In build since Nov 2024, shipping 1 July 2026

echo.An open Jarvis.On every screen.

An open Jarvis you actually own. Voice, vision, memory, a translucent multi-monitor HUD. Runs on the AI subscription you already pay for. No API keys. No second bill. Cross-platform. Open source.

0
d
00
h
00
m
00
s
Mac · Windows · LinuxVoice loop, sub-secondOpen source · MIT
The three promises

Made and kept.

Echo is built around three non-negotiable rules. Every design choice has to pass all three or it does not ship.

01 · Promise one

No API keys, ever.

Echo runs on whatever AI subscription you already pay for. It speaks to Claude Code, Codex, Gemini CLI, Ollama, anything that ships an official sanctioned channel. You bring your Pro plan. Echo provides nothing else to bill.

ECHO.CONFIGauthorisedclaudesubscriptionprocodexsubscriptionplusgeminisubscriptionfreeollamasubscriptionlocalAPI_KEYnone requiredno bill
02 · Promise two

Local-first by design.

Voice loop, memory store, skills, HUD, everything sits on your machine. No SaaS in front, no proxy in the middle. Your prompts go straight from your keyboard to the brain you authorised, and back. Nothing in between.

YOUR MACHINEechovoice · memory · skillsno SaaSno proxyno brokerno relay
03 · Promise three

The only cost is the one you already pay.

Echo itself is free and open source. The pricing promise is plain. If you have one Pro subscription you have a full Jarvis. If you run Ollama locally, you have a full Jarvis for free. We refuse to add a recurring fee on top.

£/MONTHEcho£0Claude Pro£15Generic AI app£30Enterprise stack£80
voice loopmulti-monitor HUDbrain routerOS keychainMCP skillsmemory across yearsno API keysone Rust corevoice loopmulti-monitor HUDbrain routerOS keychainMCP skillsmemory across yearsno API keysone Rust corevoice loopmulti-monitor HUDbrain routerOS keychainMCP skillsmemory across yearsno API keysone Rust core
What Echo is

A personal AI assistant for grown-ups.

There is no shortage of AI assistant apps. Every one of them either locks you into one provider, sends your data to a server you do not control, charges a second subscription on top of the one you already pay, or breaks the moment a model gets renamed.

Echo is the version that does not do any of that. It is a voice loop, a translucent multi-monitor HUD, a memory store, a proactive scheduler, and a bag of skills that act on your world. It dispatches each prompt to whichever AI brain you have authorised, picking the best fit by capability and remaining quota. When one is exhausted, the next takes over.

The only AI cost is the subscription you already pay. That is the whole premise.

It runs on macOS, Windows, and Linux from one Rust codebase. It uses your OS keychain for every token. It writes its memory as plain Markdown so your data is portable. It is open-source under MIT. It will never have a paid tier. It will never phone home. It is the version of Jarvis you can build today, on hardware you already own.

Bring your own brain

Authorise any AI you already pay for.

One click in the setup wizard. Echo runs the provider's own sign-in check. Your password and token never leave that provider. Echo just dispatches your prompts to whichever brain you authorised.

Claude Code

01 · brain

Subscription

Claude Pro or Max

Channel

claude CLI

Strong at

long reasoning, code, tool use, hooks, long context

Codex

02 · brain

Subscription

ChatGPT Plus, Pro, Team

Channel

codex CLI

Strong at

mixed reasoning, image generation, web search

Gemini

03 · brain

Subscription

Google account or Gemini Code Assist Individual

Channel

gemini CLI

Strong at

web grounding, long-context summarisation, Workspace

Ollama

04 · brain

Subscription

None, runs on your own hardware

Channel

localhost API

Strong at

fully offline, your own models, zero dependence on any cloud

LM Studio

05 · brain

Subscription

None, runs on your own hardware

Channel

localhost API

Strong at

GUI for picking models, same offline freedom as Ollama

Anything else

06 · brain

Subscription

Whatever the provider ships

Channel

New adapter file

Strong at

Brain trait is one file. Add a new provider the week they ship a sanctioned CLI.

Claude ProChatGPT PlusGeminiOllamaLM Studiobring your own brainnever a second billClaude ProChatGPT PlusGeminiOllamaLM Studiobring your own brainnever a second billClaude ProChatGPT PlusGeminiOllamaLM Studiobring your own brainnever a second bill
The pricing promise

Your only AI cost is the subscription you already pay.

