Skip to content
Agents tracked: 501 Releases (7d): 777 Agent status: no reported issuesSince last limit reset: Claude 10d · Codex 8d For AI agents: Markdown Updated Nov 21, 2026

KaneAI by TestMu AI (formerly LambdaTest)

Writes, runs and updates web and mobile tests from natural-language instructions and requirement documents, with self-healing and result analysis. The open-source Kane CLI exposes it to developers and coding agents.

AI testing and QA agents End-to-end testing agent (cloud and Kane CLI)ProprietaryFree to start

Use it in: Web app CLI Works with: Headless / CI

Price
Free
free tier available
Popularity
#5 in Testing
Gid Score 16 / 100 · #244 of 255 ranked AI agents
Trend
Growing fast
downloads up 68.6% over 30 days · up 25.2% last week
Development
Actively updated
latest 0.10.7, yesterday
Community
267 GitHub stars
1,925 package downloads a week

Usage data: latest readings Nov 19 to Nov 21, 2026, last checked Nov 21, 06:27 UTC. Date of each number

What KaneAI does

KaneAI is an end-to-end testing agent (cloud and Kane CLI) from TestMu AI, first released in August 2024. You use it through a web app and a command-line tool on macOS, Windows and Linux. Its documentation covers a non-interactive mode for scripts and CI. It has a free tier.

Key facts

MakerTestMu AI (formerly LambdaTest)
TypeEnd-to-end testing agent (cloud and Kane CLI)
First releasedAugust 2024
LicenseProprietary (the LambdaTest/kane-cli repository on GitHub is Apache-2.0)
InterfacesWeb app, CLI
PlatformsmacOS, Windows, Linux
Main languageJavaScript
Open issues and PRs89

Pricing

KaneAI: Starter $17, Pro $89, Max $179 per month billed annually (2,000/12,000/25,000 credits per agent); Enterprise custom. Test Manager: Free tier available; Premium $49/month; Enterprise custom.

Source: official pricing page, checked Oct 15, 2026. Prices change often; confirm before you buy.

Compare prices of all agents

Quick answers

  • Free to start?Yes
  • Open source?No
  • Runs onmacOS, Windows, Linux
  • Where you use itWeb app, CLI
  • Runs in scripts / CI?Yes
  • Feature comparisonAll agents
  • Closest alternativeMomentic · all alternatives

What's new in KaneAI: November 2026 so far

Full monthly summary

November brought major improvements to reliability, diagnostics, and remote execution for KaneAI. The release focused on fixing silent failures, improving error messages, and ensuring consistent behavior across local and remote runs.

Action needed: Telemetry is now always on with no opt-out option.
  • Scroll steps now properly fail when they don't actually move the page, eliminating silent successes.
  • Commands and sessions now emit lifecycle events and detailed error codes, making run behavior visible and debuggable.
  • Real devices can reach private backends through LT tunnels, expanding remote testing capabilities.
  • Telemetry now tracks healing attempts accurately, and replayed runs report matching stability numbers.

6 releases this month · summarised from the official release notes · all months

AgentGid articles about KaneAI

All guides

Get started with KaneAI

npmnpm install -g @testmuai/kane-cli

These commands use the packages tracked on this page. The vendor may recommend a different installer; see the official documentation.

Compare KaneAI with another agent

vs
# Agent Gid Score Downloads 7d 7d 30d Stars Latest release Price
23
MomenticMomentic
56 939K up 213.7%One-day spike up 112.0% — — Free + $500/mo
39
e2ee2e (formerly TesterArmy)
51 1.6M up 88.4% — 14.1K+40/day 0.24.02d ago Free (OSS)
82
mablmabl Inc.
41 12.6K up 2.1% up 7.6% — — Custom
157
ChecksumChecksum
312/4 19K up 11.0% up 30.5% — — Custom
255
QA WolfQA Wolf, Inc.
52/4 — — — — — Free + $1/mo
—
ItoPromoIto Inc.
— — — — — — $40/mo

Head to head: KaneAI vs Momentic · KaneAI vs e2e · KaneAI vs mabl · KaneAI vs Checksum

Ratings from people who use KaneAI

No ratings yet. Used KaneAI? Rate it and say what it is good and bad at.

