01
Multi-pane orchestrator
Any number of PTY panes — zsh + claude + codex + gemini + aider side-by-side.⌘N adds,⌘B broadcasts to many panes at once.
v0.2 · macOS · Linux · WindowsMIT core · BYOK
Any LLM.One memory.Your keys.
Furx is a terminal orchestrator for the four AI CLIs that matter — Claude Code, Codex, Gemini, Aider — and any OpenAI-compatible endpoint. Council Mode dispatches one prompt to as many models as you wire up. Voice to the active pane. Mobile remote. Memory shared across panes.
BYOK pure. Keys live in your OS keychain; provider calls go straight from your machine to the provider, not through us. What we never collect →
1 / 3 · auto-rotate every 7s
hover to pause
"Dispatch many. Watch them disagree. Ship the winner."
— Council Mode · the only correctness signal that's cheap
What Furx does, exactly.
— 03 primitives02
Council Mode ⌘J
One prompt fanned out to many LLM families in parallel. Diff returns side-by-side. Pick a winner with a number key. Cost shown before dispatch.
03
BYOK pass-through
Keys live in your OS keychain. Calls go straight from your machine to the provider. Audit log is local SQLite, append-only by DDL trigger.
Council Templates by phase.
— Free + ProThe five built-in presets pick voices by provider type (OpenRouter Quick / Free Tiers / Paid / Local / Mix). Templates pick voices by workflow phase— so the Council you fire matches what you're actually doing.
| Template | Default voices | Best for |
|---|---|---|
| Planning | Opus · GPT-5 · Qwen-235B · DeepSeek-V3.1 | Spec, architecture, high-level decisions. Heavy reasoning, time-tolerant. |
| Implementation | Sonnet · Codex · Gemini Flash · Aider | Diff & code generation. Speed and code focus. |
| Review | Opus · GPT-5 · Gemini Pro · Llama-4 | PR review, audit. Diverse families for cross-family blind spots. |
| Debug | Sonnet · Codex · Aider · local qwen-coder | Stack-trace aware. Cloud + local mix to keep velocity. |
| Refactor | Gemini 2.5 Pro · Opus · GPT-5 | Large codebases. Models with >200K-token context window. |
All templates ship Free. Override the voices, save your own template, or write a YAML config.
Connect whatever you already have.
— 5 pathsThe Furx Connect wizard offers five paths — mix-and-match freely. Furx doesn't manage other people's keys; every call goes straight from your machine to the provider.
OpenRouter Quick Start
1 key · 30sOne key, hundreds of models. Council Mode picks distinct providers from the OpenRouter catalog — Claude, GPT, Gemini, Qwen, DeepSeek, Llama-4 — and dispatches to as many as you wire up.
Free tiers
$0 / foreverSeparate free accounts: Cerebras, Groq, Mistral, SambaNova, Gemini AI Studio, OpenRouter free. Daily quotas vary per provider; Furx orchestrates whatever you connect.
Paid APIs direct
your spendAnthropic, OpenAI, Gemini paid, Cerebras paid, or any OpenAI-compatible endpoint. Your billing, your rate limits, your usage caps. Furx never proxies.
Local inference
$0 · privacyAuto-detects Ollama (127.0.0.1:11434), LM Studio, llama.cpp, vLLM. Council with local-only models = zero bytes leaving your machine.
Proxy / LiteLLM
org governancePaste your org proxy URL. Spend tracking, allow-listing, audit — Furx doesn't care which gateway you use as long as it speaks OpenAI-compatible JSON.
Mix-and-match
Council presetCombine all five. Council dispatches across whichever providers are healthy. Graceful degradation if one voice rate-limits, hard timeout 40s.
What we never charge for.
— in stoneBYOK means your provider spend is yours. Pro pays for cloud sync, session replay, encrypted backups and cost analytics — services we have to host. Everything below is Free, forever, MIT.
- ✓Provider keys (OS Keychain only — Furx can't read them after you store)
- ✓Prompts you send (machine → provider, never via us)
- ✓Responses you receive (same)
- ✓Number of voices in Council Mode (1, 6, 30 — same price: $0)
- ✓Number of panes (open as many as your screen fits)
- ✓Local audit log in ~/.furx/furx.db
- ✓Local Memory Hub (SQLite + FTS5 + Knowledge Graph)
- ✓Skills you write in ~/.furx/skills or ~/.claude/skills
- ✓Voice transcription (whisper.cpp local, never uploaded)
- ✓Mobile bridge (point-to-point WS on your LAN or Tailscale)
Pricing, plain.
See detail →Pass-through means our cost isn't tied to your LLM spend — we charge for the orchestration layer that we host on Cloudflare.
Free
$0
MIT · forever
Pro
$12
/mo · 14-day trial
Team
$30
/seat/mo · 5+ seats
Enterprise
$49
/seat or $2.5k perpetual
FAQ
More →›Do you take a cut of my LLM costs?
Never. Pass-through only. Furx never sees your provider keys — they live in your OS Keychain, sent directly from your machine to the provider. There is no proxy and nothing to mark up.
›What does Pro pay for if not voices?
Cloud sync of your skills, .mcp.json, and Memory Hub backups. Session replay (30 days). Cost Meter Pro with alerts and CSV export. Latency heatmap trends. Encrypted daily backups. Council voice count is unlimited on Free, same on Pro.
›How many LLMs can the Council dispatch to at once?
As many as you wire up. The five built-in presets give you 6 by default with OpenRouter Quick Start, but you can extend any preset or write your own. Free, Pro, Team — all the same.
›What's the trial?
14 days Pro on first install, no credit card. Auto-reverts to Free if you don't convert. The trial unlocks cloud sync and replay; everything you can do offline keeps working.
›Can I self-host Pro/Team?
Enterprise tier ($49/seat or $2.5k perpetual). Self-hosted notarized build, data residency Argentina or EU, source-code escrow via NCC Group.
›Refund policy?
14-day no-questions refund via Paddle MoR. Paddle handles EU VAT, AR Argentina, US sales tax automatically.
F
Trial Pro for 14 days. No credit card.
Install, run the Furx Connect wizard, and dispatch your first Council in five minutes. If you don't convert, you auto-revert to Free — keep everything that doesn't require sync.