native routing policy. Drop-in compatible: just swap the base URL. No database required, built-in cost tracking, budget enforcement and multi-tenant isolation.

    GitHub · TypeScript · 111 stars · 17 forks · +7 stars in 24 hours · Trending score 1.48

  6. 6
    lawrence3699/jev-style

    JevStyle: local decision models for AI agents. Classify, route and score with a probability per option. systemone-compatible local server, MCP tools, Claude Code guard. Open weights, Apache-2.0.

    GitHub · Python · 138 stars · 4 forks · +1 stars in 24 hours · Trending score 1.47

  7. 7
    hussi9/skill-router

    Skill + Agent + Model + Thinking depth — auto-routed before any tool fires. One SKILL.md for Claude Code. 90% routing accuracy, per-step model enforcement, 30%+ savings on multi-step chains.

    GitHub · Python · 38 stars · 1 forks · +7 stars in 24 hours · Trending score 1.37

  8. 8
    pvjbuilds/delegate-router

    Claude Code and Codex CLI skill: an LLM router that delegates bulk, already-decided coding tasks to another model you already pay for (GPT via Codex, Gemini via agy, a Claude Opus subagent), on another subscription first. Benchmark-checked routes, cost per task measured on a bench, cross-model review. The host verifies every diff.

    GitHub · Python · 43 stars · 9 forks · +1 stars in 24 hours · Trending score 0.99

  9. 9
    GoSlowPoke168/openrouter-free-model-proxy

    Lightweight OpenAI-compatible proxy for OpenRouter's free models. Automatically routes to the best available free (privacy-first) model with seamless failover.

    GitHub · Python · 8 stars · 0 forks · +3 stars in 24 hours · Trending score 0.93

  10. 10
    LAMDA-Model-Reuse/RouteFM

    Official implementation of “Pretrain Once, Route Anywhere: Towards a Foundation Model for LLM Routing” (arXiv:2609.37362).

    GitHub · Python · 11 stars · 0 forks · +3 stars in 24 hours · Trending score 0.93

  11. 11
    kalibr-ai/kalibr-sdk-python

    Stop overpaying to run your agents. Kalibr routes every request to lower-cost model and tool paths without degrading performance.

    GitHub · Python · 34 stars · 3 forks · +3 stars in 24 hours · Trending score 0.91

  12. 12
    0xNyk/council-of-high-intelligence

    Structured multi-perspective deliberation for hard decisions. Run full councils, focused triads, or duo debates across Claude Code, Codex, Gemini CLI, and OpenCode.

    GitHub · Shell · 4,874 stars · 457 forks · 0 stars in 24 hours · Trending score 0.85

  13. 13
    LAMDA-Model-Reuse/ORBIT

    ORBIT: A Unified Toolbox for LLM Routing. Unified LLM/model routing, cost-aware inference, multimodal benchmarks, and reproducible evaluation. Accepted by Frontiers of Computer Science (2026).

    GitHub · Python · 19 stars · 1 forks · +2 stars in 24 hours · Trending score 0.72

  14. 14
    CommonstackAI/TwinRouterBench

    Per-step LLM routing benchmark with 970 static labels, live SWE-bench evaluation, an open data pipeline, and a public leaderboard.

    GitHub · Python · 36 stars · 4 forks · 0 stars in 24 hours · Trending score 0.72

  15. 15
    Das-rebel/a3m-router

    ⚡ Adaptive multi-model LLM router — 80+ providers, pheromone-trail failover, parallel ensemble, semantic cache. Cuts AI costs 90%. Drop-in OpenAI proxy. Self-hosted.

    GitHub · TypeScript · 18 stars · 6 forks · +1 stars in 24 hours · Trending score 0.63

  16. 16
    ankitvirdi4/awesome-llm-cost

    Tools, libraries, papers, and patterns for reducing the cost of running large language models in production.

    GitHub · 14 stars · 15 forks · 0 stars in 24 hours · Trending score 0.46

  17. 17
    miniLV/Jev-Auto-Router

    Jev Auto Router: turn-pinned model and effort routing for Codex via TypeSafe Jev.

    GitHub · TypeScript · 10 stars · 1 forks · +1 stars in 24 hours · Trending score 0.46

  18. 18
    Akramovic1/jev-pilot

    Let Jev steer Claude Code: the right reasoning effort, subagent model and skill for every prompt. A Claude Code plugin powered by TypeSafe's Jev (OpenRouter / TypeSafe).

    GitHub · TypeScript · 13 stars · 3 forks · 0 stars in 24 hours · Trending score 0.46

  19. 19
    intikhab49/open-jev-typed-decision-engine

    Open reproduction of TypeSafe Jev: a 150M typed decision engine (noul/choice/score in one non-autoregressive pass, calibrated confidence). 0.697 vs Jev's 0.727, 2.5x better calibrated, 4x faster, free. Trains on a Colab T4 in 30 min.

    GitHub · Python · 51 stars · 4 forks · +1 stars in 24 hours · Trending score 0.45

  20. 20
    RouteWorks/RouterArena

    RouterArena: An open framework for evaluating LLM routers with standardized datasets, metrics, an automated framework, and a live leaderboard.

    GitHub · Python · 160 stars · 70 forks · 0 stars in 24 hours · Trending score 0.35

  21. 21
    OpenBMB/EC2-Bench

    EC2-Bench (EC²-Bench): benchmark for edge-cloud collaboration in long-horizon LLM agents — task performance, resource usage & privacy exposure. arXiv 2610.17816

    GitHub · Python · 24 stars · 0 forks · 0 stars in 24 hours · Trending score 0.30

  22. 22
    manomilano/orca-compass

    Smart AI worker routing for Orca. Match agents, models, and reasoning effort to task complexity while optimizing usage across your existing subscriptions.

    GitHub · TypeScript · 7 stars · 1 forks · 0 stars in 24 hours · Trending score 0.30

  23. 23
    surlymochan/swrm

    Distributed heterogeneous agent task dispatcher — claim under lease, return with evidence. Quota-aware routing across Claude, Codex, OpenCode Go and DeepSeek, in isolated git worktrees with hard budgets.

    GitHub · Python · 6 stars · 1 forks · 0 stars in 24 hours · Trending score 0.23

  24. 24
    deltawi/deltallm

    Self-hosted LLM gateway with SSO, audit logs, client access controls, routing, and usage tracking. OpenAI-compatible and MIT licensed.

    GitHub · Python · 21 stars · 5 forks · 0 stars in 24 hours · Trending score 0.21