@omniroute/opencode-plugin

🚀 OmniRoute — The Free AI Gateway

Bring your own provider accounts. This is an estimated aggregate across separately eligible third-party free tiers, not a token grant from OmniRoute. Sign up, obtain credentials where required, and connect the providers you can use; each provider controls its limits, availability, and terms.

Stacking free tiers by hand is painful — dozens of SDKs, dozens of rate limits, and no idea how much you actually have. OmniRoute catalogs 467 free-tier entries across 34 recurring pool keys and computes the token headline from the 17 pools with a published positive monthly budget plus five per-model Groq caps, deduplicated by shared pool. Quotas that only open after a regional identity check (today: ModelScope) are shown apart, +~6M behind regional identity verification, and never summed into the headline. The result stays visible on the dashboard (/dashboard/free-tiers).

Animated summary of the live /dashboard/free-tiers page. Full methodology (pool dedupe, credit tiers, provider terms): docs/reference/FREE_TIERS.md.

_{These figures are re-audited every two weeks against the live catalog and move both ways — a provider ends a free tier and the number drops; a new one lands and it climbs. We publish what the catalog actually computes, never a rounded-up best case.}

🌐 In 67 languages

# After connecting a provider, copy your OmniRoute key from Dashboard → Endpoints:
curl http://localhost:20128/v1/chat/completions \
  -H "Authorization: Bearer YOUR_OMNIROUTE_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"auto","messages":[{"role":"user","content":"Hello!"}]}'

_{auto needs an eligible route. A fresh installation can have no eligible keyless targets, and a keyless provider may reject third-party clients. Providers marked tos: avoid, including Kiro, are excluded from automatic routing by default; connecting an account does not override that setting. See the Free Tiers Guide before choosing a provider.}

_{📦 Copy-paste quickstart scripts for Python, Node.js, PHP, and cURL → examples/quickstart/}

Want to join as an Open Source Friend? These are the companies that back open source and help keep OmniRoute moving — and we say publicly where every token they give us goes. Reach out: diegosouza.pw@outlook.com

Kimi Moonshot AI

Thanks to Kimi (Moonshot AI), our founding Open Source Friend, for backing this project! Kimi is the AI lab behind the open-weight K2 and K3 model families — Kimi K3 delivers a 1M-token context window, native vision and frontier-level coding at a fraction of closed-model prices, and works out of the box with Claude Code, Codex and every coding tool OmniRoute serves. What Kimi's support powers: Kimi's API credits power OmniRoute's AI-validated release pipeline — the merge validation powered by Kimi K3 stage that reviews every pull request before it ships — plus day-to-day feature development. First-class Kimi support ships on both rails: the direct Kimi API (kimi-k3) and the Kimi Code coding plan (OAuth and API key). OmniRoute is also the first Brazilian open-source project in Kimi's support program. Get a Kimi API key with 15% extra credits →

Cheaper Inference cheaperinference.com

Thanks to Cheaper Inference, an OmniRoute Open Source Friend, for backing this project! Cheaper Inference is a cost-ranked gateway that resells 42 frontier models — Claude, GPT-5.x, Gemini, Kimi K3, GLM, DeepSeek, Grok and MiniMax — behind one OpenAI-compatible endpoint, routing each request to the cheapest eligible provider without ever charging above the model maker's list price. First-class support in OmniRoute: Chat Completions, the native /v1/responses endpoint, vision, tool calling and 3 image models (grok-imagine, nano-banana-pro, nano-banana-2, reachable as cheaperinference/<model>). Get an API key →

_{Links tagged aff=omniroute are partner links. They fund the project at no extra cost to you.}

_{🎟️ Affiliates Promo — free signup coupons from providers we don't sponsor (click to expand)}

_{This section is for referral/coupon codes only. Sponsored partnerships live in 🤝 Supported by our Open Source Friends above. OmniRoute has no sponsorship or partnership with the providers listed here — these are public coupons anyone can use.}

AgentRouter agentrouter.org

AgentRouter — affiliate signup · $100 free credits on signup (free server, expect higher latency — best for testing, not production). First-class support in OmniRoute since v3.8.50: Chat Completions, the Anthropic-compatible wire format and the OpenAI-compatible path. Available models include claude-opus-4-8, claude-opus-5, gpt-5.6-sol and more. Grab your $100 → ⚠️ Affiliate link — OmniRoute has no sponsorship or partnership with this provider.

_{Know another provider with a generous free signup coupon that benefits OmniRoute users? Open an issue and we'll add it here.}

A combo is a chain of models OmniRoute routes across automatically. If quota runs out, a provider fails, or costs spike, the combo can move to the next eligible healthy model. 🛡️

⚡ Zero-config — just use auto

No combo to create. Set your model to auto (or a variant) and OmniRoute builds a virtual combo from your connected providers, scored live:

🔀 Or build your own — 20 routing strategies

All 20 strategies — mix & match per combo step:

_{The Auto-Combo engine scores every candidate on 16 factors (health, quota, cost, latency, task fit, quality, session availability…) — see docs/routing/AUTO-COMBO.md.}

🧱 Resilience is built in (3 independent layers)

_{📖 Auto-Combo Engine · Resilience Guide}

_{📊 Full methodology & per-feature detail vs 9router, OpenRouter, CLIProxyAPI & LiteLLM → docs/comparison/OMNIROUTE_VS_ALTERNATIVES.md}

💚 Support OmniRoute

OmniRoute is MIT-licensed and maintained in the open. If it saves you time or money, here's how to keep it independent — pick whatever fits you. Sponsorship never affects routing priority; it buys visibility, not ranking.

