Rayline routes Claude Code subagents to on-device and cheaper models
Hi HN, I’m one of the builders of Rayline. Rayline is a Claude Code compatible LLM gateway. It intercepts and overrides claude code’s internal routing and lets you route subagent calls to different models instead. For example, you can run the main agent on Opus, some subagents on cloud-hosted open models, and other subagents on-device. We’ve seen others implement routing for claude code as tools the agent can invoke. In our experience, that doesn’t work well because it requires the main agent to use tokens to think about + call the tools, and LLMs are generally a very inefficient way to make…
Rayline routes Claude Code subagents to on-device and cheaper models launched on June 8, 2026 with 11 votes, #1,225 of 22,647 launches that month and more than 90% of that year's launches.
In plain words
Rayline is a gateway that intercepts Claude Code's internal routing to direct subagent calls to different language models. It allows users to run the main agent on one model while routing individual subagents to cheaper cloud-hosted or on-device alternatives. Unlike tool-based routing approaches, Rayline uses deterministic configuration and optional machine learning to make routing decisions without consuming tokens on the main agent, reducing costs and improving efficiency in multi-agent workflows.
written from the facts on this page · September 2026
From the sources
Rayline builds ARC, the orchestrator model that chooses the model and reasoning effort for every turn — plus Workshop, Arena, and the ARC API.
Rayline builds ARC, the first adaptive intelligence model—routing every turn to optimize cost and quality. ARC selects the model and reasoning effort most likely to succeed at every turn—at the lowest total cost. ARC works behind the API you already use, matching every request to the intelligence it needs. Four working versions of the same idea—compare them, then keep building from the one you choose. Production-ready software from an agent that adapts to the work. Build with ARC directly—or experience it through Raylinefrom rayline.ai
In the maker’s words, at launch
Hi HN, I’m one of the builders of Rayline. Rayline is a Claude Code compatible LLM gateway. It intercepts and overrides claude code’s internal routing and lets you route subagent calls to different models instead. For example, you can run the main agent on Opus, some subagents on cloud-hosted open models, and other…
Does a similar job
all alternatives →
Claude Code and Claude 3.7 Sonnet 2025 · anthropic.com · ▲875Claude Opus 4.7 is Anthropic's most capable generally available model, released April 16, 2026. It outperforms Opus 4.6, GPT-5.4, and Gemini 3.1 Pro on key benchmarks including agentic coding, multidisciplinary reasoning, scaled tool use, and agentic computer use. It is benchmarked below Claude Mythos Preview — which remains restricted to Project Glasswing partners. https://vucense.com/ai-intelligence/ai-tools/claude-opus-4-7...
Smart model routing directly in Claude, Codex and CursorJun 2026 · github.com · ▲216We built a model router that plugs into coding agents (e.g. Claude Code, Codex, Cursor, etc.) and intelligently sends requests to the best model to serve them. Here's a quick demo of running it locally: https://www.youtube.com/watch?v=isKhAyivtfM. At Weave, we write most of our code with AI, and it's been getting more expensive. This came to a head when Opus 4.7 was released and, thanks to its tokenizer changes, our costs shot up. We knew we didn't need Opus for everything but we didn't want to lose out on the intelligence for the cases where you really need it. So we decided…
Fork of Claude-code working with local and other LLM providers2025 · github.com · ▲177
FastRouter.ai22d ago · fastrouter.ai · ▲364Route requests to the right LLM for cost, latency & quality
Skill that lets Claude Code/Codex spin up VMs and GPUsFeb 2026 · cloudrouter.dev · ▲138I've been working on CloudRouter, a skill + CLI that gives coding agents like Claude Code and Codex the ability to start cloud VMs and GPUs. When an agent writes code, it usually needs to start a dev server, run tests, open a browser to verify its work. Today that all happens on your local machine. This works fine for a single task, but the agent is sharing your computer: your ports, RAM, screen. If you run multiple agents in parallel, it gets a bit chaotic. Docker helps with isolation, but it still uses your machine's resources, and doesn't give the agent a browser, a desktop, or a GPU to…
LLM Gateway2025 · llmgateway.io · ▲296I built an OpenAI-compatible LLM gateway that routes requests to OpenAI, Anthropic, Ollama, vLLM, llama-server, SGLang... anything that speaks /v1/chat/completions. Single Go binary, one YAML config file, no infrastructure. It does the things you'd expect from this kind of gateway... semantic routing via a three-layer cascade (keyword heuristics, embedding similarity, LLM classifier) that picks the best model when clients omit the model field, weighted round-robin load balancing across local inference servers with health checks and failover. The part I think is most…
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 21d ago · stillwet.art
PixVerse R2▲381A real-time world model you can explore and change
AI · 30d ago · world.pixverse.video
Source: Show HN post ↗ · launch text quoted in part
Launched alongside, June 2026
the whole month →
Fundraisly▲1,537AI fundraising agent that finds investors and books meetings
AI · Jun 2026 · fundraisly.com
Homebrew 6.0.0▲1,481Today, I’m proud to announce Homebrew 6.0.0. The most significant changes since 5.1.0 are a new tap trust security mechanism, the new faster, smaller, default internal Homebrew JSON API, sandboxing on Linux, better defaults informed by our user survey, many brew bundle improvements, improved performance and initial support for macOS 27 (Golden Gate). Happy to discuss any questions here!
Dev tools · Jun 2026 · brew.sh
Hi HN! I was super frustrated at apps like tiktok and wechat preventing me from saving or downloading the animated gifs, so I made a little tool to turn a screen recording into a slack-sized emoji. Hope you get some value from this!
Life & fun · Jun 2026 · vorpus.github.io
Search 18 years of Hacker News and chart how any topic, tool, or person trended. Overlay terms to compare their rise and fall across 45M posts and comments.
Life & fun · Jun 2026 · hackernewstrends.com