Your Claude Pro/Max subscription works in exactly one place: Claude Code.
dario makes it work everywhere — at subscription pricing, not per-token API bills.
One local endpoint. Every AI tool you own. The subscription you already pay for.
npm i -g @askalf/dario · 0 runtime deps · SLSA-attested every release · nothing phones home · ~22k lines you can read in a weekend · independent, unofficial, third-party (DISCLAIMER.md)
v5 is a breaking simplification: two removals, zero feature pile-on.
- 🏊 Pool-as-primitive. Every dario is now a pool. A plain
dario loginis a pool of one; add a second Claude seat and the samelocalhost:3456load-balances across them by live headroom — no mode switch, no config flag.- 🧹 Shim mode removed. The deprecated shim transport is gone. Proxy mode rebuilds every request to Claude Code's wire shape and is strictly better for every client.
Upgrading from v4? Solo
dario login+dario proxyusers: nothing to do. Full notes → MIGRATION.md · CHANGELOG
You're already paying $20, $100, or $200 a month for Claude. Then Cursor wants an API key. Aider wants an API key. Cline, Continue, Zed, your scripts — every one of them bills you again, per token, while the subscription you already bought sits idle in Claude Code.
dario is one local endpoint that routes all of them through the Claude subscription you already pay for. Point any Anthropic- or OpenAI-compatible tool at http://localhost:3456 and you're done. No per-tool config, no second bill.
# 1. Install
npm install -g @askalf/dario
# 2. Log in to your Claude subscription (Pro, Max 5x, or Max 20x)
dario login # or `dario login --manual` for SSH / headless
# 3. Start the local proxy
dario proxy # separate terminal or background
# 4. Point any Anthropic-compat tool at it
export ANTHROPIC_BASE_URL=http://localhost:3456
export ANTHROPIC_API_KEY=darioThat's the whole setup. Every tool that honors those env vars now runs on your subscription.
Works with: Claude Code, Cursor, Aider, Cline, Roo Code, Continue.dev, Zed, Windsurf, OpenHands, OpenClaw, Hermes, Codex CLI, the Claude Agent SDK, your own scripts.
Add other providers and reuse the same proxy:
dario backend add openai --key=sk-proj-...
dario backend add groq --key=gsk_... --base-url=https://api.groq.com/openai/v1
dario backend add openrouter --key=sk-or-... --base-url=https://openrouter.ai/api/v1
dario backend add local --key=anything --base-url=http://127.0.0.1:11434/v1
export OPENAI_BASE_URL=http://localhost:3456/v1
export OPENAI_API_KEY=darioForce a specific backend with a model prefix: openai:gpt-4o, claude:opus, groq:llama-3.3-70b, local:qwen-coder. Prefer Docker? ghcr.io/askalf/dario:latest — multi-arch (amd64+arm64), published every release (guide). Something off? dario doctor prints one paste-ready health report.
Type dario with no args (in another terminal) for a full-screen control panel — live request stream, per-model burn-rate, rate-limit utilization, billing-bucket breakdown, and an in-place config editor that writes to ~/.dario/config.json. Subscription accounting you watch happen instead of reading out of log files. Pure ANSI, zero new runtime deps.
┌─ dario ─────────────────────────────[ q quit · Tab next · ? help ]──┐
│ Status Config ▎Analytics▎ Hits Accounts Backends │
├─────────────────────────────────────────────────────────────────────┤
│ ANALYTICS — last 60 min │
│ │
│ Requests: 247 (4.1/min) Tokens in: 142,830 │
│ Tokens out: 38,200 Subscription %: 98% │
│ │
│ Per-model: │
│ opus-4-8 ████████████░░░░░░░░ 60% (148 req) │
│ sonnet-5 █████░░░░░░░░░░░░░░░ 26% ( 64 req) │
│ haiku-4-5 ███░░░░░░░░░░░░░░░░░ 14% ( 35 req) │
│ │
│ Rate-limit: │
│ 5h ████░░░░░░░░░░░░░░░░░░░░░░░░ 18% │
│ 7d ██░░░░░░░░░░░░░░░░░░░░░░░░░░ 8% │
└─────────────────────────────────────────────────────────────────────┘
| Setup | Monthly cost — heavy user |
|---|---|
| Cursor + Anthropic API direct | $80–$300 |
| Multi-tool heavy use (Cursor + Aider + Cline + Continue), per-token | $200–$600+ |
| Any of the above + dario | $20–$200 flat — your existing Pro/Max plan, nothing extra |
One subscription, every tool. Switching providers is a model-name change, not a reconfigure — add a backend once and the same localhost:3456 speaks OpenAI, Groq, OpenRouter, or a local Ollama too.
