Skip to content

Open-source platform for 3D AI agents. Turn text or a photo into a rigged, animated GLB avatar, give it an LLM brain, memory and a wallet, and embed it anywhere with one web component. Remote MCP server, x402 payments, Three.js, browser-native.

docs(changelog): tell the community the smart home page now speaks their language

nirholasa1e009114ff6
diff --git a/CHANGELOG.md b/CHANGELOG.md
index a67fbc3f3..f90cf8b25 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -8,17 +8,21 @@ Public history for [three.ws](https://three.ws), newest first. New pages come fr
- **Docs · Home households and roles** (`/docs/home-households`): Sharing a connected house without sharing a login: the five roles and what each one may do, per-member entity scopes that narrow the house a member can even see, how invitations are issued and accepted, what happens to somebody's access when they leave, and the rule everything hangs off, that a guest can never confirm an action that opens a building.
- **Docs · Home privacy and retention** (`/docs/home-privacy`): Everything three.ws stores about a home you connect, why, for how long, and what removes it: the full inventory, the promise that room names and device states are never persisted, the 90-day action-log window and the control that changes it, the export and deletion paths, the logging rules, and the disclosure text shown at connect and at the voice opt-in.
+- **Docs · Home security** (`/docs/home-security`): The threat model for a connected house, written about a building rather than a database: what each actor can do and what stops them, why the confirmation gate is the load-bearing control and prompt filtering is depth, the eleven checks that run with every build, the SSRF guard every server-side dial goes through and why a hostname check is not one, the prompt-injection proof that ends by asking a real lock whether it opened, and the residuals accepted on purpose.
- **Docs · three.ws Drive** (`/docs/carplay`): How a three.ws agent rides in the car: the CarPlay entitlement categories measured, why Apple's voice-based conversational category is the one that fits and why it grants no drawing surface, the open-source in-car projects worth adopting and the copyleft ones that are not, and how the /drive surface, the native CarPlay scene, and an open head unit share one implementation.
- **Hands-free voice for your home** (`/voice/home`): Talk to your house without finding a phone: a wake word matched on your own device, real barge-in mid-sentence, and a spoken confirmation that a background yes can never satisfy.
- **Home plan** (`/smart-home/plan`): What your plan covers for connected homes: homes, household seats, live screens, voice minutes and agent turns, each with what you have used and when it resets. Pause and resume which homes are live without disconnecting any of them. Locking up, closing a garage and arming an alarm are never limited.
+- **Join a home** (`/smart-home/join`): Accept an invitation to somebody's connected home. The link says which home it is, exactly what your role would let you do there and what it would never let you do, before you sign in. It works once and it expires.
- **Smart home** (`/smart-home`): Connect a Home Assistant house to your three.ws agent. Your agent reads every room and device, runs the scenes you already built, and stops to ask before it unlocks, opens or disarms anything.
- **three.ws Drive** (`/drive`): Your 3D agent in the car: voice-first, glanceable, and built to the rules CarPlay and Android Auto enforce. Runs on a head unit, a phone in the cradle, or inside the native car shell.
- **Voice satellite** (`/smart-home/satellite`): Give your existing Home Assistant voice assistant a face. Pair a three.ws satellite and the same pipeline you already use gains a 3D agent that lip-syncs its answers and reacts, on any screen in the house. Home Assistant keeps the wake word, the speech recognition and the answer; closing the page never stops the voice working.
+- **A stranger cannot make your agent open your front door**: The home lane now has a written threat model and eleven security checks that run with every build, and the standard they hold is a lock, not a database row. The big fix: the address you give for your house is now resolved and pinned on our side before anything dials it, so a web address that secretly points back into our own network is refused instead of connected to, and it is re-checked every time your house reconnects rather than trusted from the day you added it. A device or integration in your house cannot talk your agent into anything either: we wrote an unlock instruction into a real room name, a real device name and a real scene name, ran a real agent against that house, and the front door stayed locked. Your privacy page is now rate limited like everything else, so nobody can hammer the export or the delete. (`/smart-home`) `[security, improvement]`
- **Connect your house to your agent, and see every way it can go wrong**: The /smart-home page now takes you from "I have a Home Assistant somewhere" to a connected house, and it is honest at every step. An address that only exists on your home network is refused the moment you type it, with the two real ways round it, instead of spinning for fifteen seconds. A rejected token says so and puts the cursor back in the token box. A house that stops answering keeps its rooms on screen, marked stale with how long ago it last replied, rather than blanking out. Your access token is sent once, encrypted at rest, and never comes back to the page: it is not in your browser storage, not in a URL, and not in any response. Disconnecting says plainly that the stored token is erased and reminds you to delete it in Home Assistant too. (`/smart-home`) `[feature]`
- **See, export and delete everything a connected home stores**: Connecting a house to three.ws hands over a key to a physical building, so the answer to "what do you keep, and for how long" is now a page you can read and an endpoint you can call. Every piece of data a connected home creates is listed with why it exists and what removes it, including the parts we deliberately never store: the names of your rooms and devices, their states, and any audio from voice control. There is no record of which lights were on, or when. The log of what the agent did in your home is yours: it keeps 90 days by default, you can shorten it to a single day and the old entries go immediately, and an operator who has to keep records for longer can, with a written reason. One endpoint shows you what is stored, downloads all of it as JSON, and deletes one home or every trace of all of them. (`/docs/home-privacy`) `[feature, security, docs]`
- **The status page can tell one dark house from an outage**: Connected homes now report on the public status page at /status, and the hard part was making that number honest. If your Home Assistant is switched off, your token expired or your internet dropped, that is your house: it shows up in your own home view, not as a three.ws outage and not as an alert to anyone. It takes at least ten homes failing at once before the platform will call it a problem on our side, because with three homes connected one holiday cottage losing power would look like a third of everything being broken. One thing is treated as an emergency at a count of one: an action that can open a building (a lock, a garage door, an alarm) recorded as having run without someone saying yes. That has no acceptable rate. (`/status`) `[infra, improvement]`
- **The tour atlas counts its stops correctly again**: The atlas at /tour/atlas is the map of the guided tour: one card per stop, numbered in the order you would walk them. Two hundred and three of those cards were still carrying numbers from an older version of the tour, so the grid showed duplicate stop numbers, skipped others, and put cards out of order, under a heading that claimed one more stop than the grid actually held. Every card is now numbered by its real position in the tour and the count above the grid matches what is under it. Nothing about the stops themselves changed: same pages, same screenshots, same highlights. (`/tour/atlas`) `[fix]`
- **three.ws Drive: your agent, in the car**: There is a new page at /drive built for a car screen instead of a desk. Your agent is on it full size, you hold one big button and talk, and it answers out loud in its own voice with its face moving. It shows you one line of what it said rather than a wall of chat, because you are driving. It starts dark, because a bright panel at night is glare, and it will switch to a day palette on one press or one sentence. The keyboard stays out of the way while you are moving: if your browser can tell how fast you are going, text entry locks itself the moment you pull away and comes back when you have properly stopped. A few things you say never leave the car at all, so "repeat that", "stop talking", "louder" and "night mode" happen instantly, while "stop at the next charger" still goes to your agent like any other question. It works today on a head unit browser, on a phone in a cradle, and on Android Automotive. The Apple CarPlay version is built and waiting on Apple's approval for voice assistants in the car. One thing this fixed for everyone: an avatar used to answer in silence if you were not signed in, and now it always has a voice. (`/drive`) `[feature, improvement]`