🇧🇷 PIX — instant, no fees (Brazil)

Key (random): 5d865059-bc44-483a-962d-43ceb80126eb

Pix copia-e-cola:

00020101021126580014br.gov.bcb.pix01365d865059-bc44-483a-962d-43ceb80126eb5204000053039865802BR5922OMNIROUTE CONTRIBUICAO6006BRASIL62070503***630475DD

🐛 Found a bug or have feedback? Open a Discussion.

Developer notes: The project may generate a local .env file during npm install/postinstall for developer convenience. This file is intentionally ignored via .gitignore (see .gitignore) and must never be committed — if accidentally committed, rotate any exposed secrets and remove the file from history. See docs/DEVELOPER-ENVIRONMENT.md for guidance on managing local environment files and secrets.

📡 OmniRoute Radar

The main free-tier headline remains ~1.62B tokens/month from the documented, pool-deduplicated catalog above. Temporary provider signup credits can separately lift the first month to ~2.22B. Radar is an optional, signed catalog overlay for people who want fresher free-model availability between OmniRoute releases; the community catalog and every existing free feature remain free.

Supporters can receive the live catalog and additional provider opportunities. Its separate, mutable ceiling is approximately 3B tokens/month at most, depending on provider availability. That ceiling is not a guarantee: providers can change quotas, eligibility, models, or regions at any time.

Radar is opt-in and GET-only. The OmniRoute client does not upload prompts, traffic, provider configuration, usage telemetry, or local announcement-dismiss state. Learn about eligibility and the current catalog at radar.omniroute.online/planos.

Recent highlights from v3.8.20 → v3.8.53. Full history in CHANGELOG.md.

• ⚖️ quota-weighted routing — the 20th combo strategy skips exhausted accounts, then draws among the rest in proportion to leftover quota ÷ in-flight load, keeping existing conversations pinned. → Auto-Combo
• 🧰 Headless mode — omniroute serve --headless (or OMNIROUTE_HEADLESS=1) runs only the /v1/* proxy engine, with the dashboard and dashboard-only subsystems off. → Headless Mode
• 🔎 Model discovery — /v1/models filters by capability, context, kind and text, and POST /v1/models/query returns a short deterministic shortlist with the same per-key visibility. → API Reference
• 🔑 Per-key routing control — pin an API key to one model or combo with forcedModel, and add or remove a key's models and combos atomically (/api/keys/{id}/access). → API Reference · OpenAPI
• 🛡️ Finer PII controls — per-type selection, up to 20 validated custom masking patterns and per-type detection counters; masking itself stays opt-in. → Guardrails
• 🌍 67 languages — dashboard, docs mirrors and CLI, with npm run i18n:add-locale adding a language everywhere in one command. → i18n Guide
• 🎛️ OmniConductor — inbound A2A delegation to your agent fleet, Conductor skills on the Agent Card, and a dashboard panel with Faro push-to-talk voice chat. → A2A Server
• 🛂 Adaptive admission & overload protection — heavyweight chat requests queue instead of 503ing, with atomic RPM rolling leases per connection. → Resilience Guide
• 🗂️ Canonical /v1/models ordering — one contiguous provider-grouped block per provider (combos pinned first), stable across every catalog source. → API Reference
• 🗜️ Compression hardening — default-on inflation guard, Caveman packs for DE / FR / JA + Chinese (wényán), RTK filters for Gradle & .NET. → Compression
• 💸 Honest flat-rate cost — subscription / coding-plan providers read $0 in cost analytics; budget, quota & routing keep estimating. → API Reference
• ⚖️ Quota-Share routing — split a shared account's quota fairly across pooled keys, work-conserving so idle slices are lent out. → Resilience Guide
• 🤖 One-command CLI/agent setup — 15 registered setup-* commands; omniroute run launches 7 CLIs (Claude Code, Codex, Aider, Goose, OpenCode, Qwen Code, Gemini CLI); omniroute configure supports 11 targets with an interactive provider+model picker and per-context favorites. → CLI Integrations
• 🛰️ Remote mode — drive a remote OmniRoute with scoped tokens (connect / contexts / tokens) + an antigravity OAuth helper for VPS installs. → Remote Mode
• 🧭 Smarter auto-routing — auto/<category>:<tier> combos, Fusion (model panel + judge), task-aware routing, per-request model / mode / USD-budget overrides. → Auto-Combo
• 🗜️ Pluggable compression — 12 composable engines + Compression Studios: LLMLingua-2, two-tier Ultra, omniglyph, per-step fidelity gate, GCF v3.2, drag-reorder editor. → Compression
• 🕵️ Transparent MITM decrypt (TPROXY) — capture CLIs that ignore proxy env vars, with a per-SNI CA + trust-store installer. → MITM/TPROXY
• 💸 Cost telemetry everywhere — X-OmniRoute-* cost/usage headers on every endpoint, cache-HIT savings header, per-key USD spend quotas. → API Reference
• 🧠 Memory you control — off by default, opt-in int8 vector quantization + typed decay, per-request x-omniroute-no-memory. → Memory
• 🛡️ Security — prompt-injection guard on every LLM route (red-team suite), opt-in credential-masking guardrail (redacts leaked API keys/secrets in both directions), free DuckDuckGo last-resort web search, and an optional OIDC login gate for the dashboard (password login always stays available). → Guardrails
• 🖼️ New endpoints — /v1/ocr (Mistral OCR) and /v1/audio/translations (Whisper-style) round out the media surface. → API Reference
• 🎨 Image / video / audio generation — one API for media: xAI Grok Imagine & Novita AI video, ComfyUI, Magnific, Adobe Firefly, Segmind, and speech providers such as ElevenLabs. → API Reference
• 🌍 Deployment & ops — reverse-proxy basePath, browser-language auto-detect, per-key device tracking, root-less MITM trust, zh-TW localization. → Environment
• 🤝 More providers & agents — cloud agents (Codex Cloud, Cursor, Devin, Jules), Grok Build (xAI) with browser + OAuth login, Ollama first-class card, Claude Opus 5 & Sonnet 5, Kimi official partnership (Code/Web/Moonshot), Zed, Requesty, SenseNova, Yuanbao, Agnes AI… and a refreshed 375-provider catalog. → Providers
• 📡 Routing transparency — every response carries an X-OmniRoute-Decision header naming the strategy/provider/latency that served it, a new cache-optimized combo strategy + Auto-Combo cacheAffinity factor route repeat requests back to the connection holding the cached prefix, and a read-only /v1/auto-combo/{channel}/candidates endpoint exposes an auto/* channel's live candidate pool. → Auto-Combo
• ⚡ Local performance & infra — one-click local Redis, Cloudflare Workers / Deno Deploy relay deployers, Bifrost & Mux as supervised embedded services. → Embedded Services
• 🧩 Also in the box — plugin framework + marketplace, Omni/Agent/GitHub skills frameworks, Obsidian vault integration (22 MCP tools), OpenAI-compatible Batch & Files APIs, semantic response cache, gamification with leaderboards, ACP agent discovery (15 built-in agents), scheduled log export to BigQuery, auto/chaos parallel multi-model fan-out, a Telegram bot bridge, an in-app version manager and LMArena-ELO free-provider rankings. → Docs

