vLLM Semantic Router is a programmable routing layer that chooses or combines language models for each request in a system using multiple models and types of computing infrastructure. It helps teams route inference by signals such as user preferences, application policies, quality, cost, latency, privacy, and safety requirements. The catalogue skills and instructions support configuring and operating this model-routing system.
Borrowing it
Nothing to install: this file belongs to vllm-project/semantic-router. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/vllm-project/semantic-router/main/AGENTS.mdgit clone --depth 1 https://github.com/vllm-project/semantic-routerWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/vllm-project/semantic-router/agents-md)<a href="https://agentmods.dev/instructions/vllm-project/semantic-router/agents-md"><img src="https://agentmods.dev/badge/instructions/vllm-project/semantic-router/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/vllm-project/semantic-router/agents-md"><img src="https://agentmods.dev/badge/instructions/vllm-project/semantic-router/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00968 | $0.00968 |
| Opus 5.5 | $0.00387 | $0.00387 |
| Sonnet 5.5 | $0.00194 | $0.00194 |
| Haiku 4.5 | $0.00097 | $0.00097 |
Grade A, and why
semantic-router AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 24d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
vLLM Semantic Router agent entry
vLLM Semantic Router is an Envoy ExtProc router for LLM inference. A public entrypoint resolves to an isolated recipe; its signals and projections feed a decision and algorithm, which select a backend and recipe-scoped plugins.
Start here
- Read the nearest
AGENTS.mdonly for directories you change. - Use
tools/agent/docs/change-surfaces.mdwhen a user-visible router contract crosses configuration, runtime, deployment, or documentation. tools/agent/domains.yamlis the single changed-path registry for ownership, minimum checks, CI jobs, images, and E2E profiles.
make impact ENV=cpu CHANGED_FILES="path/one path/two"
make check CHANGED_FILES="path/one path/two"
make verify DOMAIN=<domain> # explicit integration check
make verify PROFILE=<e2e-profile>
make ci-full # complete local PR baseline
Use make harness-check after changing the registry, workflows, harness code,
or these instructions. impact reports facts; it does not select a skill,
prescribe a work loop, or decide when the task is complete.
Repository map
src/semantic-router/: Go router, ExtProc runtime, routing, and APIssrc/vllm-sr/: Python CLI and local stack orchestrationsrc/model-runtime/: model runtime that serves every model the router usesconfig/: canonical configuration, fragments, schemas, and recipesdashboard/: React frontend and Go management backenddeploy/: deployment artifacts and operatore2e/: end-to-end framework and profilestools/: build, development, release, security, and harness toolingwebsite/: public documentation
src/semantic-router/cmd/ contains only the Router process entrypoint and its
lifecycle tests. Authoring commands belong in tools/dev/, calibration tools
in tools/calibration/, benchmark drivers beside their benchmark, and the
browser compiler in dashboard/wasm/. Keep shared Go contracts in the Router
module; tools/make/go-tools.mk explicitly builds, tests, and lints external
Go commands against that module's dependencies.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 24d ago Changed · +6 lines · +97 tokens per session 0b6fb15b6df4
- 1mo ago Changed · -10 tokens per session 14a7d16a13c3
- 1mo ago Changed · +9 lines · +127 tokens per session 01d5597082c8
- 1mo ago Changed · +1 lines · +21 tokens per session c4598aa12175
- 1mo ago Changed · -20 lines · -1,313 tokens per session 15bee1dd6658
- 2mo ago Changed · +1 lines · +53 tokens per session 9e78f7e6d76a
- 2mo ago First seen · 87 lines · 1,993 tokens per session scan A 54240a3e2840
semantic-router AGENTS.md is an instructions file published in the GitHub repository vllm-project/semantic-router (6,402 stars, last pushed yesterday), licensed Apache-2.0. It adds 968 tokens to every session, about $0.0039 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
semantic-router AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| semantic-router AGENTS.mdvllm-project/semantic-router | Instructions file | 6.4k | yesterday | Apache-2.0 | A | 968 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |