Newshot Meet Chap,your AI agent for work.
A meeting assistant, a note-taker and a pair of hands on whatever tab you're on — Chap sits where you already work and runs on your machine. Bring any model or agent and swap between them mid-conversation, while sensitive details are anonymized before they leave your machine and restored in the reply you read. No ChatPanel server in the middle.
In your browser
As an app, or in your terminal
Chat the moment you install — a private AI model runs right in your browser, no API key, no account, nothing to set up. Works in Firefox, Chrome, Edge, Brave & Arc. Move to a local model, a cloud API, or your own agent anytime. The desktop app carries the Gateway and Bridge, so there is nothing else to install.
A side panel isn't the point — every browser ships one now. The point is that this one is yours: your model or agent, your notes and meetings as context, your sensitive data anonymized before it ever leaves the browser.
What actually makes it different
Six things a built-in browser assistant won't do for you.
Nothing leaves without your say
No ChatPanel server sits in the path. Emails, phones, cards and keys — and with on-device AI, names, orgs and locations — are anonymized on your machine before a request goes out, then de-anonymized in the reply. The same protection can wrap the agents you already use.
A notebook your AI writes with you
Linked, wiki-style notes your AI can research, co-write and restructure alongside you — capture from any page, then turn a selection into a plan without leaving the panel.
A meeting assistant for every major platform
Zoom, Meet, Teams and Webex — running notes, decisions and action items straight from the live captions. It all happens in your browser: no bot joins your call, nothing is uploaded.
Never locked to one model
The in-browser model, Ollama or LM Studio on your laptop, 20+ cloud APIs, or agents like Claude Code, Codex, GitHub Copilot and Antigravity under your own logins — switch between them mid-conversation.
One memory across everything
Notes, meetings and past chats live in a single searchable store, so an answer can draw on last week's call, a note from March, and the page in front of you at once.
Actions, not just answers
MCP servers and browser actions give your AI real reach — and when you point it at a coding agent, its own tools come with it, so you get the full power of what you already pay for.
Anonymize sensitive data before it reaches any model
ChatPanel strips PII out of everything you send — emails, phones, cards and keys, plus (with on-device AI) names, organizations and locations — and puts it back in the reply you read. The model only ever sees opaque placeholders; your real values are restored for you.
Reversible anonymization swaps a value for a placeholder the model can still reason about, then restores it for you. Pseudonymize permanently swaps a name for an alias. Detection runs locally, you choose which categories to protect — and the same protection extends to the agents you already use, so Claude Code, Codex or any OpenAI-compatible client can sit behind it too.
Never locked to one model
Start on the in-browser model, move to Ollama on your laptop, jump to a cloud API, then hand the same conversation to Claude Code, Codex, GitHub Copilot or Antigravity running under your own logins. Switch mid-conversation — your panel, history and tools don't change.
A one-time helper app connects the local agents. Prefer a cloud or local model instead? Skip the helper and point ChatPanel straight at it.
Give your AI hands — and borrow your agent's
On its own, a chat model can only talk. Add MCP tools from a built-in directory and it can search, pull in live data, and work with your other apps on your behalf. Point the panel at a coding agent and its own tools come along too, so you get the full power of the agent you already pay for — right inside the chat.
Start with one tool for free; add as many as you like with Pro. Advanced users can even share their own browser back to other agents.
Your notes, meetings and chats — one memory
Everything you capture lands in a single searchable store on your computer: past conversations, linked notes, and meeting transcripts. Ask a question and the answer can draw on last week's call and the page you're on. Open a visual map of it all, grouped by topic, and jump straight back in.
A meeting assistant for every major platform
On Zoom, Meet, Teams, and Webex, ChatPanel turns the live captions into running notes, decisions, and action items — plus a transcript you can search or ask about afterward. It runs entirely in your browser: no bot joins the call, and nothing is uploaded.
Reads the meeting's captions only — never your audio or video. Free covers your first 10 meetings; Pro is unlimited.
Your go-to prompts, one tap away
Save the things you ask for again and again — summarize, explain, review — as one-tap shortcuts. Use the built-ins, or write your own and drop them into any chat.
And a few more things
Smaller touches that add up. Most take a quick one-time setup.
Ask about what you're looking at Free
Pull in the current tab, other tabs you pick, highlighted text, or a link you paste — and only when you ask for it.
Let it fill forms & click Free
Turn on Act on Page and ask in plain words. ChatPanel fills in fields, picks options, and clicks for you — only when you switch it on, and it checks with you before sensitive steps.
Draw on canvas apps, cleanly Pro
On Excalidraw, draw.io, and tldraw, your agent builds shapes as structured data — exact positions, in one pass — instead of nudging the mouse around. Flowcharts, diagrams, and wireframes come out crisp. On Free it falls back to slow pixel-drawing.
Chat instantly, no setup Free
The moment you install, a small private model runs right in your browser on WebGPU — no API key, no account, nothing to run. Your first message downloads it once (~700 MB), then it works offline. Want more power? Connect Ollama or LM Studio, or bring your own API key. Nothing you type ever leaves your machine.
Plug in any command-line tool Pro
Already use OpenCode, Pi, or a script of your own? Point ChatPanel at it and it works like any built-in agent.
Take your data anywhere Pro
Back up your settings and conversations to a single file, then restore them on another machine.
Many agents, one panel Free
Set up several agents and models, then switch between them in the middle of a conversation.
Capture anything, link everything Free
Capture anything into linked notes with [[wiki-links]], then let your AI co-write, research across your workspace and the web, and turn a selection into a plan — right in the note. Free keeps your first 10 notes; Pro is unlimited.
Talk instead of type Free
With the Gateway installed, speech-to-text runs on your own machine — dictate chats, notes, and questions, transcribed locally by an on-device model. Your audio never leaves your computer, and no cloud key is needed.
Bring almost any AI provider
Choose from 20+ ready-made presets or add your own. Many providers have free tiers. Sign in or paste a key — whichever yours uses — and your credentials stay in your browser.
No keys to copy
For providers that support it, just sign in from the panel. No tokens to paste or manage.
Hosted APIs & free tiers
Presets fill in the technical bits and link you to where each key lives. Some providers ask for billing or credits.
Private & local endpoints
Point ChatPanel at a private gateway or a model running on your own machine. Full control over the connection.
Setting one up takes about a minute: pick a provider, add your sign-in or key, load the model list, and run a quick Test to confirm it works.
Private by design
ChatPanel has no cloud in the middle. Your prompts, keys, notes, meetings and history stay on your machine; what you send goes straight to the AI you picked — anonymized first, if you want it — and nowhere else.
Local-first
Conversations, notes, meeting transcripts, keys and settings live on your computer. Content only ever goes to the model or agent you chose.
The model sees placeholders
Names, emails, phones, cards and keys are swapped for tokens before a request leaves your browser, then restored in the reply — and the same shield can front your existing agents.
We never see your chats
There's no ChatPanel server in the path. We don't store, route, or read your conversations — ever.
Up and running in minutes
Free, no account, and it works on its own with the model you pick.
- 1Install ChatPanelThe browser extension from the Chrome Web Store, Edge Add-ons or Firefox — or the CLI with npm i -g @chatpanel/cli. About a minute either way.
The browser extension from the Chrome Web Store, Edge Add-ons or Firefox — or the CLI with npm i -g @chatpanel/cli. About a minute either way.
- 2Connect an AI — or don't Chat on the in-browser model straight away, or point it at a provider, a local model, or your own agents. Run Test and you're set.
Chat on the in-browser model straight away, or point it at a provider, a local model, or your own agents. Run Test and you're set.
- 3Start chattingOpen the panel on any tab. Upgrade to Pro anytime — it activates instantly.
Open the panel on any tab. Upgrade to Pro anytime — it activates instantly.
Simple pricing
Start free, or take all of Pro for 3 months. Then pay once and own it, or keep it monthly — your call.
Free
- One local agent — Claude Code, Codex, GitHub Copilot, or Antigravity
- One model of your choice — cloud or local
- Ask about the current tab or a pasted link
- Let it fill forms and click for you
- One tool from the built-in directory
- Anonymize secrets before they're sent
- Your first 10 notes and 10 meetings
- Searchable history across chats, notes & meetings
Pro
- Everything in Free
- All your agents & models unlocked
- Bring your own command-line agent
- Unlimited tools from the directory
- Use several tabs or your whole window as context
- Clean diagrams on Excalidraw, draw.io & tldraw
- Unlimited notes & meeting notes — Zoom, Meet, Teams & Webex
- AI auto-detect anonymization — names, orgs & locations
- Create your own skills
- Export & back up your conversations
Card required so it doesn't cut out on you · cancel any time before it ends and you're charged nothing · then $5/mo
or $5/mo · $42/yr
or buy once for $49
Lifetime covers the v1 Pro feature set, forever. Cloud/Team features are separate. Limited-offer terms apply.
Team
- Everything in Pro
- Cloud sync across devices
- Shared team agents & skills
- Hosted agents — no helper to run
Per-seat annual for cloud, or a one-time license if you self-host. We'll size it to your team.
Two ways to get Pro — both activate in the extension
Check out above, then open ChatPanel → the License tab → “Restore Pro on this device”, enter your purchase email, and we'll email a one-tap activation link. Other devices on the same Chrome profile activate automatically.
Open ChatPanel → the License tab → “Subscribe to Pro”. Pro activates on that device the moment checkout finishes — no email step — and follows your purchase email to your other devices.
Limited-offer terms. This limited-offer price is a promotional discount available for a limited time and/or a limited number of purchases, at ChatPanel's sole discretion. We may modify, extend, or end this offer at any time without prior notice. The discount is applied at checkout while available; the standard price is $89.
Install in two minutes
ChatPanel comes as a browser extension, a desktop app and a command line. They share one memory, one privacy layer and the same models — pick where you work, or use all three.
In your browser
As an app, or in your terminal
The desktop app carries the Gateway and Bridge, so there is nothing else to install. The CLI needs the Gateway — one line, below. Full steps for each:
Browser extension
No developer tools needed. Install from the Chrome Web Store or Microsoft Edge Add-ons, then connect a model — a provider with a free tier, your own key, or a free local app like Ollama. The last step (the helper app) is optional and only needed for local Claude Code, Codex & Antigravity.
Chrome, Edge, Brave & Arc
- Download chatpanel-extension.zip and unzip it to a folder you’ll keep.
- Load it. Open chrome://extensions (Edge: edge://extensions), turn on Developer mode, click Load unpacked, and pick the unzipped folder (the one with manifest.json).
- Install from the listing — addons.mozilla.org. One click, and it auto-updates.
- There is no sideload option on Firefox: it installs only add-ons signed by Mozilla, and the Chromium .zip above is a different build that won’t run there. Testing an unreleased build? Open about:debugging → This Firefox → Load Temporary Add-on and pick its manifest.json — that lasts until you restart.
- Connect a model. Open Settings → API, choose a provider, add your sign-in or key, load the model list, pick one, and click Test.
- (Optional) Install ChatPanel on your machine — one install. The Gateway carries the Bridge and starts it for you, so the browser extension gets your local Claude Code, Codex, GitHub Copilot & Antigravity, plus PII redaction, model routing, local voice, projects and teams — from one command. Runs quietly in the background; ChatPanel finds it automatically. # macOS / Linux — one line, no extra tools needed curl -fsSL https://dl.chatpanel.net/install.sh | bash # Windows (PowerShell) — no Node needed irm https://dl.chatpanel.net/install.ps1 | iex # have Node.js? the npm build runs the local models faster (two commands — PowerShell has no &&) npm i -g @chatpanel/gateway --ignore-scripts # the flag is part of the install — see the FAQ chatpanel-gateway --install # Windows: "not recognized"? open a new PowerShell, or run # node "$(npm root -g)/@chatpanel/gateway/bin/chatpanel-gateway.js" --install Already using ChatPanel Desktop? It ships both and the extension finds them — nothing to install. Any OpenAI-compatible client (OpenCode, Pi, aider) can point at http://127.0.0.1:4320/v1: redacted on the way out, restored on the way back. Install one build, not both — the binary shadows npm on your PATH. Which build to pick. Only want the bridge, without the gateway? curl -fsSL https://dl.chatpanel.net/bridge/install.sh | bash (or npx @chatpanel/bridge to try it once).