+- **Your house reads in your language, in your units, at a size a finger can hit**: Three fixes to the smart home page, all of them things you would have noticed. It now speaks all 87 languages: the page was written to be translated but never loaded the piece that does the translating, so everyone got English, and Arabic and Hebrew never flipped to right to left. Temperatures now come from your house rather than from an assumption. If your Home Assistant is set to Fahrenheit, every room reads in Fahrenheit, and a room at 70 no longer shows as blazing hot because the comfort range was written in Celsius. A house that mixes a Celsius sensor with a Fahrenheit thermostat is converted before it is averaged, so the number you see belongs to a real scale. The small print at the top of the page also got lighter so it clears the contrast standard, in both the light and dark themes, and the Show button next to the token field is now big enough to tap without missing. (`/smart-home`) `[fix, improvement]`
## 2026-09-02
diff --git a/data/changelog.json b/data/changelog.json
index b105f4627..88f8d69e0 100644
--- a/data/changelog.json
+++ b/data/changelog.json
@@ -25894,6 +25894,16 @@
"improvement"
],
"link": "/smart-home"
+ },
+ {
+ "date": "2026-09-03",
+ "title": "Your house reads in your language, in your units, at a size a finger can hit",
+ "summary": "Three fixes to the smart home page, all of them things you would have noticed. It now speaks all 87 languages: the page was written to be translated but never loaded the piece that does the translating, so everyone got English, and Arabic and Hebrew never flipped to right to left. Temperatures now come from your house rather than from an assumption. If your Home Assistant is set to Fahrenheit, every room reads in Fahrenheit, and a room at 70 no longer shows as blazing hot because the comfort range was written in Celsius. A house that mixes a Celsius sensor with a Fahrenheit thermostat is converted before it is averaged, so the number you see belongs to a real scale. The small print at the top of the page also got lighter so it clears the contrast standard, in both the light and dark themes, and the Show button next to the token field is now big enough to tap without missing.",
+ "tags": [
+ "fix",
+ "improvement"
+ ],
+ "link": "/smart-home"
}
]
}
diff --git a/public/changelog.json b/public/changelog.json
index 28d2f0b55..461cde9d5 100644
--- a/public/changelog.json
+++ b/public/changelog.json
@@ -1,5 +1,5 @@
{
- "generated_at": "2026-09-03T03:56:06.745Z",
+ "generated_at": "2026-09-03T03:57:33.265Z",
"generated_by": "scripts/build-page-index.mjs from data/pages.json + data/changelog.json",
"site": {
"name": "three.ws",
@@ -26,6 +26,16 @@
"launch"
]
},
+ {
+ "date": "2026-09-03",
+ "type": "launch",
+ "title": "Docs · Home security",
+ "summary": "The threat model for a connected house, written about a building rather than a database: what each actor can do and what stops them, why the confirmation gate is the load-bearing control and prompt filtering is depth, the eleven checks that run with every build, the SSRF guard every server-side dial goes through and why a hostname check is not one, the prompt-injection proof that ends by asking a real lock whether it opened, and the residuals accepted on purpose.",
+ "link": "/docs/home-security",
+ "tags": [
+ "launch"
+ ]
+ },
{
"date": "2026-09-03",
"type": "launch",
@@ -56,6 +66,16 @@
"launch"
]
},
+ {
+ "date": "2026-09-03",
+ "type": "launch",
+ "title": "Join a home",
+ "summary": "Accept an invitation to somebody's connected home. The link says which home it is, exactly what your role would let you do there and what it would never let you do, before you sign in. It works once and it expires.",
+ "link": "/smart-home/join",
+ "tags": [
+ "launch"
+ ]
+ },
{
"date": "2026-09-03",
"type": "launch",
@@ -86,6 +106,17 @@
"launch"
]
},
+ {
+ "date": "2026-09-03",
+ "type": "update",
+ "title": "A stranger cannot make your agent open your front door",
+ "summary": "The home lane now has a written threat model and eleven security checks that run with every build, and the standard they hold is a lock, not a database row. The big fix: the address you give for your house is now resolved and pinned on our side before anything dials it, so a web address that secretly points back into our own network is refused instead of connected to, and it is re-checked every time your house reconnects rather than trusted from the day you added it. A device or integration in your house cannot talk your agent into anything either: we wrote an unlock instruction into a real room name, a real device name and a real scene name, ran a real agent against that house, and the front door stayed locked. Your privacy page is now rate limited like everything else, so nobody can hammer the export or the delete.",
