9:12 AM
The task shows up
Import your board from Linear, Jira or GitHub Issues in one click. MAT-214 is already here, with its description, and it syncs both ways.
Every other agentic development environment stops at the pull request.
Coldtea runs production monitoring and agentic end to end testing.
Let's walk through your first day in Coldtea
Say you have agents writing code all day.
9:40 AM
Your agents pick it up
Start it in the terminal. Run several agents at once on the same task. They share context, so they can work in parallel and build on each other's work.
11:05 AM
The work explains itself
Every agent session leaves a plan and a log on the task. Come back in a week, or hand it to someone else. The thinking is still there.
1:20 PM
You open a PR
Nothing leaves your machine until you say so. When it does, the pull request closes the task it came from, so everything after this points back to one change.
1:24 PM
Every pull request gets regression tested
QA agents open the preview URL for your pull request and click through the product like real users. All we need to test your app is a URL, we'll handle authentication, bot detection, agent orchestration and more.
Applying promo code MATCHA10 takes ten percent off the total.Tests in plain English. Run on web, desktop, iOS and Android.
2:58 PM
You ship
Merge. Deploy. Then the same tests run again, this time on production.
3:00 PM
Production is watched
Connect Sentry, PostHog, your logs, your feedback inbox. Monitoring agents read them all day, the way an on-call engineer would.
9:06 PM
What broke comes back as work
A monitoring agent saw that a wrong address could bypass client and server validation. It repeated the bug and filed MAT-209 on this morning's delivery board, ready for the next agent to pick up. No user had to report it.
That is how you ship fast without breaking things
You focus on your product. We bring the infrastructure for cloud runtime, agentic testing and production monitoring.
Loved by developers
Most AI-generated code is slop that goes nowhere. Anyone can write code, but building software that works is still hard and requires much more than the ability to prompt a model. I like what these guys just released. Keep your terminal and your coding agent, and use Coldtea to Show more
Been absolutely LOVING coldtea. Being able to seamlessly pass tasks between codex and claude has been such a hack. Also Ohans is one of the most cracked engineers i've ever met
Congrats on the launch! 🎉 Coding agents that can take care of entire SDLC and help ship with confidence is the future. I have seen cold tea qa agent taking care of fixes like a pro taking away all headaches. Well done team Cold Tea💫
The QA agents driving the real app is wild. Writing more code is a solved and a boring problem now haha
This is the future of agentic development.
This feels much closer to how developers actually ship software.
This could remove a lot of unnecessary tool switching.
The most powerful environment to ship with agents
Everything the work needs after an agent starts: parallel worktrees, an editor, annotations, tasks, QA and monitoring.
Parallel worktrees
One repo, many agents, zero collisions. Each run gets its own worktree on its own branch, so five attempts at one task never touch each other
Terminal splits that talk
Split the tab into panes, run an agent in each, and let them message each other. A builder and a reviewer, going back and forth until it is right
Every CLI agent
It is a real terminal, so anything that runs in one runs here. Claude, Codex, opencode, and whatever ships next month
An editor beside the terminal
Review and code in the same tab. Read the change, tweak a line yourself, hand it back to the agent
Annotate the diff
Point at the exact line, in the editor or in the terminal. The note lands with the agent, so it sees precisely what you meant
Shareable artifacts
A run can publish a page: a report, a preview, a doc. One link anyone on the team opens, with nothing installed
Tasks
Every task carries its implementation plan and session logs, so an agent picks up work knowing what the last one did. Syncs with Linear, Jira and GitHub issues
Monitoring
Connect the tools you already run: PostHog, Sentry, Vercel and the rest. What breaks in production comes back as work your coding agents pick up
QA testing
Agents drive your app in a real browser and hand back a verdict. On every pull request, or on a schedule you set
And everything you already expect
The loop is what makes Coldtea different. Here is the rest, so you are not left guessing.
Terminal
- Your shell, settings and dotfiles, set up for you
- Claude Code, Codex, Gemini CLI, OpenCode and more
- Agent teams that plan, build and review together
- A git worktree per task, so runs never collide
- MCP servers and your existing agent config
Cloud
- Background agents that run tasks off your laptop
- Many tasks in parallel, followed from one place
- Off by default. Your code stays local until you turn it on
Tasks
- Two-way sync with Linear, Jira and GitHub Issues
- Implementation plans and session logs on every task
- Board, backlog and workflow states built in
Built in
- An editor built in, so a diff never sends you elsewhere
- In-app browser you and your agents can both drive
- Annotate any pane or page and send it straight to an agent
- Monitoring across Sentry, Datadog, Grafana, New Relic, PostHog, Vercel
You keep everything you already use
Your editor stays your editor
Your shell is set up for you and your settings come across. Day one looks like every other day.
Your code stays on your machine
Cloud runs are there when you want them, and off until you do.
Your agents stay your agents
Coldtea is not another coding agent. It runs the ones you picked.
Get started for free
Free on the parts you open every day. No lock-in on the rest: your code stays on your machine, your agents stay yours, and we will not bill you for data you already pay for.
Terminal
Free forever
Every agent, every agent team, no seat count and no trial clock.
Monitoring
Free, bring your own keys
Your Sentry, your PostHog, your Datadog. Or bring your own AI keys.
Agentic testing
2,000 credits a month, free
Use them across web and mobile tests. Add more credits whenever you need them.
No sales call. No seat minimum. No contact-us tier.
macOS, Apple silicon and Intel.
Coldtea is an IDE, not a dashboard. It runs on your machine, right next to your repo, using the shell, agents and settings you already have. It is a new kind of agentic development environment: the terminal you work in every day, with testing and production monitoring built around it.