# macOS / Linux — one line, no extra tools needed
curl -fsSL https://dl.chatpanel.net/install.sh | bash
# Windows (PowerShell) — no Node needed
irm https://dl.chatpanel.net/install.ps1 | iex
# have Node.js? the npm build runs the local models faster (two commands — PowerShell has no &&)
npm i -g @chatpanel/gateway --ignore-scripts # the flag is part of the install — see the FAQ
chatpanel-gateway --install # Windows: "not recognized"? open a new PowerShell, or run
# node "$(npm root -g)/@chatpanel/gateway/bin/chatpanel-gateway.js" --install
Desktop app
The same ChatPanel as the extension, as an app — with the Gateway and Bridge built in, so there is nothing else to install: your local coding agents, on-device redaction, the small models, memory, skills and teams, in one download. Not in an app store yet; download the installer for your machine.
- macOS — Apple Silicon (.dmg)
- Windows — x64 (.exe)
Same downloads as the badges at the top of this section.
Intel Mac? No app build yet — the on-device models need a native runtime that is not built for Intel macOS today. Use the browser extension with the one-line Gateway install; it is the same ChatPanel. Early builds: if macOS says the app is from an unidentified developer, right-click → Open once (or System Settings → Privacy & Security → Open Anyway); if Windows SmartScreen appears, More info → Run anyway. Every download comes from the latest GitHub release.
Terminal (CLI)
The same chats, models, tools, memory, skills and teams as the extension — in your terminal, as a chat screen and as commands you can script. Everything goes through the Gateway on your machine, so personal data is redacted before a model sees it, and a chat you have here shows up in the extension's history a few seconds later.
- Install ChatPanel on your machine (the Gateway — it carries the Bridge, and it is what the CLI talks to). Skip this if you already did it for the extension above. # macOS / Linux curl -fsSL https://dl.chatpanel.net/install.sh | bash # Windows (PowerShell) irm https://dl.chatpanel.net/install.ps1 | iex
# macOS / Linux
curl -fsSL https://dl.chatpanel.net/install.sh | bash
# Windows (PowerShell)
irm https://dl.chatpanel.net/install.ps1 | iex
- Install the CLI — needs Node.js 22 or newer. npm i -g @chatpanel/cli
npm i -g @chatpanel/cli
- Chat. cpcli opens the screen; cpcli ask "…" answers once and exits. cpcli # the chat screen — / for commands, Ctrl+P to pick a model cpcli ask "what did we decide about the rollback?" git diff | cpcli ask "review this" # anything piped in becomes context cpcli -c # continue the last chat Start it inside a project and it asks, once, whether coding agents (Claude Code, Codex…) may work in that folder. !git status runs a shell command and puts the output in front of your next question. Skills, teams and recipes you saved in the extension are /commands here too. Models come from the Gateway's list — a local CLI agent, Ollama, or any provider you connected; cpcli models shows what can answer. cpcli --help lists everything.
cpcli # the chat screen — / for commands, Ctrl+P to pick a model
cpcli ask "what did we decide about the rollback?"
git diff | cpcli ask "review this" # anything piped in becomes context
cpcli -c # continue the last chat
Bridge vs Gateway? The Bridge is lightweight — its one job is connecting the browser extension to your local CLI agents; most people only need this. The Privacy Gateway is a separate, privacy-focused model router: it redacts with a bundled NER and routes the cleaned request to a model API or your CLI agents — and any OpenAI-compatible client, including the extension, can point at it. Three independently-versioned pieces (extension, bridge, gateway); install only what you use.