You point every tool at one URL. dario reads each request, decides which backend owns it, and forwards it in that backend's native protocol.
| Client speaks | Model | Routes to | What happens |
|---|---|---|---|
| Anthropic Messages | claude-* / opus / sonnet / haiku |
Claude backend | OAuth swap + CC template → api.anthropic.com |
| Anthropic Messages | gpt-*, llama-*, … |
OpenAI-compat backend | Anthropic→OpenAI translation, forwarded |
| OpenAI Chat | gpt-* / o1-* / o3-* |
OpenAI-compat backend | Auth swap, body forwarded byte-for-byte |
| OpenAI Chat | claude-* |
Claude backend | OpenAI→Anthropic translation, then Claude path |
| Either | <provider>:<model> |
Forced by prefix | Explicit override |
The tool doesn't know. The backend doesn't know. dario is the seam.
The full Claude lineup, autodetected. Opus 4.8, Sonnet 5, and Haiku 4.5 — plus [1m] long-context variants — by full id (claude-opus-4-8) or shortcut (opus / sonnet / haiku, append 1m for the long-context form). GET /v1/models reads Anthropic's live catalog (TTL-cached, baked fallback when offline), so a new model resolves the day it lands with no dario release, and the model-specific request shape is applied automatically. Families pulled upstream are filtered from both the live catalog and the fallback so /v1/models never advertises a model that 404s — reversible via DARIO_SUSPENDED_MODELS if a family is ever pulled again.
In v5 every dario is a pool — a plain dario login is a pool of one, no separate mode to switch on. One Claude subscription has a ceiling; hold more than one seat — a personal Max and a work Max, a couple of Pros, team seats — and the same localhost:3456 routes every request to whichever seat has the most headroom, live, per request. A single dario accounts add even bootstraps a servable proxy with no dario login step:
dario accounts add work
dario accounts add personal
dario proxyThree things it does that a round-robin doesn't:
- Per-model headroom routing. Anthropic meters each model family separately — a
5hbucket, a7dbucket, and a per-model7d_<family>bucket. dario reads all of them off every response and routes each request by the bucket that governs it: an Opus call to the seat with Opus room, a Sonnet call to the seat with Sonnet room, independently. Plan tiers mix freely — dario cares about headroom, not tier. - Session stickiness. Claude's prompt cache is scoped to
{account × cache key}, so rotating a long conversation across seats on headroom alone re-pays cache-create every turn — a 5–10× token-cost multiplier on the cached portion. dario pins each conversation to one account (hashed from its first message, deterministic) for the life of the session, and rebinds only when that account is exhausted. - In-flight 429 failover. A seat hits its wall mid-request and dario retries the same request against the next-best account before your client ever sees an error. The sticky binding follows to the new seat, so the next turn doesn't re-select the cold one.
┌─ dario ─────────────────────────────[ q quit · Tab next · ? help ]──┐
│ Status Config Analytics Hits ▎Accounts▎ Backends │
├─────────────────────────────────────────────────────────────────────┤
│ ACCOUNTS — 3 pooled · routing by headroom │
│ │
│ work Max 20x 5h ██░░░░░ 12% 7d ████░░░ 41% ← next opus │
│ personal Max 5x 5h █████░░ 78% 7d ██████░ 88% │
│ side Pro 5h ░░░░░░░ 3% 7d █░░░░░░ 9% ← next sonnet│
│ │
│ sticky bindings: 4 active · 429 failovers (1h): 2 │
└─────────────────────────────────────────────────────────────────────┘
dario accounts {add,list,remove} from any shell, or provision entirely over HTTP with the headless admin API — zero-console Docker / k8s / Pi installs included. Routing internals and the live /accounts + /analytics endpoints: docs/multi-account-pool.md; covered end-to-end by test/pool-e2e.mjs.
During normal operation, a subscriber should never see a single response billed outside their subscription pool. If one is, something is wrong — wire-shape drift, an account misconfig, a change upstream — and forwarding more requests in the same shape either bleeds real money (accounts with extra-usage enabled) or returns a wall of rejections. The first hit is the signal; the rest are damage.