+ "link": "/smart-home",
+ "tags": [
+ "security",
+ "improvement"
+ ]
+ },
{
"date": "2026-09-03",
"type": "update",
@@ -140,6 +171,17 @@
"improvement"
]
},
+ {
+ "date": "2026-09-03",
+ "type": "update",
+ "title": "Your house reads in your language, in your units, at a size a finger can hit",
+ "summary": "Three fixes to the smart home page, all of them things you would have noticed. It now speaks all 87 languages: the page was written to be translated but never loaded the piece that does the translating, so everyone got English, and Arabic and Hebrew never flipped to right to left. Temperatures now come from your house rather than from an assumption. If your Home Assistant is set to Fahrenheit, every room reads in Fahrenheit, and a room at 70 no longer shows as blazing hot because the comfort range was written in Celsius. A house that mixes a Celsius sensor with a Fahrenheit thermostat is converted before it is averaged, so the number you see belongs to a real scale. The small print at the top of the page also got lighter so it clears the contrast standard, in both the light and dark themes, and the Show button next to the token field is now big enough to tap without missing.",
+ "link": "/smart-home",
+ "tags": [
+ "fix",
+ "improvement"
+ ]
+ },
{
"date": "2026-09-02",
"type": "launch",
diff --git a/public/changelog.xml b/public/changelog.xml
index 77c1da9c9..1306618b8 100644
--- a/public/changelog.xml
+++ b/public/changelog.xml
@@ -22,6 +22,14 @@
<category>launch</category>
<description>Everything three.ws stores about a home you connect, why, for how long, and what removes it: the full inventory, the promise that room names and device states are never persisted, the 90-day action-log window and the control that changes it, the export and deletion paths, the logging rules, and the disclosure text shown at connect and at the voice opt-in.</description>
</item>
+ <item>
+ <title>Docs · Home security</title>
+ <link>https://three.ws/docs/home-security</link>
+ <guid isPermaLink="false">2026-09-03:Docs · Home security</guid>
+ <pubDate>Thu, 03 Sep 2026 12:00:00 GMT</pubDate>
+ <category>launch</category>
+ <description>The threat model for a connected house, written about a building rather than a database: what each actor can do and what stops them, why the confirmation gate is the load-bearing control and prompt filtering is depth, the eleven checks that run with every build, the SSRF guard every server-side dial goes through and why a hostname check is not one, the prompt-injection proof that ends by asking a real lock whether it opened, and the residuals accepted on purpose.</description>
+ </item>
<item>
<title>Docs · three.ws Drive</title>
<link>https://three.ws/docs/carplay</link>
@@ -46,6 +54,14 @@
<category>launch</category>
<description>What your plan covers for connected homes: homes, household seats, live screens, voice minutes and agent turns, each with what you have used and when it resets. Pause and resume which homes are live without disconnecting any of them. Locking up, closing a garage and arming an alarm are never limited.</description>
</item>
+ <item>
+ <title>Join a home</title>
+ <link>https://three.ws/smart-home/join</link>
+ <guid isPermaLink="false">2026-09-03:Join a home</guid>
+ <pubDate>Thu, 03 Sep 2026 12:00:00 GMT</pubDate>
+ <category>launch</category>
+ <description>Accept an invitation to somebody's connected home. The link says which home it is, exactly what your role would let you do there and what it would never let you do, before you sign in. It works once and it expires.</description>
+ </item>
<item>
<title>Smart home</title>
<link>https://three.ws/smart-home</link>
@@ -70,6 +86,14 @@
<category>launch</category>
<description>Give your existing Home Assistant voice assistant a face. Pair a three.ws satellite and the same pipeline you already use gains a 3D agent that lip-syncs its answers and reacts, on any screen in the house. Home Assistant keeps the wake word, the speech recognition and the answer; closing the page never stops the voice working.</description>
</item>
+ <item>
+ <title>A stranger cannot make your agent open your front door</title>
+ <link>https://three.ws/smart-home</link>
+ <guid isPermaLink="false">2026-09-03:A stranger cannot make your agent open your front door</guid>
+ <pubDate>Thu, 03 Sep 2026 12:00:00 GMT</pubDate>
+ <category>security</category>