🤖 Compatible CLIs & Coding Agents

One config — http://localhost:20128/v1 — and every AI IDE or CLI runs on free & low-cost models.

Claude Code	Codex CLI	Cline	Kilo Code	Zoo Code	Continue
Aider	ForgeCode	jcode	DeepSeek TUI	CodeWhale	OpenCode
Factory Droid	Copilot CLI	Cursor CLI	Smelt	Pi	Grok Build
Hermes Agent	OpenClaw	Goose	Open Interpreter	Warp AI	deyin.ai

＋ also works with · Agent Deck · Kiro · Command Code · Antigravity · Windsurf · AMP · any OpenAI-compatible tool

_{📖 Per-tool setup for all 37 tools (27 CLI Code's + 10 CLI Agents) → docs/reference/CLI-TOOLS.md · 🧩 OpenCode plugin → @omniroute/opencode-provider}

Launch any supported CLI through OmniRoute in one command — no config files written, credentials injected per process, Qwen/Gemini get a throwaway isolated home:

omniroute run claude   --model openai/gpt-5.4          # Claude Code
omniroute run codex    --model glm/glm-5.2             # OpenAI Codex CLI
omniroute run aider    --model glm/glm-5.2 -- --message "reply OK"
omniroute run goose    --model glm/glm-5.2
omniroute run opencode --model glm/glm-5.2 -- run "reply OK"
omniroute run qwen     --model glm/glm-5.2 -- -p "reply OK"
omniroute run gemini   --model glm/glm-5.2 -- --skip-trust -p "reply OK"

# Or pick provider+model interactively and write the tool's own config:
omniroute configure codex          # also: claude opencode qwen aider goose gemini cline continue kilo 5dive

Every command honors the active remote context (omniroute connect <host>), --dry-run previews the exact env/args without executing, and --api-key-env NAME keeps secrets out of your shell history. → CLI Integrations

375 registered providers across the canonical chat, media, search, local, cloud-agent and system collections, including 153 carrying hasFree: true discovery metadata. The chat model registry covers 239 providers / 3,059 distinct provider-model pairs / 1,475 raw model IDs; the separate free-budget catalog has 467 per-model rows, 34 recurring pools and 51 recurring/keyless free-forever providers. These are different denominators by design; definitions and pool-deduped calculations live in the Provider Reference and Free Tiers.

🏢 Every major lab — through one endpoint

OpenAI	Anthropic	Gemini	xAI Grok	DeepSeek	Mistral
Qwen	Meta Llama	Groq	NVIDIA	MiniMax	Cohere
Perplexity	HuggingFace	Together	Fireworks	Cloudflare	Baidu

_{…and 350+ more — every icon resolves live from the dashboard's provider catalog. 📖 Provider Reference}

🆓 Free Forever — $0, no card

OpenCode Zen DeepSeek V4, Nemotron 3 No token cap	Kilo Code Auto-router, Tencent Hy3 Free forever	Requesty GPT-OSS 120B, Nemotron Free forever	SiliconFlow DeepSeek V3.2 / R1 Free tier	Z.AI GLM GLM-4.7 / 4.5-Flash Free forever	Baidu ERNIE ERNIE 4.0 Free forever
Qoder AI Qwen3-Max, Kimi-K2 Unlimited FREE	Pollinations GPT, Llama, Claude No key needed	Cloudflare AI 50+ models 10K neurons/day	NVIDIA NIM GLM, MiniMax ~40 RPM free	Cerebras GLM 4.7, GPT-OSS One-time $5 credit; card required	OpenRouter :free models +$10 → higher RPM

📖 Full machine-readable catalog → docs/reference/PROVIDER_REFERENCE.md

Same app, your machine, your rules. From a global npm install to your phone via Termux.

_{📖 Docker Guide · Desktop · Menu-bar tray · Termux · PWA · OpenCode}

No new sidebar, no new chat UI — every model OmniRoute serves shows up right in the Copilot Chat model picker you already use. Since VS Code 1.122, provider models work without a GitHub sign-in or a Copilot subscription — agent mode, tool calling and vision, for free.

Install the OmniCopilot extension, point it at your OmniRoute server (defaults to localhost:20128), then open Copilot Chat → model picker → Manage Models… → OmniRoute.

From inside the editor: open the Extensions view, search "OmniRoute", click Install — works the same way on both stores. Source, issues and the publishing runbook live at diegosouzapw/OmniCopilot.