So the moment any upstream response bills to something other than your subscription pool, dario halts the proxy. The check is an allow-list, not a match on one string: anything that isn't a known subscription claim (five_hour / seven_day and their fallbacks) and isn't the unknown no-header sentinel trips it — so a billing bucket dario has never seen still halts. Subsequent requests return 503 with an Anthropic-shaped error body until you run dario resume, press R in the TUI, or the cooldown clears (default 30 min). The halt shows across the TUI, fires a best-effort OS notification, and emits named SSE events. Tune it via ~/.dario/config.json → overageGuard or --overage-behavior=warn / --no-overage-guard / --overage-cooldown=<ms>. (In upstream-API-key passthrough mode — ANTHROPIC_UPSTREAM_API_KEY — the guard is off; api billing is the point there.) Verified end-to-end by test/overage-guard-e2e-live.mjs. Background: #288.
Claude Code's request shape changes between releases — new betas, tool renames, per-model thinking configs — usually with no subscriber-facing note. dario doesn't guess that shape: it captures it live from your own installed claude binary on every startup, diffs it against each upstream release, and replays it byte-for-byte. That's why your subscription routes the same through dario as it does through Claude Code itself — the request that leaves your machine is the shape your plan expects. Details: docs/wire-fidelity.md · #13 · #14.
Keeping that current is the whole job, and it's automated. Three watchers run unattended:
- npm-release drift —
cc-drift-watch.ymlcatches each new Claude Code npm release;cc-drift-auto-release.ymlauto-drafts, merges, and ships within minutes. - Same-binary remote-config drift —
cc-drift-template-watch.ymlruns on a self-hosted runner with a live Claude session (the only place this class is visible) and opens an auto-rebake PR with the diff inline. Anthropic ships changes through Claude Code's remote config, not just npm. - Rate-map drift —
cc-billing-classifier-canary.ymlsends one live request a day and asserts the response still bills to a subscription bucket.
Guarded by a PR-time compat gate that runs the full suite against a live proxy before any wire-shape change merges, and a liveness alarm if a watcher goes quiet. A few recent changes the watchers caught and shipped fixes for, same-day:
| Change (no subscriber-facing note) | Effect | dario shipped |
|---|---|---|
context-1m dropped from the default beta set on the OAuth path |
Subscription requests default to the 200K window on Sonnet/Opus | v3.38.3–4 |
thinking: {type:"adaptive"} gated per-model server-side |
Sonnet/Opus 4-5 400 every request through any proxy | v3.38.5 |
Per-model anthropic-beta sets (opus 9, sonnet 8, haiku 6) |
Proxies sending one set diverge for non-opus models | v4.8.53 |
The full ledger lives in the CHANGELOG. Setup + walkthrough: docs/drift-monitor.md. Residual manual cases — OAuth rotation, runner re-registration — are in the recovery runbook.
On 2026-05-13 Anthropic announced that, from 2026-06-15, Agent-SDK and claude -p (headless) traffic would leave the subscription pool for a small separate monthly credit ($20 / $100 / $200 by plan), then metered API rates. They paused it before that date — those surfaces still bill subscription today, and Anthropic says it will give advance notice before any revised version. Nothing changed; no credits were issued.
The split isn't live, but it was announced once on short notice and could return — so dario is built for it either way. Every request is rebuilt into interactive Claude Code shape before it leaves your machine (and, with --stealth, the response-correlated timing an interactive session has), so your traffic sits in the subscription pool whether a split is paused or live. The daily canary is the tripwire: it surfaces a revived split within a day instead of on a surprise invoice. Verify on your own machine right now — dario doctor --usage fires one request and prints the rate-limit headers; representative-claim should read five_hour or seven_day (both subscription buckets). Full timeline: docs/why-now-2026-06.md.
- Multi-account pool. Several Claude seats behind one endpoint, routed by per-model headroom with sticky-session cache locality and in-flight 429 failover. → Multi-account pool
- Byte-faithful passthrough for real Claude Code. A genuine CC request already is the CC shape, so dario forwards it verbatim — system prompt, tools, thinking, key order untouched — keeping only its billing tag, identity, and cache breakpoints. Covers CC's whole family: the main loop, its Task/Agent sub-agents, and the permission classifier. Non-CC clients get the full template rebuild that keeps them routing. Background: #678.