A user with Claude Pro

£15 a month

Pay Anthropic for Pro. Authorise Echo to use the claude CLI. Get the full Jarvis-grade voice loop, multi-screen HUD, calendar, mail, vision, memory. No further AI bill, ever.

A user with Ollama

£0 a month

Install Ollama, pick a model that fits your hardware, authorise it as a brain. Echo runs end to end on your own machine. No internet, no provider, no recurring cost.

Why this matters

Most AI assistants make money by reselling API access behind a recurring fee. Echo refuses that model. The user owns the cost path. The result is the cheapest possible Jarvis on the market by structure, not by promotion.

Monthly cost

What you actually pay

£ / month
Echo (the app itself)£0
Echo + Ollama (offline)£0
Echo + Claude Pro£15
Echo + ChatGPT Plus£16
Typical AI-app subscription£25
Enterprise assistant stack£80
Echo never adds a fee. The cheapest path is the path you already had. The most expensive option above is a typical enterprise assistant stack, included for scale only.
Thirty perks

Everything Echo does for you.

The full feature list at launch. Every entry is implementable on the day Phase 8 ships. No vapourware, no maybes.

01

Wake-word voice loop

Say the name. Echo listens. Sub-second turn time on a midrange laptop.

02

Streaming TTS

Sentence-by-sentence playback the moment the brain emits a full clause. No awkward dead air.

03

Brain router

Capability plus quota plus user pins. Always the right brain for the right job.

04

Multi-monitor HUD

Glass card on the primary screen. Dashboard on the second. Ambient brief on a third. Configurable per display.

05

Memory across years

Plain Markdown facts plus JSONL episodes plus sqlite vector index. Survives sessions, machines, restarts.

06

OS keychain auth

Every OAuth token lives in Keychain, DPAPI, or Secret Service. Never on disk in plain text.

07

Vision when asked

Screenshot any monitor on explicit consent. Red dot indicator the whole time. Never silent capture.

08

Calendar awareness

Google, Microsoft, Apple. Read, create, cancel. One-click OAuth per provider.

09

Mail awareness

Triage, summarise, draft. Approval queue in the HUD before anything sends.

10

Music control

Spotify or Apple Music. Play, queue, skip, mood-based selection.

11

Home Assistant bridge

Lights, scenes, temperature, locks. One token, full house.

12

Health glance

Apple Health on macOS, Google Fit on Linux. Read-only by default.

13

Notes integration

Notion and Obsidian. Append, search, link. No vendor lock-in.

14

Code awareness

Watches your repos. Surfaces build failures, open PRs, unresolved review comments.

15

Proactive watches

Cron-style scheduler with quiet hours, focus mode, priority overrides.

16

Multi-step workflows

Borrowed from agent-orchestrator. Plan, run, replay, audit.

17

Single-click OAuth

Local callback server on a random port. Provider auth, then keychain. Done.

18

Local-first storage

Optional disk encryption keyed to OS secure storage. Forget button wipes everything.

19

MCP skill bus

Every skill is a small MCP server. Plugs into Claude Code, Codex, Gemini, anything MCP-aware.

20

Cross-platform shell

Tauri 2. Mac, Windows, Linux from one Rust core. 10MB binary, not 100MB.

21

Pulse animations

Listening, thinking, speaking. The HUD never leaves you guessing what state Echo is in.

22

Keyboard-only mode

Press a chord, type a prompt, read the reply. For meetings, libraries, noisy offices.

23

Subtitle mode

Live captions in the HUD. Big text, high contrast, configurable.

24

Web search skills

Brave, Tavily, SearXNG. Pick yours. Cached locally for repeat queries.

25

Image generation

Through whichever brain supports it on the user plan. Output goes to a local gallery.

26

Local file search

Spotlight, Windows Search, recoll on Linux. One protocol, three OSes.

27

Network audit log

Every outbound call by skill and host, visible in the HUD audit panel.

28

Skill SDK

TypeScript or Rust. Write a skill in an afternoon. Manifest, tools, OAuth scope, done.

29

Quiet hours respected

Outside working hours Echo is silent unless a watch is marked emergency.

30

MIT licensed

Same as every other open-source repo from this studio. No vendor lock-in, ever.

macOSWindowsLinuxone Rust coresigned installersauto updateropen sourceMIT licensedmacOSWindowsLinuxone Rust coresigned installersauto updateropen sourceMIT licensedmacOSWindowsLinuxone Rust coresigned installersauto updateropen sourceMIT licensed
Multi-monitor aware

A different role for every screen.

