![\"dario](\".github/readme/hero.jpg\")
\n\n# `dario`\n\n### Your Claude and ChatGPT subscriptions each work in exactly one place.dario makes them work **everywhere** — at subscription pricing, not per-token API bills.\n\n
\n ![\"npm](\"https://img.shields.io/npm/v/@askalf/dario?color=6f42c1&label=npm&logo=npm\")
![\"Latest](\"https://img.shields.io/github/v/release/askalf/dario?color=6f42c1&label=release&logo=github\")
![\"CI\"](\"https://github.com/askalf/dario/actions/workflows/ci.yml/badge.svg?branch=master\"){kind=icon}
\n ![\"CodeQL\"](\"https://github.com/askalf/dario/actions/workflows/codeql.yml/badge.svg?branch=master\"){kind=icon}
\n \n
\n
![\"License\"](\"https://img.shields.io/npm/l/@askalf/dario?color=6f42c1\")
![\"GitHub](\"https://img.shields.io/github/stars/askalf/dario?color=6f42c1&logo=github\")
![\"Downloads\"](\"https://img.shields.io/npm/dm/@askalf/dario?color=6f42c1\")
![\"Node](\"https://img.shields.io/node/v/@askalf/dario?color=6f42c1\")
\n ![\"Claude](\"https://img.shields.io/badge/dynamic/json?url=https%3A%2F%2Fraw.githubusercontent.com%2Faskalf%2Fdario%2Fmaster%2Fsrc%2Fcc-template-data.json&query=%24._version&prefix=v&label=tracks%20Claude%20Code&color=8b5cf6\"){kind=icon}
![\"Daily](\"https://github.com/askalf/dario/actions/workflows/cc-billing-classifier-canary.yml/badge.svg\"){kind=icon}
\n ![\"Hourly](\"https://github.com/askalf/dario/actions/workflows/cc-drift-watch.yml/badge.svg\"){kind=icon}
\n ![\"Live](\"https://github.com/askalf/dario/actions/workflows/cc-drift-template-watch.yml/badge.svg\"){kind=icon}
\n
One local endpoint. Every AI tool you own. The subscriptions you already pay for.
\n\nnpm i -g @askalf/dario · 0 runtime deps · SLSA-attested every release · nothing phones home · ~40k lines you can read in a weekend · independent, unofficial, third-party (DISCLAIMER.md)\n\nStart · Why dario · Routing · Risk · Reference · Trust · Coming back after a while?\n\n![\"Terminal:](\".github/readme/quickstart-dark.svg\")
\n![\"One](\".github/readme/keys.jpg\")
\n\n## What it does with a request\n\nYou point every tool at one URL. dario reads each request, decides which plan or backend owns it, and forwards it in that backend's native protocol.\n\n| Client speaks | Model | Routes to | What happens |\n|---|---|---|---|\n| Anthropic Messages | `claude-*` / `opus` / `sonnet` / `haiku` | Claude pool | OAuth swap + Claude Code template, then `api.anthropic.com` |\n| Anthropic Messages | a slug your ChatGPT account lists | Codex engine | Messages→Responses translation, subscription auth |\n| Anthropic Messages | `gpt-4o`, `llama-*`, any name no plan lists | Refused | `400` + `x-dario-upstream-rejection: model_unroutable`; reach an API-key backend from this shape with a provider prefix |\n| OpenAI Chat | `gpt-*` / `o1-*` / `o3-*` / `o4-*` | OpenAI-compat backend | Auth swap, body forwarded byte-for-byte |\n| OpenAI Chat | a slug your ChatGPT account lists | Codex engine | chat/completions→Responses translation, subscription auth |\n| OpenAI Chat | `claude-*` | Claude pool | OpenAI→Anthropic translation, then the Claude path |\n| Either | `![\"Everything](\".github/readme/trust.jpg\")
\n\n| Signal | Status |\n|---|---|\n| Source | **~40k** lines of TypeScript across **78** files, auditable in a weekend. One credential path since v5: the pool. |\n| Dependencies | **0 runtime.** Verify: `npm ls --production` |\n| Provenance | Every release [SLSA-attested](https://www.npmjs.com/package/@askalf/dario) via GitHub Actions + Sigstore, published with OIDC trusted publishing — no long-lived npm token exists to leak |\n| Scanning | [CodeQL](https://github.com/askalf/dario/actions/workflows/codeql.yml) on every push to master, every PR and weekly · [ClusterFuzzLite](./.github/workflows/cflite.yml) fuzzes the SSE translator, the rejection parsers and the cch stamper weekly · [OpenSSF Scorecard](https://scorecard.dev/viewer/?uri=github.com/askalf/dario) and [Best Practices](https://www.bestpractices.dev/projects/13638) badges above are live |\n| Tests | **241 test files** run in parallel by `npm test` on Node 18, 20 and 22; the live e2e / compat / stealth suites have their own entry points. Green on every release |\n| Credentials | Your own subscription tokens, never logged, redacted from errors, `0600` on disk in `0700` dirs |\n| Network | Binds `127.0.0.1` by default; upstream only to configured backends over HTTPS; hardcoded SSRF allow-list; refuses a non-loopback bind without `DARIO_API_KEY` |\n| Telemetry | **None.