- Headless admin API (
DARIO_ADMIN=1). Provision and manage pool accounts entirely over HTTP — start with zero accounts,POST /admin/login/start, paste the code back, routable the moment the200lands (live hot-reload, no restart). Token-gated even on loopback, audit-logged, rate-limited. Built for Docker / k8s / Pi. →docs/admin-api.md - Runs any agent. A 64-entry schema-verified
TOOL_MAPpre-maps Cline, Roo, Kilo, Cursor, Windsurf, Continue, Copilot, OpenHands, OpenClaw, Hermes, and hands tool names to CC's native set — no flag, no validator errors. MCP tools (mcp__server__tool) forward verbatim. Compatibility matrix · agent-compat.md. - Behavioral stealth (
--stealth). Adds when a request arrives to what it looks like — response-length-correlated think time and session-start latency. →docs/wire-fidelity.md - VPN / egress routing. Route dario's upstream traffic through a VPN without putting the whole host on one. →
docs/vpn-routing.md - Recover output (
--system-prompt=partial). Strips CC's tone/verbosity constraints for 1.2–2.8× more output on open-ended work, without changing which pool you bill to. #183 ·docs/system-prompt.md - Client-shape overrides.
--honor-client-thinkingpasses a client's ownthinkingblock through unchanged;--preserve-output-formatcarries a client'soutput_config.formatJSON schema through so structured-output SDKs (e.g. the Vercel AI SDK'sgenerateObject) get schema-constrained output. Both off by default. - Reachable from inside CC / any MCP client.
dario subagent installregisters a CC sub-agent for in-session diagnostics;dario mcpexposes dario as a read-only MCP server. →docs/sub-agent.md·docs/mcp-server.md
| Signal | Status |
|---|---|
| Source | ~22k lines of TypeScript across 49 files — auditable in a weekend (v5 removed shim; the pool is the one code path) |
| Dependencies | 0 runtime. Verify: npm ls --production |
| Provenance | Every release SLSA-attested via GitHub Actions + Sigstore |
| Scanning | CodeQL on every push and weekly |
| Tests | 113 test files run in parallel by test/all.test.mjs — green on every release |
| Credentials | Your own subscription tokens, never logged, redacted from errors, 0600 on disk in 0700 dirs |
| Network | Binds 127.0.0.1 by default; upstream only to configured backends over HTTPS; hardcoded SSRF allow-list |
| Telemetry | None. No analytics, no tracking, nothing phones home |
npm audit signatures
npm view @askalf/dario dist.integrity
cd $(npm root -g)/@askalf/dario && npm ls --productiondario uses your own subscription credentials, authenticates you as you, and impersonates nobody. What it changes is the client — it rebuilds each request into the exact shape Claude Code emits (captured live from your installed binary) so your plan routes the same no matter which tool actually sent it. Be clear-eyed on both sides of that: it's a transparency tool, in that it documents request behavior Anthropic doesn't publish for subscribers — and it's also, plainly, running through your subscription traffic that Anthropic's own tools bill differently. Both are true. dario is unofficial and unaffiliated (DISCLAIMER.md); decide with both in view.
Best fit: developers juggling multiple LLM tools and per-tool API keys · Claude Pro/Max subscribers who want their plan usable everywhere, not just in Claude Code · teams running local/hosted OpenAI-compat servers who want one stable local endpoint · Agent SDK users who want subscription routing with zero code change (baseURL: 'http://localhost:3456') · power users wanting multi-account pooling + 429 failover.
Not a fit: you need vendor-managed production SLAs (use the provider APIs) · you want a hosted multi-tenant team platform with dashboards / SSO (dario is a single-owner local proxy) · you want a chat UI (use claude.ai).
dario (TUI) · login · proxy · doctor · accounts {list,add,remove} · backend {list,add,remove} · mcp · subagent {install,status,remove} · usage · config · upgrade · status · refresh · resume · logout · help
Full flag/env reference: docs/commands.md · SDK examples + per-tool setup: docs/usage.md
Does this violate Anthropic's terms? Mechanically, dario uses your existing Claude Code OAuth tokens — it authenticates you as you, with your subscription, through Anthropic's official endpoints. Whether any particular use complies with current terms is between you and Anthropic; consult their terms and your agreement. Independent, unofficial, third-party — see DISCLAIMER.md.
