Visible work
Every task, command, preview, and file edit stays attached to the workspace timeline.
TUNC.AI · Operator Console
Tunc Hub.
Tunc Hub.
For Operators
What it is
The governed workspace for AI coding agents.
Run agents, approve risky actions, and keep every tool call, task, preview, and memory trail visible in one operator-controlled workspace.
Governed autonomy
Agents can move fast because operators stay in control.
When Trejo wants to edit code, run tests, or publish a deploy, Hub shows the repo, tool call, permission mode, diff, and approval point before anything risky happens.
Approval gates
Permission modes make risky actions explicit instead of burying them in a chat transcript.
Recoverable history
Memory, logs, and audit trails make agent work inspectable after the tab, model, or session changes.
Why teams pick it
Autonomy without the blank check.
Tunc Hub lets agents keep working while operators keep the decisions, approvals, and audit trail.
01 · Momentum
Agents keep work moving.
Parallel tasks, checks, and previews continue while your team reviews the moments that matter.
02 · Control
Risky actions wait for approval.
Tool access, permission modes, and deploy gates are visible before an agent can change something important.
03 · Ownership
Your code and history stay yours.
Keys, memory, policies, and audit trails stay under your rules instead of disappearing into a prompt window.
What it does
Work, verify, govern — in one window.
Chat, agents, tools, previews, memory, and permissions are grouped around one job: keep AI work visible, reviewable, and recoverable.
01 / CHAT
Chat with your codebase
Pick the model: Claude, OpenAI, DeepSeek, your call. Ask questions, get answers grounded in the real repo, not a guess from training data.
claude-opus-4
gpt-5
deepseek-v4
+ workspace ctx
02 / TOOLS
Real work, not just chat
AI reads files, runs commands, uses git, opens PRs, and checks its work in a browser. All inside isolated workspaces (local or cloud), so your laptop stays untouched.
▾acme/checkout
▾stripe/
+ webhook.ts
·idempotency.ts
·tests/
03 / AGENTS
Send AI to work in the background
Spawn agents to plan, refactor, review, or implement while you keep moving. Nudge them, stop them, or take over whenever you want.
refactor-tests
review-pr-482
scope-fix
04 / PREVIEW
See what AI is building
Preview the app, the diff, the docs, or the browser session right next to the chat. No app-switching, no guesswork about what changed.
05 / MEMORY
Nothing gets forgotten
Every chat, plan, task, and tool call is saved against the workspace. Restart the app, switch devices, come back next week. The context is still there.
10:02
10:14
10:31
now
06 / GOVERN
Stay in control
Decide which models, tools, and credentials each workspace can use. Set policy once. Apply it everywhere your team works.
policy on
Core vault
07 / PERSONAS
Know who's speaking
Give each AI a name, a role, and a co-author signature, so reviewers, PRs, and commits always show exactly who (or what) did the work.
B
R
08 / TOOL ACCESS
Just the keys it needs
Allow some tools, deny others, ask before risky ones. AI doesn't even see the tools you've hidden. No blank checks.
shell.execallow
file.writeask
external.pushdeny
09 / AUDIT
Show me what AI did
Every tool call, every approval, every diff is logged against the workspace. Useful for debugging, cost, security, or just answering "wait, why?"
shell.exec · git status
file.write · webhook.ts
external.push · prod
How it works
Sign in. Pick a workspace.
Start a turn.
It's a desktop app. You open it, sign in, and you're working. The technical bits happen quietly in the background.
01 / SIGN IN
Sign in with Google
We check you're an operator. Your workspaces and credentials load automatically.
02 / SELECT
Pick your project
Pick the repo or client workspace. The right credentials and policies follow.
03 / CHAT OR PLAN
Choose how to work
Pick your AI, your mode, your level of supervision. Then start talking.
04 / RUN
AI does the work
AI uses its tools under whatever rules you set. You watch, approve, or step in.
05 / PREVIEW
See the result
Read the diff, run the app, browse the output. Without leaving the window.