KaneAI news

All AI agent news

  1. Release GitHub Releases

    KaneAI 0.10.7 released

    Mark the bugs a test hits — the new kane-cli bugs commands record known bugs against a test, and the next RCA run reads them instead of starting from scratch.; Your org's own RCA categories — kane-cli bugs categories lists the available root-cause categories…

  2. Release GitHub Releases

    KaneAI 0.10.6 released

    A scroll that moves nothing now fails — authoring scrolls, coordinate (vision) scrolls, and scrolls that never ran are reported as failures, the same way a locator click that misses one is…; Until-scrolls fail when the condition is never met — no more runs…

What changed: recent KaneAI releases

25 stable releases in the last 90 days · Monthly summary · Full changelog

0.10.7
  • Mark the bugs a test hits — the new kane-cli bugs commands record known bugs against a test, and the next RCA run reads them instead of starting from scratch.
  • Your org's own RCA categories — kane-cli bugs categories lists the available root-cause categories and lets you add and manage the ones specific to your organization.
  • Known bugs and categories show up in results — the known bug ID and the org category name are carried through to failure.yaml, so triage output matches what you recorded.
  • Take back feedback the same way you gave it — kane-cli bugs retire now makes it clear that feedback can be withdrawn regardless of how it was submitted.
  • Name an exploration when you start it — kane-cli explore run --name <name> labels the exploration it creates, and the name follows through to the export so runs are easy to find later.
  • Retries keep their identity — retrying an exploration without passing a name no longer loses track of it.
0.10.6
  • A scroll that moves nothing now fails — authoring scrolls, coordinate (vision) scrolls, and scrolls that never ran are reported as failures, the same way a locator click that misses one is…
  • Until-scrolls fail when the condition is never met — no more runs that scroll forever and then move on as if they succeeded.
  • Scroll detection reaches further — scrollable regions inside cross-origin (out-of-process) iframes, dialogs in front of the page, and <body> scrolling under a locked <html> are all detected and…
  • Text-mode page output shows what scrolls — the page document lists scrollable containers, so you can see what the agent has to work with.
  • Scroll results are judged on scroll offsets — the screenshot comparison is gone, so a visually similar page no longer hides a scroll that never happened.
  • Pool variables per member — a --remote job names each member's pool variables and carries their secrets from the vault, so remote runs behave like local ones.
Earlier releases
0.10.5
  • Heal counts come from the real heal chain — the number of self-healing attempts in a run is read directly off the heal call chain, so the totals shown match the steps kane-cli actually took.
  • Replayed runs report the same stability numbers — telemetry for stability and self-healing is carried through replay, so a replayed run no longer shows different stats than the original.
  • If/else branches compare the right value — exported automation code now compares the operand from your step instead of an empty string, so conditional branches behave the same in exported code as…
0.10.4
  • Commands report their own lifecycle — every command emits a start and end event, including run, testmd run and explore, so a run's shape is visible even if it dies early.
  • Sessions say what they are and how they ended — session start records the surface and target; session end records the outcome, including sessions that exit without finishing.
  • Failures carry an error code, a domain and the actual error — no more guessing from a bare stack trace, and a testmd run that throws now logs why before closing its session.
  • Ctrl+C is recorded as a signal exit, not a crash — interrupting a run no longer pollutes your history with phantom crashes.
  • Telemetry is always on — there is no opt-out, and usage before login is attributed by machine id.
  • A failed test is not a CLI error — test failures and CLI failures are now reported on separate lanes, so scripts and CI can tell them apart.
0.10.3
  • Real devices can now reach private backends through your LT tunnel. Pass --tunnel or --tunnel-name <name> to run, testmd run or testrun run.
  • On web, a type step can ask for a delay, so fields that ignore a normal fill are typed key by key. The delay carries through replay, upload and code export.
  • Android vision taps now map to full-display pixels.
  • Mobile API calls keep their timeout in milliseconds.
  • A session that can't be saved now says why, instead of "No test_id available".
  • When a test can't be created, Test Manager's own message is shown.
0.10.2
  • Python steps trust what kane-cli trusts — the certificate bundle is handed to Python programs as SSL_CERT_FILE, so runs behind a TLS-inspecting proxy or corporate network no longer fail with…
  • A broken trust file can't poison a run — if the configured trust file is missing or invalid, it is never passed along to Python programs instead of being handed over and failing mid-run.
  • Locator actions say why they failed — instead of a bare "action failed", the error names the reason, so you can tell a missing element from a blocked click without digging through logs.
  • Vision-based select no longer claims false success — if a dropdown selection didn't actually take, the step reports it as a failure.
  • Reworded labels don't throw off selection — when a dropdown option's label is only rephrased (same option, different wording), kane-cli keeps the existing select instead of discarding it and…
  • Evidence is sealed as captured — secret redaction no longer runs over the evidence pack before sealing, so the sealed pack matches exactly what was recorded during the run.

