Zest

Zest 2 · for you and your coding agents

Ship better
AI code.

AI coding analytics for engineering teams: the agents, models and skills behind your merged pull requests.

What you and your agents did today, in three rings, a three-line standup and your level.

npx @winding-labs/zest
Start free

Free for 3 seats · No credit card · Works with Claude Code, Codex, Cursor, VS Code and more

Sample data

The Zest app's Home tab

USED BY ENGINEERING TEAMS AT

Flyps Charm Wildfires Geoforge MisaLabs

Home · today so far

What you and your agents did today.

Open Zest and the day is already counted: three rings for AI tasks, AI time and agents ran, then build, bug and process hours against your usual week. Every number comes from your agents' sessions and GitHub, with nothing to fill in.

  • Rings fill as your sessions sync, on the phone and the web
  • Build, bug, upkeep and process hours, model-estimated, never timesheets
  • Spend against your Claude Max, Codex and GitHub Actions plans

Setup · one command

One npx. Every agent.

Run it once on your laptop. It finds the coding agents you use, opens your browser once to sign you in, and connects them all. With GitHub alone you already get a standup; your agents add the hours, the models and your level.

npx @winding-labs/zest
$ npx @winding-labs/zest
Found: Claude Code, Codex, Cursor
Opening your browser to sign in…
✓ Signed in as sam
✓ Claude Code · hooks added
✓ Codex · plugin added
✓ Cursor · extension added
Done. Your sessions sync as they end.

Bench · levels

Five levels, from Hand Coder to Code Factory.

Your last 30 days of sessions and GitHub put you on one of five levels, and the lemon gets better armor at each one. Bench shows where you stand, in percentiles, and the one unlock that gets you to the next.

  1. L0

    Hand Coder

    You write it; AI autocompletes. Zest still works from GitHub alone.

  2. L1

    Pair Programmer

    One agent at a time, editing and running things while you watch.

  3. L2

    Delegator

    Agents plan first and test themselves; you review the PR.

  4. L3

    Orchestrator

    Several agents at once, and agents review agents.

  5. L4

    Code Factory

    Agents start the work and report back.

Standups · fewer words

Three standups. Short ones.

Push, email and Slack carry all three. They read the same numbers, so they never disagree.

  • Yours, short until you press it: your day in three lines at 6pm.
  • Press it for the long one: every line, the tips, and what it was built with.
  • Your team's, people and agents in one list.
  • And your agents', written from their own sessions: what they decided, and what waits on you.
Sample data

Me: today's standup

Team · nobody manages teams

Share AI best practices with your team.

Teams appear from who works on which repos, with nothing to set up. The leaderboard shows who ships the most with agents, people and agents side by side, and the Library keeps the prompts and practices your team shares: how standups read, what to check each week, the questions worth asking.

  • Teams inferred from repos; the leaderboard stays inside your workspace
  • One Library of prompts and practices, written by your team
Sample data

Team: the leaderboard

Stack

See your AI stack.

Models, harnesses, skills and agents: see the setup behind the work. Stack scores how well yours is wired, lists the gaps that would raise the score, and shows your top model each week and every agent you've connected.

Sample data

Stack: your score and the gaps

Skills · from your team

Share the best AI skills.

Discover a teammate's shortcut and try it in your next session. Tap anyone on the leaderboard to see the techniques, skills, agents and MCP tools behind their week, and how often each one ran.

Sample data

Team: a teammate's skills

Timeline · what shipped

Celebrate what ships.

Make the work visible, and share the practice that made it possible. Standups, reports and merged PRs land on one timeline, and every session reads as a story: what shipped, the cheat codes it earned, and one thing to try next time.

  • Standups, reports and merged PRs on one timeline, newest first
  • Each session as a story card, with a Share button
Sample data

Timeline: what shipped

Ask Zest · the lemon button

Ask anything. Pin the answer.

Tap the lemon on any screen, or hold any card, and ask about it: "why was Tuesday slow?", "which skill saved the most time?", "is my Max plan worth it?". Answers come back as cards you can pin to Home, Me or Team.