06 / AUDIT
Everything logged
Every decision is saved. For next time, for your team, or for your CFO.
AI doesn't replace your team.The Tunc.AI principle
It just stops slowing them down.
AI governance
AI you can trust,
because you can see it.
Everything AI does is visible, approvable, and reversible. Not buried in a settings tab. Right on the chat surface, where the work happens.
Personas with names
Give each AI a name and a role. Backend engineer, frontend specialist, code reviewer, QA. The persona shapes how it speaks, what it can do, and whose name shows up on the commit.
Lock a persona to a workspace or company. The right AI runs the right work. No mystery.
- AI gets a name and a role you assign
- How it talks, and how it signs work
- Different persona per workspace if you want
- Live attribution on commits and PRs
Active persona
B
Available roles
Backend
Frontend
Reviewer
QA
Architect
policy.persona = backend@acme
Give AI just the right tools
AI doesn't need every tool every time. Pick what each workspace can use: shell, git, file writes, browser, MCP servers, your own integrations.
Lock down anything risky. Hide what you don't trust. AI doesn't even know the hidden tools exist.
- Allow, ask, or deny per tool
- Different rules per workspace
- Hidden tools are truly hidden
- Block or allow specific commands
Workspace policy: acme/checkout
shell.exec · git.*allow
shell.exec · rm -rfdeny
file.writeask
browser.navigateallow
mcp.figma.exportask
external.push · proddeny
Always know what mode AI is in
Four modes. They're visible on the chat surface, so you never wonder what AI is allowed to do right now.
In Auto, the safer stuff runs, the dangerous stuff is blocked, the iffy stuff still asks. Bypass exists, but only when you explicitly choose it.
- Default: AI asks before it changes anything
- Plan: AI proposes, doesn't touch
- Auto: safe runs, risky asks, dangerous blocked
- Bypass: only when you explicitly opt in
Current mode
Auto classification
file.read · webhook.tsauto-allow
file.write · webhook.tsask
shell · remove proddeny
Replay anything, anytime
Every chat, plan, tool call, and approval is logged against the workspace. When you need to know what happened, what AI tried, what got approved, what didn't, it's all there.
Useful for debugging, sharing decisions with the team, or just answering "why did it do that."
- Full chat and tool history
- Approvals, denials, and asks
- Agent runs, plans, and previews
- Backed up to Core if you want
Activity: last 4 events
shell.exec · git diff
file.write · webhook.ts (operator-approved)
external.push · prod (policy)
Where your stuff lives
Your stuff stays yours.
Your code, your keys, and your team's identity stay where they belong. Hub is just the app you use. Core is the backend that ties workspaces, credentials, and policies together. Both honor your existing security model.
In Hub, on your machine
- AI runs in isolated workspaces, not on your laptop
- All your chat history and tool runs, saved locally
- Files, diffs, browser, and markdown previews
- Reusable skills you can drop in
- Project memory that survives restarts
In Tunc Core, behind the app
- Google sign-in and team assignment
- Workspace-scoped credentials in a vault
- Personas, tool rules, and permission policies
- Who-said-what attribution in chat
- Auto-updates with signed releases
For enterprise
Make it yours.
Want everything private? We white-label Tunc Hub and Tunc Core, then deploy a private Core in your cloud or on your servers. Your domain, your sign-in, your policies. Your data never leaves your perimeter.
Same desktop experience your team already trusts, with your logo on it.
- Your brand on Hub and Core
- On-premises, AWS, GCP, or Azure
- Every chat, persona, and policy stays with you
- Your identity provider, your domain
- Custom retention and audit windows
- Private release channels
Get Tunc Hub for Mac.
Tunc Hub ships as a macOS desktop app. Public installers are distributed as signed DMG files; in-app updates use signed Tauri updater artifacts served through Tunc Core release metadata.
Download for Mac →
macOS · Apple Silicon · v1.0
Intel · soon
Windows · planned
Linux · planned