KaneAI popularity and usage data

KaneAI was downloaded 1,925 times from npm in the week ending Nov 19, 2026, up 25.2% on the week before and up 68.6% over the last 30 days compared with the 30 before. The GitHub repository has 267 stars, 16 of them added in the last 30 days. The latest stable release is 0.10.7, published Nov 20, 2026; there were 7 stable releases in the past 30 days. It was mentioned in 1 Hacker News posts and comments over the last 30 days.

Downloads per daynpm, 7-day average 275/day
GitHub starsrunning total 267
Hacker News mentionsposts and comments, rolling 7-day total 1 this week

Download the raw daily series: kaneai.csv

Gid Score breakdown

Adoption6
Community0
Attention0
Momentum84

Gid Score shows public popularity and activity (usage, GitHub stars, mentions, growth), not the quality of the product. Each component is scored 0 to 100 from public signals; a dash means no data for it. How the Gid Score works.

How fresh these numbers are

NumberLatest readingLast checked
Package downloadsNov 19, 2026Nov 21, 06:21 UTC
GitHub starsNov 21, 2026Nov 21, 06:27 UTC
Hacker News mentionsNov 20, 2026Nov 21, 06:27 UTC

We fetch every source once a day. Registries publish downloads and page views a day or two late, so their latest reading trails the check. A reading more than 4 days old is marked out of date; the Gid Score still uses it until a newer one arrives.

KaneAI FAQ

How much does KaneAI cost?

KaneAI: Starter $17, Pro $89, Max $179 per month billed annually (2,000/12,000/25,000 credits per agent); Enterprise custom. Test Manager: Free tier available; Premium $49/month; Enterprise custom.

Is KaneAI open source?

No. KaneAI is a proprietary product from TestMu AI (formerly LambdaTest).

How popular is KaneAI?

KaneAI was downloaded 1,925 times from npm in the week ending Nov 19, 2026, up 25.2% on the week before and up 68.6% over the last 30 days compared with the 30 before. The GitHub repository has 267 stars, 16 of them added in the last 30 days. The latest stable release is 0.10.7, published Nov 20, 2026; there were 7 stable releases in the past 30 days.

What is the latest version of KaneAI?

The latest stable release we track is 0.10.7, published on Nov 20, 2026.

What are the alternatives to KaneAI?

The closest alternatives in the same category by Gid Score are Momentic, e2e, mabl, Checksum.

For the makers of KaneAI badges, corrections

Add a live badge to your README or site:

AgentGid: #5 in Testing Gid Score: 16/100 downloads: 1,925/week ▲69% 30d

[![AgentGid: #5 in Testing](https://agentgid.com/badges/kaneai-rank.svg)](https://agentgid.com/agents/kaneai/)
[![Gid Score: 16/100](https://agentgid.com/badges/kaneai-score.svg)](https://agentgid.com/agents/kaneai/)
[![downloads: 1,925/week ▲69% 30d](https://agentgid.com/badges/kaneai-downloads.svg)](https://agentgid.com/agents/kaneai/)

Something wrong or outdated on this page? Send a correction with a link to the official source. More for makers.

Where these numbers come from

npm: @testmuai/kane-cli. GitHub: LambdaTest/kane-cli. See data sources for how each one is collected.

Product facts and pricing were checked against: testmuai.com, github.com.