Echo detects every monitor at startup and on hot-plug. Assign each one a role. The HUD scales with how you actually work.

03 · Ambient
Coming 1 July 2026
12°
Clear, rain at 18:00
SLOWFTSE +0.4%
STEPS8,142
NEXTStandup 9:30
01 · Primary
echolistening14:32
"what is on today"
Standup at 09:30, design review at 11. Rain after 18:00.
NEXT
Standup, 5 min
INBOX
3 unread
BRAIN
claude 234/300
02 · Dashboard
Cal
Mail
Code
Music
Home
Slack
Queue
Draft 3 mail replies
Plan birthday dinner
Architecture

One Rust core, three operating systems.

rendering
Echo end to end. One Rust core. Brain CLIs do the AI work. Skills do the world work. Memory ties it together.
Privacy and security

Local-first means actually local.

OS keychain for every token

Keychain on macOS, Credential Vault on Windows, Secret Service on Linux. Never written to disk in plain text.

Hardware-style mic indicator

Mute means mute. Bypass by skills is impossible. Red dot when capturing screen, always visible.

No telemetry of any kind

No phone-home pings, no anonymous usage analytics, no crash reports unless you explicitly opt in.

Network audit log

Every outbound call by skill and host, queryable from the HUD. You see what Echo is actually doing.

Optional disk encryption

Memory store can be encrypted at rest, keyed to OS secure storage. Toggle in settings.

A real forget button

Wipes session memory and logs with one click. A second button wipes everything Echo has ever stored.

Started Nov 2024, shipping July 2026

Built slowly, shipped honestly.

Started November 2024 in private. Nine phases. Six already shipped, the last three closing now, public 0.1.0 on 1 July 2026.

P0
Done

Repo scaffold

Tauri 2 monorepo, CI for Mac, Windows, Linux. First glass card on the primary monitor.

P1
Done

MVP voice loop

Wake word, STT, brain dispatch, TTS, starter skills. Greets the user when prompted.

P2
Done

HUD polish

Multi-monitor detection, full glass layout, pulse animations, accessibility, subtitle mode, system tray.

P3
Done

Multi-brain router

Claude, Codex, Gemini, Ollama, LM Studio adapters. Scoring policy, user pins, quota awareness.

P4
In flight

Calendar plus mail

Google, Microsoft, Apple. One-click OAuth. Morning briefings. Meeting warnings.

P5
In flight

The senses

Vision, music, notes, tasks, health, home, Slack, news, finance. One skill at a time.

P6
Next

Proactive engine

Cron and watch scheduler with quiet hours, focus mode, watch templates, approval queue.

P7
Next

Autonomous workflows

Multi-step plans, durable orchestration, journal across restarts, multi-day tasks.

P8
1 July 2026

0.1.0 release

Signed installers for all three OSes. Auto-updater. Public docs. Hacker News launch day.

Stack

Boring tech, surgical complexity.

Tauri 2

Cross-platform shell, Rust core, 10MB binary

Rust

cpal for audio in, whisper-rs for STT, native APIs

React 19 + Tailwind v4

HUD windows, same stack as sarmalinux.com

Whisper.cpp

Local STT, runs offline

Piper TTS

Local TTS with OS-native fallback

Porcupine

Wake-word detection, low CPU

MCP stdio

Skill bus protocol, industry standard

sqlite-vss

Local vector store for memory recall

GitHub Actions

Three-OS build matrix, signed installers

A pure passion project

Open by design, yours by default.

Echo exists because the pieces finally do. Voice models that run locally. Brain CLIs that respect a Pro subscription. MCP as a clean skill protocol. Tauri as a real cross-platform shell. OS keychains everywhere.

Built openly because closed assistants always end up renting your attention. Built local-first because your prompts are your business. Built MIT because the next person should be able to fork it on a Tuesday and not owe anyone a thing.

This page exists so the work is visible from day zero. The plan is published. The repo is open. When the launch lands on 1 July 2026, the only news will be that it works exactly as the page already says.

Questions

The honest answers.

Because a normal Pro subscription is meant to be the only AI cost. APIs charge per token on top, with bills that can spike. Echo refuses to put that risk on the user. If a user genuinely needs API access they can use Claude Code or Codex directly with their key set, not Echo.

10 · The invitation

Watch the build,in public.

The repo is the announcement channel. Star it, watch it, read the wiki as the phases ship. No email list, no marketing funnel, no notification spam.

MIT licensedOpen source1 July 2026