Which agent burned the most tokens this week, and on what?

Codex on payments: 41% of your tokens, mostly two long runs on Thursday that re-read the same test logs.

Try: give it the failing test name up front. Pin to Home

Sample data

iOS · Android · web

Your standup, in your pocket.

The rings, your standup and the agents running right now, one glance away, and any answer pinned to your home screen. The web app at meetzest.com/app mirrors the phone, five tabs and the lemon.

Sample data
Sample data
Sample data
Sample data
Sample data
Sample data
Sample data
Sample data

The Zest app

Your data

Kept short. Never trained on.

Read the privacy policy

SIMPLE PLANS. ROOM TO GROW.

Start small.
Bring the whole team.

One workspace price. Seats included. Credits shared.

Starter

Try AI analytics

$0 per workspace per month

3 seats included

Get Started

No credit card needed.

  • Coding agent analytics
  • Models & Skills analytics
  • AI cheatcodes

Max

Scale AI analytics

$149 per workspace per month

10 seats included

Choose Max

Starts free on Starter, no card. Switch to Max from Billing.

  • Agentic product management
  • AI Feature + Ticket analytics
  • Cloud agent + Hermes

Enterprise

Custom credits + history · SSO/SCIM + audit controls · Data governance + custom retention · SLA + dedicated success

Talk to us

A head start for startups.

50% off Pro or Max for 6 months. Pre-Series A, under $2M revenue in the past 12 months.

Apply for the discount

A FEW THINGS TO KNOW

Questions

What does Zest help my team do?+

Zest shows what you and your coding agents did today: a short standup, your level from Hand Coder to Code Factory, your team's leaderboard and timeline, and the stack behind it, from your agents' sessions and GitHub.

What are “build hours”?+

These are model-estimated activity hours, including overlapping automation. They are not employee working hours, timesheets, or a measure of a person’s value.

Can we start for free?+

Yes. Starter is $0 per workspace per month with 3 seats included. You can choose a paid plan as your team’s needs grow.

What metrics does Zest track?+

Per engineer and per team: AI tasks, AI time and agents run each day, build, bug, upkeep and process hours, the models, skills and MCP tools each session used, tokens and list-price cost against your plans, and pull requests opened and merged, with PR throughput and cycle time from GitHub. Each engineer also gets a level, from L0 Hand Coder to L4 Code Factory. Zest has no DORA metrics.

Which tools can we connect?+

Claude Code, Cursor, VS Code (GitHub Copilot Chat), Codex, Hermes, Grok Build, OpenCode and Freebuff, each through its own Zest plugin or extension, and GitHub for pull requests. One command, npx @winding-labs/zest, finds the ones on your machine and signs them all in; each also has a setup guide in our docs.

What data leaves an engineer's machine?+

Each coding-agent session's prompts and replies, model, token counts, skills and tool calls, after secrets are redacted on the machine. Zest collects no code diffs. Raw logs are kept 30 days, analyzed sessions and cards 180 days, daily totals 400 days and weekly totals 3 years, and a workspace can shorten them.

Which Git hosts does Zest work with?+

GitHub only, through the Zest GitHub App. It reads pull requests, commits and their metadata, and never writes to your code. Zest has no GitLab, Bitbucket or Azure DevOps integration.

Is our data used to train AI models?+

No. We do not sell customer data, and no customer data is used to train AI models. Our sub-processors page names each company that handles data for us and what it does.

How do we set Zest up?+

Each engineer runs npx @winding-labs/zest once: it finds their coding agents, opens the browser once to sign in, and connects them all. Someone on the team installs the Zest GitHub App and picks the repositories, and teams appear on their own from who works on which repos.

Who makes Zest?+

Zest is made by a small team at Winding AI, Inc. Ilya Volodarsky, who co-founded Segment, is one of its co-founders. Several products share the name; this one is the AI coding analytics product at meetzest.com.