_{📖 VS Code Copilot Chat guide — setup, what the picker shows, dashboard-in-a-tab, troubleshooting}

omniroute serve is happiest when it's always on. OmniRouteTray turns that into a set-and-forget menu-bar app for macOS: it starts the server, keeps it alive across reboots, updates it in place, and puts your live token budget one click away — no terminal window left open, no npm install -g omniroute to babysit.

Built with Tauri v2 (a Rust core the size of a rounding error), it ships its own signed Node 24 runtime and manages an app-owned OmniRoute install, so it never fights your global node/bun. It shares your existing ~/.omniroute/ config and database — so it's the same OmniRoute you already run, just with a hat on. 🎩

brew install --cask zoispag/tap/omniroute-tray

_{Prefer a download? Grab the latest .dmg from Releases. Source, issues and build docs live at zoispag/omniroute-tray.
💛 A community project by @zoispag — not an official OmniRoute release.}

_{📖 Authorization · Guardrails · Compliance}

Beyond the server, OmniRoute is a full command-line cockpit with 80+ commands, plus open agent protocols so an AI agent can drive it on its own.

⌨️ A real CLI (not just start)

omniroute               # serve gateway + dashboard (port 20128)
omniroute chat          # interactive TUI chat client (slash: /model /combo /skill /memory)
omniroute setup         # guided first-run wizard
omniroute doctor        # diagnose providers, ports, native deps

🛰️ Remote mode — run the CLI here, OmniRoute on a VPS

OmniRoute on a server? Drive it from your laptop with the same CLI. Log in once with a scoped access token; every command then targets the remote.

omniroute connect 192.168.0.15            # password → scoped token, saved as a context
omniroute models                         # ← runs against the REMOTE server
omniroute configure codex                 # ← picks a remote model, writes a local Codex profile
omniroute tokens create --name ci --scope read   # mint narrower tokens for other machines
omniroute contexts use default            # ← switch back to the local server

Tokens are scoped read / write / admin; process-spawning routes stay loopback-only. _{📖 Remote Mode}

🤝 Connect an agent — and it controls OmniRoute itself

Expose OmniRoute over MCP, A2A, a REST API, webhooks or a remote CLI — any capable agent (or your own code) gets the keys to the whole gateway: routing, providers, combos, cache, compression, memory — autonomously. HTTP endpoints below are served under http://localhost:20128.

# Give Claude Code the full OmniRoute toolset over MCP:
claude mcp add-server omniroute --type http --url http://localhost:20128/api/mcp/stream

_{📖 MCP Server · A2A Server · Agent Protocols}

📖 How it works — pipeline, architecture & savings math

Default stacked combo runs RTK → Caveman. When both act on the same tool/context payload, savings compound:

combined = 1 − (1 − RTK) × (1 − Caveman_input)
average  = 1 − (1 − 0.80) × (1 − 0.46) = 89.2%
range    = 78.4 – 94.6%

Code blocks, URLs, JSON and structured data are always protected by the preservation engine.

Why use many tokens when few tokens do the trick? Every request passes through OmniRoute's compression pipeline transparently — no client changes. It's now a stack of 12 composable engines that run in order and mix & match per routing combo — building on ideas from RTK, Caveman (⭐ 90K+), LLMLingua-2, and Troglodita (PT-BR).

🧱 The 12-engine stack

Engines run in pipeline order; each is independently toggleable and configurable per combo:

Code blocks, URLs and structured data are always preserved byte-perfect. One-click presets combine the engines:

Real example — Standard mode:

Before (69 tokens): "The reason your React component is re-rendering is likely because you're creating a new object reference on each render cycle. When you pass an inline object as a prop, React's shallow comparison sees it as a different object every time, which triggers a re-render. I would recommend using useMemo to memoize the object."

After (19 tokens): "New object ref each render. Inline object prop = new ref = re-render. Wrap in useMemo."

Same answer. 72% fewer tokens. Zero accuracy loss. ✅

PT-BR example — Troglodita mode:

Antes (42 tokens): "O problema é que o componente está re-renderizando porque uma nova referência de objeto está sendo criada em cada ciclo de renderização. Eu recomendaria usar useMemo."

Depois (12 tokens): "Re-render: ref nova cada ciclo (objeto inline recriado). Usar useMemo."

Mesma resposta. ~70% menos tokens. Precisão técnica intacta. ✅

🎚️ Beyond the engines — output styles, the adaptive dial & per-request control

The 12 engines above shrink what goes in. Three more layers shape how, when, and what comes out:

• 🪄 Output Styles (output-axis steering) — inject deterministic, cache-safe response-shaping instructions; combinable, each at lite / full / ultra intensity. Adding a style is a one-line registry entry:
  • Terse prose — drop filler / articles / hedging; keep technical substance exact.
  • Less code — "lazy senior dev" YAGNI: smallest working change, no unrequested scaffolding.
  • Ponytail (lazy senior dev) — climb the YAGNI ladder, fix the root cause, smallest working diff.
  • I have ADHD (action-first) — next action leads, steps numbered, one concrete next step, no preamble.
  • Terse CJK (文言) — classical-Chinese ultra-terse style (locale-gated to zh).
• 🎯 Adaptive context-budget (the dial) — instead of one on/off token threshold, escalate the cheapest, most-lossless engines only as far as needed to fit the model's context window. Policy: reserve-output (default, model-aware) · percentage · absolute. Mode: floor (guarantee fit) · replace-autotrigger (your explicit choice wins) · off (legacy threshold).
• 🎛️ Where compression is decided (precedence, high → low) — per-request x-omniroute-compression header › routing-combo override › active named profile › adaptive / auto-trigger › panel default › off. The applied plan echoes back in the X-OmniRoute-Compression: <mode>; source=<source> response header.