Do I need Claude Code installed?
Recommended, not required. With CC, dario login picks up credentials automatically and the template extractor reads your binary on every startup. Without it, dario runs its own OAuth flow and falls back to the bundled (scrubbed) template snapshot.
Do I need Bun?
Optional, recommended — Bun's TLS ClientHello matches CC's runtime. Without it dario works fine; dario doctor flags the mismatch and --strict-tls hard-fails until resolved.
Can I use dario without a Claude subscription?
Yes. Skip dario login, run dario backend add openai --key=…, and you have a local OpenAI-compat router with no Claude involvement.
representative-claim: seven_day in my headers — am I downgraded?
No. five_hour and seven_day are both subscription billing — different accounting buckets, same mode. overage is the one that flips you to per-token. #1.
Will the billing split break my setup? It was announced, then paused before it took effect — today nothing changed and your traffic still bills subscription. If it returns (Anthropic promised advance notice), dario already rewrites every request to interactive-CC shape, and the daily canary surfaces the change within a day. See The billing split.
Full FAQ: docs/faq.md
- #183 — Modifying CC's system prompt doesn't change billing; stripping its constraints recovers 1.2–2.8× output
- #68 — dario vs LiteLLM / OpenRouter / Kong AI Gateway (when each wins)
- #14 — Template Replay: why we replay the shape instead of matching signals
- #13 — Claude Code's request shape, documented
- #1 — Rate-limit header analysis
PRs welcome. Small TypeScript codebase, zero runtime deps. Architecture + file-by-file map in CONTRIBUTING.md.
git clone https://github.com/askalf/dario && cd dario
npm install
npm run dev # tsx, no build step
npm test # 113 test files via test/all.test.mjs
npm run e2e # live proxy + OAuth (needs a working Claude backend)Two easy ways to help beyond code: star the repo (the clearest signal this is useful), and file drift — open an issue when a rate-limit header flips or a tool that worked yesterday breaks today, and it gets documented in public alongside the fix. Follow @ask_alf for drift bulletins as they land.
| Who | Contributions |
|---|---|
| @GodsBoy | Proxy auth, token redaction, error sanitization (#2) |
| @belangertrading | Billing-classification investigation (#4, #6, #7, #12, #23) |
| @iNicholasBE | macOS keychain credential detection (#30) |
| @boeingchoco | Reverse tool-param translation (#29), SSE framing regression catch, hybrid-tool motivation (#33, #36) |
| @tetsuco | Scrubber path corruption (#35), OpenClaw reverse-mapping collisions (#37), 20x-tier report (#42) |
| @mikelovatt | Silent subscription-drain surfaced via friendly billing buckets (#34) |
| @ringge | --no-auto-detect for text-tool auto-preserve (#40) |
| @earlvanze | OpenClaw tool mappings (#19), OAuth manual override (#47), HTTPS warning (#53) |
dario is an independent, unofficial, third-party project. Not affiliated with, endorsed by, or sponsored by Anthropic, OpenAI, or any vendor referenced here. Provided as-is, no warranty. You are solely responsible for compliance with your subscription's terms, the security of your credentials, and the content you send through the proxy. Not for safety-critical, regulated, or production environments without your own review. Full text: DISCLAIMER.md.
MIT — see LICENSE and DISCLAIMER.md.
dario is the routing layer of Own Your Stack — open tools for owning your AI infrastructure instead of renting it by the token. One subscription. Your box. Your terms.
- dario — own your routing (you are here)
- hybrid — own your inference
- deepdive — own your research
- hands — own your computer-use
- browser-bridge — own your browser
- redstamp — own your agent security
- truecopy — own your agent skills
- strongroom — own your agent secrets
- cordon — own your prompts
- fieldpass — own your agent browser
- amnesia — own your search
- askalf — own your operation: the AI operation that runs Sprayberry Labs
dario is part of Own Your Stack — the open toolkit behind Sprayberry Labs, the software studio with one human on staff — run by askalf, the AI operation these tools are part of.
Built in the open, scars included. Follow the build → @ask_alf · sprayberrylabs.com/own-your-stack
Part of Own Your Stack — own your AI infrastructure instead of renting it. Built by Thomas Sprayberry.