** No analytics, no tracking, nothing phones home |\n| Overhead | Measured in the open on every PR: [`scripts/bench-overhead.mjs`](./scripts/bench-overhead.mjs) runs a real proxy against an instant upstream beside a bare http server serving the same bytes. On loopback dario adds no measurable p50 wall time over that floor; the CPU per request is the number to watch, and the per-request [timing split](./docs/analytics.md#the-timing-split) shows it live |\n| This README | CI fails if the line count above drifts from `src/` or a link or anchor here stops resolving ([`check-readme-line-count.mjs`](./scripts/check-readme-line-count.mjs), [`check-readme-links.mjs`](./scripts/check-readme-links.mjs)); the TUI screenshots are rendered from the real TUI and the diagrams are briefed art, not screenshots ([how](./scripts/readme/README.md)) |\n\n```bash\nnpm audit signatures\nnpm view @askalf/dario dist.integrity\ncd $(npm root -g)/@askalf/dario && npm ls --production\n```\n\nSecurity reports go to **security@askalf.org**, not a public issue: [SECURITY.md](SECURITY.md). API stability commitments (`@stable` / `@experimental` / `@deprecated`, deprecation cycles): [STABILITY.md](STABILITY.md).\n\n## Deep dives\n\n- [Claude Code wire drift](https://askalf.github.io/dario/drift-feed/) — every change to what Claude Code sends on the wire, as the template watcher observed it; [RSS](https://askalf.github.io/dario/drift-feed/feed.xml) · [JSON Feed](https://askalf.github.io/dario/drift-feed/feed.json)\n\n- [#183 — Modifying Claude Code's system prompt doesn't change billing; stripping its constraints recovers 1.2–2.8× output](https://github.com/askalf/dario/discussions/183)\n- [#68 — dario vs LiteLLM / OpenRouter / Kong AI Gateway (when each wins)](https://github.com/askalf/dario/discussions/68)\n- [#14 — Template replay: why we replay the shape instead of matching signals](https://github.com/askalf/dario/discussions/14)\n- [#13 — Claude Code's request shape, documented](https://github.com/askalf/dario/discussions/13)\n- [#1 — Rate-limit header analysis](https://github.com/askalf/dario/discussions/1)\n- [system-prompt-classifier-study.md](./docs/research/system-prompt-classifier-study.md), the measurements behind `--system-prompt=partial`\n\n## Contributing\n\nPRs welcome. Small TypeScript codebase, zero runtime deps. Architecture, file-by-file map and the review bar in [CONTRIBUTING.md](CONTRIBUTING.md); release mechanics in [RELEASING.md](RELEASING.md).\n\n```bash\ngit clone https://github.com/askalf/dario && cd dario\nnpm install\nnpm run dev # tsx, no build step\nnpm test # 241 files in parallel via test/all.test.mjs\nnpm run e2e # live proxy + OAuth (needs a working Claude backend)\n```\n\nDrift and audit runners, none of them part of `npm test`:\n\n```bash\nnpm run drift:wire # compare a live Claude Code capture against the baked template\nnpm run drift:sdk # Agent SDK / Stainless pin drift\nnpm run audit:tui # drives the real TUI through a fake TTY at 12 geometries\nnpm run check:overage # overage-classifier check against live headers\nnpm run stress # concurrency / queue behaviour under load\nnpm run cch:calibrate # re-derive the billing-tag cch seed for a new Claude Code build\nnpm run readme:assets # regenerate the diagrams and TUI screenshots (README + docs/)\n```\n\nTwo 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](https://x.com/ask_alf) for drift bulletins as they land.\n\n