Auto-trigger by token threshold, flip on the adaptive dial, pin a named profile, set a one-off per request, or assign a pipeline per routing combo — whichever fits the workload. An opt-in offline eval harness (npm run eval:compression) scores fidelity vs. savings on a pinned corpus before you promote a change.

📖 COMPRESSION_GUIDE.md · RTK_COMPRESSION.md · COMPRESSION_ENGINES.md

1) Install & run

npm install -g omniroute
omniroute

💡 See npm warn ERESOLVE or peer-dep warnings? They're harmless. Using npm 11 or later? npm may block package lifecycle scripts unless they are allowed. OmniRoute's postinstall (node scripts/build/postinstall.mjs) is required to prepare its native runtime files. Allow the packages named in npm's warning when installing globally. For the package set reported by OmniRoute 3.8.53:

npm install -g --allow-scripts=omniroute,keytar,onnxruntime-node,@parcel/watcher,@swc/core,protobufjs,esbuild omniroute

To reuse this allowlist for future global installs, configure it once, then install normally:

npm config set allow-scripts=omniroute,keytar,onnxruntime-node,@parcel/watcher,@swc/core,protobufjs,esbuild --location=user
npm install -g omniroute

The dependency list can change between releases; if npm reports a different list, use the package names from that warning. Allowing a package permits its install scripts to run. Using Gemini Web or another web-cookie provider? The npm package includes Playwright but not its Chromium binary. See the Playwright Chromium setup note before making the first web-provider request.

Dashboard at http://localhost:20128 · API at http://localhost:20128/v1.

2) Connect an eligible provider using your own account

Dashboard → Providers → choose a provider whose current terms and quota fit your use case → add its API key or complete its account flow. Free tiers may require signup, approval, or a payment method. Review the Free Tiers Guide; keyless availability is not guaranteed, and providers marked tos: avoid are excluded from auto by default.

3) Point your coding tool

Base URL: http://localhost:20128/v1
API Key:  [copy from Dashboard → Endpoints]
Model:    auto            (routes among eligible connections — or choose provider/model)

4) Verify it's working

curl http://localhost:20128/v1/models -H "Authorization: Bearer YOUR_KEY"

You should see your connected models listed. 🎉 That's it — start coding, and OmniRoute auto-routes & falls back for you.

If your client cannot send custom headers, OmniRoute also exposes tokenized compatibility aliases:

OpenAI catalog:   http://localhost:20128/vscode/YOUR_KEY/
OpenAI models:    http://localhost:20128/vscode/YOUR_KEY/models
OpenAI chat:      http://localhost:20128/vscode/YOUR_KEY/chat/completions
OpenAI responses: http://localhost:20128/vscode/YOUR_KEY/responses
Ollama chat:      http://localhost:20128/vscode/YOUR_KEY/api/chat
Ollama tags:      http://localhost:20128/vscode/YOUR_KEY/api/tags

Use these only for clients that cannot attach Authorization: Bearer .... Header auth remains the preferred mode.

📦 More install methods — Docker, source, pnpm, Arch

🐳 Docker

docker run -d --name omniroute --restart unless-stopped --stop-timeout 40 \
  -p 127.0.0.1:20128:20128 -v omniroute-data:/app/data diegosouzapw/omniroute:latest

:latest follows the highest published stable SemVer. It does not track git main. Pin :X.Y.Z for GitOps. See Docker Release Channels.The image pins OMNIROUTE_MEMORY_MB=1024. That is enough for the dashboard and a light chat. Coding agents (POST /v1/responses from Claude Code, Codex, Grok, …) need a much larger V8 heap or the process FATAL ERRORs at ~12 GiB under two overlapping long contexts. Size the container above the heap (native buffers sit outside V8):

docker run -d --name omniroute --restart unless-stopped --stop-timeout 40 \
  -e OMNIROUTE_MEMORY_MB=8192 --memory=10g \
  -p 127.0.0.1:20128:20128 -v omniroute-data:/app/data diegosouzapw/omniroute:latest

Full table: Docker Guide — runtime RAM.

Pre-release Docker channel: diegosouzapw/omniroute:next and diegosouzapw/omniroute:next-web follow the current default release/v* branch. These mutable tags are intended only for testing unreleased fixes and are not supported for production. See Docker Release Channels.

🥟 Bun

Standard bun install and global installation (bun install -g omniroute) are supported via Bun runtime detection:

• Built-in bun:sqlite: OmniRoute uses Bun's built-in bun:sqlite driver when running under Bun, falling back to better-sqlite3 on Node.js or sql.js.
• Automatic Webpack bundler selection in dev: Development (bun run dev) automatically detects Bun and disables Turbopack in favor of Webpack to prevent native V8 binding incompatibilities. Production builds (bun run build) follow OMNIROUTE_USE_TURBOPACK exactly as on Node: Turbopack by default, OMNIROUTE_USE_TURBOPACK=0 to build with Webpack (Dockerfile.bun exposes it as a --build-arg).
• Dedicated Bun Dockerfile: Multi-stage Dockerfile.bun for native Bun production deployments (docker build -f Dockerfile.bun -t omniroute:bun .).

# Install and run with Bun
bun install
bun run dev

🛠️ From source

cp .env.example .env && npm install
PORT=20128 npm run dev

📦 pnpm

pnpm add -g omniroute@latest --allow-build=better-sqlite3 --allow-build=@swc/core && omniroute

🐧 Arch Linux (AUR)

yay -S omniroute-bin && systemctl --user enable --now omniroute.service

🔧 Nix (Flake)

# Using Nix flakes
nix develop
npm run dev

# Or using devbox
devbox run npm run dev

📖 Docker Guide — Compose profiles, Caddy HTTPS, Cloudflare tunnels.