+ <description>The home lane now has a written threat model and eleven security checks that run with every build, and the standard they hold is a lock, not a database row. The big fix: the address you give for your house is now resolved and pinned on our side before anything dials it, so a web address that secretly points back into our own network is refused instead of connected to, and it is re-checked every time your house reconnects rather than trusted from the day you added it. A device or integration in your house cannot talk your agent into anything either: we wrote an unlock instruction into a real room name, a real device name and a real scene name, ran a real agent against that house, and the front door stayed locked. Your privacy page is now rate limited like everything else, so nobody can hammer the export or the delete.</description>
+ </item>
<item>
<title>Connect your house to your agent, and see every way it can go wrong</title>
<link>https://three.ws/smart-home</link>
@@ -110,6 +134,14 @@
<category>feature</category>
<description>There is a new page at /drive built for a car screen instead of a desk. Your agent is on it full size, you hold one big button and talk, and it answers out loud in its own voice with its face moving. It shows you one line of what it said rather than a wall of chat, because you are driving. It starts dark, because a bright panel at night is glare, and it will switch to a day palette on one press or one sentence. The keyboard stays out of the way while you are moving: if your browser can tell how fast you are going, text entry locks itself the moment you pull away and comes back when you have properly stopped. A few things you say never leave the car at all, so &quot;repeat that&quot;, &quot;stop talking&quot;, &quot;louder&quot; and &quot;night mode&quot; happen instantly, while &quot;stop at the next charger&quot; still goes to your agent like any other question. It works today on a head unit browser, on a phone in a cradle, and on Android Automotive. The Apple CarPlay version is built and waiting on Apple's approval for voice assistants in the car. One thing this fixed for everyone: an avatar used to answer in silence if you were not signed in, and now it always has a voice.</description>
</item>
+ <item>
+ <title>Your house reads in your language, in your units, at a size a finger can hit</title>
+ <link>https://three.ws/smart-home</link>
+ <guid isPermaLink="false">2026-09-03:Your house reads in your language, in your units, at a size a finger can hit</guid>
+ <pubDate>Thu, 03 Sep 2026 12:00:00 GMT</pubDate>
+ <category>fix</category>
+ <description>Three fixes to the smart home page, all of them things you would have noticed. It now speaks all 87 languages: the page was written to be translated but never loaded the piece that does the translating, so everyone got English, and Arabic and Hebrew never flipped to right to left. Temperatures now come from your house rather than from an assumption. If your Home Assistant is set to Fahrenheit, every room reads in Fahrenheit, and a room at 70 no longer shows as blazing hot because the comfort range was written in Celsius. A house that mixes a Celsius sensor with a Fahrenheit thermostat is converted before it is averaged, so the number you see belongs to a real scale. The small print at the top of the page also got lighter so it clears the contrast standard, in both the light and dark themes, and the Show button next to the token field is now big enough to tap without missing.</description>
+ </item>
<item>
<title>Docs · Materialize: turn a generation into a real object</title>
<link>https://three.ws/docs/materialize</link>
diff --git a/public/features.json b/public/features.json
index 7c05cda8f..5884dbea3 100644
--- a/public/features.json
+++ b/public/features.json
@@ -1,5 +1,5 @@
{
- "generated_at": "2026-09-03T03:56:06.690Z",
+ "generated_at": "2026-09-03T03:57:33.231Z",
"generated_by": "scripts/build-page-index.mjs from data/pages.json",
"site": {
"name": "three.ws",
@@ -1222,6 +1222,16 @@
"tags": [],
"showcase": false
},
+ {
+ "path": "/smart-home/join",
+ "title": "Join a home",
+ "description": "Accept an invitation to somebody's connected home. The link says which home it is, exactly what your role would let you do there and what it would never let you do, before you sign in. It works once and it expires.",
+ "added": "2026-09-03",
+ "auth": null,
+ "indexable": true,
+ "tags": [],
+ "showcase": false
+ },
{
"path": "/smart-home/plan",
"title": "Home plan",
@@ -3267,6 +3277,16 @@
"tags": [],
"showcase": false
},
+ {
+ "path": "/docs/home-security",
+ "title": "Docs · Home security",
+ "description": "The threat model for a connected house, written about a building rather than a database: what each actor can do and what stops them, why the confirmation gate is the load-bearing control and prompt filtering is depth, the eleven checks that run with every build, the SSRF guard every server-side dial goes through and why a hostname check is not one, the prompt-injection proof that ends by asking a real lock whether it opened, and the residuals accepted on purpose.",
+ "added": "2026-09-03",
+ "auth": null,
+ "indexable": true,
+ "tags": [],
+ "showcase": false
+ },
{
"path": "/docs/home-privacy",
"title": "Docs · Home privacy and retention",