🦭 Podman

# 1. Prepare the bind-mounted data directory
mkdir -p data

# 2. Linux + local rootless Podman only (never a remote Podman Machine client):
podman unshare chown 1000:1000 ./data

# 3. Set the runtime hint, build the local Compose image, and start
echo "CONTAINER_HOST=podman" >> .env
podman compose --profile base up -d --build

On macOS or Windows, Podman uses a remote Podman Machine: skip podman unshare and follow the topology-specific data directory guidance.

📖 Podman Guide — Compose builds, Podman Machine, and Linux/systemd Quadlet setup.

⚡ Faster / leaner install (skip the native build)

The native SQLite engine (better-sqlite3) is an optional dependency, so a global install never blocks on compiling from source: it uses a prebuilt binary when one matches your platform/Node, and otherwise falls back transparently to a pure-JS engine (node:sqlite on Node 22+, else the bundled sql.js WASM) — no build tools required.

To skip the post-install native warm-up entirely (CI, headless, or slow machines). Note: this only skips the native SQLite warm-up step (scripts/postinstall.mjs); the binary-copy/repair hook (scripts/build/postinstall.mjs) still runs normally:

OMNIROUTE_SKIP_POSTINSTALL=1 npm install -g omniroute   # CI=1 also skips it

For the fastest installs prefer pnpm (content-addressed store + hard links — see above). For a dashboard-free, headless runtime use the Docker base profile (above) or the Termux guide. The CLI and the web dashboard are served by the same process on one port, so there is no separate CLI-only package today.

📹 Video Guides

_{Snapshot do painel em 2026-10-18 · Catálogo bruto: YT 1.352 | TT 334 | IG 290 · Frescor (dias): YT 5 | TT 48 | IG 49}

🎬 #1 — Instagram nick_saraev — 3,042,474 views

🎬 #2 — Instagram nnapier7 — 1,454,535 views

🎬 #3 — YouTube Amidia AI & Tech — 794,974 views

🎬 #4 — Instagram theopenstack — 692,419 views

🎬 #5 — TikTok migue.baena — 685,788 views

Ranking completo (URLs canônicas deduplicadas, v > 0, maior alcance):

Métricas canônicas em 2026-10-18: 1.976 vídeos únicos · 20.220.289 visualizações conhecidas (v > 0) · 1.210 canais/perfis por rede. O painel bruto contém 1.976 linhas (YouTube 1.352 = 740 longos + 612 Shorts · TikTok 334 · Instagram 290); nenhuma duplicata restou após a normalização pela URL canônica, que mantém a maior contagem por vídeo. A coleta do YouTube está congelada em 2026-10-13 (quota da API esgotada de 14 a 18/10) e TikTok/Instagram desde 2026-09-02 (sem créditos de coleta); 76 vídeos ainda não têm contagem de views.

🎬 Made a video about OmniRoute? Open an issue or discussion with the link — we'll feature it here.

📘 Getting Started

🔧 Operations & Deployment

🧠 Features & Architecture

🤖 Protocols & APIs

📋 Project & Quality

⭐ Top Contributors

OmniRoute is shaped by a passionate open-source community. These individuals have made exceptional contributions that directly impact the quality, stability, and reach of the project. Thank you.

External contributors by merged pull requests

Rank	Contributor	Merged PRs	~Changed lines
1	maxmad64bis	371	25,326,561
2	HouMinXi	269	13,456,272
3	backryun	210	270,562
4	oyi77	190	411,243
5	pacocartones	174	78,276
6	JxnLexn	151	3,562,936
6	KooshaPari	151	5,972,314
8	rdself	145	80,663
9	RaviTharuma	123	500,065
10	herjarsa	88	230,872
11	hartmark	84	2,849,554
12	jonlwheat2-gif	67	68,548
13	artickc	62	43,502
14	chirag127	52	6,661
15	xz-dev	50	245,976
16	xiaoyaner0201	47	33,626
17	woodsonl	46	809,391
18	rqzbeh	44	147,896
19	QuangBlue	43	13,112
20	MumuTW	40	26,093

_{Census taken 2026-10-18 15:09:09 UTC with live release/v3.8.52 tip 656f01cb43. The paginated GitHub GraphQL census contains 9,191 merged PRs: 3,834 by the repository owner, 229 by Dependabot, 6 by other bots/apps, and 5,122 external PRs from 835 distinct contributors. “Changed lines” is GitHub additions + deletions and includes generated files, lockfiles, catalogs, translations and documentation; it is churn, not authored LOC. 49 PRs report GitHub diffs above 500,000 lines (for example #13399, a single provider addition, lists 2,347 changed files), which inflates several totals above. Ties are ranked together.}

GitHub-attributed commits

Dizzle 🥇 367 GitHub-attributed commits	Bob.Hou 🥈 269 GitHub-attributed commits	Paijo 🥉 229 GitHub-attributed commits	backryun 🏅 202 GitHub-attributed commits	Paco Cartones 🏅 174 GitHub-attributed commits	Ravi Tharuma 🏅 126 GitHub-attributed commits
Markus Hartung 🏅 114 GitHub-attributed commits	Randi 🏅 108 GitHub-attributed commits	Jan Leon 🏅 87 GitHub-attributed commits	Chris 🏅 70 GitHub-attributed commits	Koosha Paridehpour 🏅 68 GitHub-attributed commits

_{Rechecked at 2026-10-18 14:44:45 UTC: GitHub-attributed commits reported by the repository Contributors API for the release/v3.8.52 default branch. The API returned 849 identities (429 users, 2 bots, 418 anonymous); this table excludes the maintainer, bots and anonymous identities and retains competition ties. It is distinct from both the merged-PR ranking above and the Git-metadata census below.}

🙏 These contributors' features, bug fixes, and infrastructure improvements are a core part of what makes OmniRoute reliable and feature-rich. Every pull request, every test case, and every i18n translation file matters. Open source is built by people like them.

💖 Sponsors

A heartfelt thank-you to the people who fund OmniRoute out of their own pocket — every contribution keeps the project free, independent and moving.

Andrew 💛 Active monthly sponsor	Vlad I 💛 Active monthly sponsor	小妍儿 💛 Active monthly sponsor	Guilherme Costa 💛 Active one-time sponsor	Henrique Iurkiv 💛 Active one-time sponsor	Somesh Ghaturle 💛 Active one-time sponsor
Kolonie AI 💛 Past one-time supporter	Prof. Igor Morais 💛 Past one-time supporter	Pixma 💛 Past one-time supporter	Paco Cartones 💛 Past one-time supporter	longtao 💛 Past one-time supporter

_{… and others who prefer to stay private 💛}

_{Public GitHub Sponsors revalidated on 2026-10-18 through the GitHub Sponsors GraphQL API: 11 public sponsorships (6 active, 5 past) out of 14 in total. GitHub's isActive status determines the active labels above; past public one-time supporters remain thanked, and private sponsors remain anonymous. Ko-fi, Buy Me a Coffee, Liberapay, PIX and crypto donations are not listed because they have no public sponsor record.}

💖 Become a sponsor → — every dollar keeps OmniRoute free and independent.

_{Audited on 2026-10-18 at live release/v3.8.52 tip ad160ab2d1 (6,826 commits): 993 normalized human Git identities — 707 appear as commit authors (including the maintainer) and 286 only in explicit Co-authored-by trailers. The census applies .mailmap, compares e-mail addresses case-insensitively, joins numeric and plain GitHub noreply addresses only when they encode the same handle, excludes 26 bot/agent/service/placeholder identities, and does not merge ordinary e-mail addresses merely because their display names match. The 2026-08-24 audit published 639; this method re-run on that audit's base ac02c5b42f gives 619, so the increase comes from new contributors, not from a looser method.}

How to Contribute

1. Fork the repository
2. Branch from the active release/vX.Y.Z tip (not main) — see Branching & Release Model
3. Create your feature branch (git checkout -b feat/amazing-feature)
4. Commit your changes (git commit -m 'feat: add amazing feature')
5. Push to the branch (git push origin feat/amazing-feature)
6. Open a Pull Request with base = that release/vX.Y.Z branch

See CONTRIBUTING.md for detailed guidelines.

Releasing a New Version

# Create a release — npm publish happens automatically
VERSION=x.y.z
gh release create "v${VERSION}" --title "v${VERSION}" --generate-notes

📊 Stars

🌍 StarMapper

🙏 Acknowledgments

OmniRoute stands on the shoulders of giants. It started as a fork of 9router and a TypeScript port of the Go project CLIProxyAPI — and from there, every subsystem below was inspired by an open-source project that got there first. Each one shaped a concrete piece of OmniRoute. This is our thank-you to all of them. 🙏

⭐ star counts verified from GitHub's REST API on October 18, 2026 — go give these projects a star. Counts are an exact dated snapshot and will naturally change.

🧬 Lineage & gateway

Project	⭐	How it inspired OmniRoute
9router	31,004	The original project this fork is built on — extended here with multi-modal APIs and a full TypeScript rewrite.
CLIProxyAPI	55,591	The Go implementation that inspired this JavaScript / TypeScript port.
LiteLLM	61,482	The AI gateway whose public pricing dataset feeds our cost-tracking sync and whose provider-normalization model informed our routing.
codex-chatgpt-web	14,526	MIT source adapted into the vendored ChatGPT Web → Codex Responses bridge, including browser-session, response-framing, usage and web-search adapters.
free-claude-code	61,430	Patterns ported into stream recovery, no-thinking aliases, fallback web search, sliding-window limits, log redaction and hardened launcher flows.
composer-api	346	Cursor Composer tool-choice, output-constraint and tool-commit patterns adapted into the native Cursor executor.
codex-multi-auth	553	Fresh-login and refresh-token rotation patterns ported into Codex OAuth reauthentication.
opencode-anthropic-auth	558	Claude Code-compatible transform defaults and billing-header behavior generalized into OmniRoute's config-driven bridge.
grok2api-merged	2	Its Grok model mappings, fake-TypeError Statsig generator, request and device defaults, and NDJSON response processor were materially adapted into OmniRoute's Grok Web executor.
TQZHR/grok2api	706	The principal transitive code source behind grok2api-merged; its model, header, payload, Statsig and processor implementations are preserved in the Grok Web lineage.
chenyme/grok2api	7,819	The underlying MIT source for Grok payload and device defaults, the Statsig generator, and the result.response processor carried through TQZHR and grok2api-merged.
grok2api-pro	27	A transitive source credited by grok2api-merged for its proxy-pool layer; OmniRoute preserves that lineage notice but does not claim a proxy-pool port in its bounded Grok Web executor.
GrokProxy	51	Its cookie-authenticated Grok proxy and result.response.token streaming pattern informed OmniRoute's Grok Web transport.
GrokBridge	5	The original Grok Web implementation consulted its HTTP/browser upstream design; its direct HTTP path derives from GrokProxy, so no independent code port is claimed.

🗜️ Context & token compression — engines

Project	⭐	How it inspired OmniRoute
Caveman	113,396	The viral "why use many token when few token do trick" project — its caveman-speak philosophy powers our standard compression mode and 30+ filler/condensation rules.
RTK – Rust Token Killer	83,835	High-performance command-output compression — inspired our RTK engine, JSON filter DSL, raw-output recovery and the stacked RTK → Caveman pipeline.
headroom	75,741	Reversible context-compression (SmartCrusher) — inspired our headroom engine and the ccr retrieve-marker pattern.
LLMLingua	6,757	Prompt-compression research (LLMLingua / LLMLingua-2) — inspired our async, code-safe, fail-open llmlingua engine.
llmlingua-2-js	32	The JS/ONNX port (MobileBERT / XLM-RoBERTa) used as the worker-thread backend for our LLMLingua engine.
Troglodita	50	PT-BR token compression — powers our pt-BR language pack: pleonasm reduction and filler removal tuned for Brazilian-Portuguese grammar.
ponytail	166,731	The viral "lazy senior dev" YAGNI-coder skill — inspired our less-code Output Style: smallest-working-change steering that cuts _generated_ code (the output-axis sibling to Caveman's terse prose).
i-have-adhd	57,628	Its action-first, ADHD-friendly response style was adapted into OmniRoute's concise output style across five languages.

🧩 Compact formats, token research & code-aware tooling

Project	⭐	How it inspired OmniRoute
TOON	25,509	Token-Oriented Object Notation — its columnar, header-plus-rows model shaped our tabular compaction stage.
GCF – Graph Compact Format	59	Its compact graph format and generic-profile design informed OmniRoute's tabular compaction and Headroom codec format.
gcf-typescript	4	The MIT TypeScript implementation directly vendored and extended as the Headroom generic-profile codec.
token-optimizer-mcp	551	Brotli/SQLite cache + per-session context-delta — inspired our session-dedup engine.
token-savior	1,182	Bash-output compaction + MCP profiles — inspired our compression bail-out discipline and MCP tool-manifest reduction.
token-saver	154	Content-aware, per-file-type output compression with failure-aware bail-out — validated our per-type dispatch and minimum-gain skip.
token-optimizer	2,595	"Find the ghost tokens" — its offload + recoverable-handle pattern informed our CCR offload thinking.
TokenMizer	33	A session-graph + cross-turn line-dedup blueprint that informed our session-dedup design.
OmniCompress	3	Rust columnar-JSON + content-addressed retrieve + cross-message dedup — validated our headroom/ccr/session-dedup engine design and the cache-stable "compressed form is position-independent" invariant.
mcp-compressor	133	MCP tool-schema/description compression — informed our MCP tool-manifest cardinality reduction.
RepoMapper	217	Aider-style repo-map ranking — informed our repo-map / retrieval-ranking exploration.
quiet-shell-mcp	4	Declarative shell-output reduction over MCP — validated our declarative bash-output compaction.
ts-morph	6,205	TypeScript Compiler API toolkit — inspired our parser-based comment removal that preserves string, template and regex literals.

🧠 Memory & RAG

Project	⭐	How it inspired OmniRoute
Mem0	67,385	Universal memory layer — its proxy-as-write/read-boundary model shaped our memory architecture.
Letta (MemGPT)	25,179	Stateful agents with tiered memory — inspired our Context Control & Recovery (CCR) tiered model.
WFGY	1,800	The ProblemMap taxonomy of 16 recurring RAG/LLM failure modes — the shared vocabulary in our troubleshooting guide.

🛰️ Traffic inspection, MITM & transparent proxy

Project	⭐	How it inspired OmniRoute
llm-interceptor	79	MITM interception/analysis of coding-assistant ↔ LLM traffic informed early Traffic Inspector requirements. Four previously derived modules — SSE merging, conversation normalization, secret masking and header sanitization — have been replaced by independent clean-room implementations based on public protocol standards. The two host-passthrough surfaces (passthrough.ts and _internal/bypass.cjs) remain OmniRoute-internal implementations classified independently; they were not rewritten as part of that replacement.
ProxyBridge	6,814	Transparent per-process proxy routing — inspired our crash-safe MITM teardown, socket idle-timeouts, /proc process attribution and TPROXY capture.

📚 Model data, observability & UI

Project	⭐	How it inspired OmniRoute
models.dev	7,286	Open database of AI model specs, pricing and capabilities — synced natively into our model catalog.
React Flow / xyflow	38,705	The node-based graph library powering our real-time Compression Studio and Combo/Routing Studio.
LangGraph	43,443	LangGraph Studio's live workflow-graph visualization inspired our Studios' real-time cascade view.
Langfuse	35,990	Its trace → span → generation observability model shaped our Compression Studio waterfall.
Kiali	3,645	Istio service-mesh observability — inspired our circuit-breaker badges and error-edge visuals in the Routing/Combo Studio.
lobe-icons	2,615	AI/LLM brand logos that render the provider icons across our dashboard.
flag-icons	12,473	Provides the MIT-licensed SVG flags used by the README language selector.

🛡️ Security

Project	⭐	How it inspired OmniRoute
awesome-secure-defaults	722	A curated list of secure-by-default libraries that guides our security choices (Helmet.js, DOMPurify, ssrf-req-filter, safe-regex, Google Tink).

🧭 Complementary tools

Project	⭐	How it inspired OmniRoute
ClawRouter	6,628	Inspired request deduplication, emergency zero-cost fallback, pluggable Auto-Combo strategies and multilingual intent classification.
Antigravity-Manager	32,333	Its account-aware model remapping, executable-path validation and plan-label behavior informed OmniRoute's Antigravity runtime.
vscode-antigravity-cockpit	4,850	Its compact quota-reset countdown format inspired the corresponding provider-limit display in OmniRoute.
AionUi	33,611	Its ACP integrations inspired OmniRoute's automatic detection of installed CLI agents.
CodexBar	22,616	Identified the Grok Build quota surface; OmniRoute then verified and corrected the live wire format independently.

📄 License

MIT License - see LICENSE for details.

---

⬆ Back to top · Built with ❤️ for the open-source AI community.

_{OmniRoute v3.8.53 · Node ≥22.22.2 · MIT License · omniroute.online}