by kirodotdev
A persistent workspace for development work that self-improves and continues beyond one session.
# Add to your Claude Code skills
git clone https://github.com/kirodotdev/KiroCrewLast scanned: 8/5/2026
{
"issues": [
{
"file": "AGENTS.md",
"line": 87,
"type": "secret-exfiltration",
"message": "Instruction appears to send credentials/secrets to an external endpoint",
"severity": "medium"
},
{
"file": "README.md",
"line": 70,
"type": "remote-install",
"message": "Install command (remote install script piped to a shell — review the source before running): \"curl -fsSL https://download.crew.kiro.dev/cli.sh | sh\"",
"severity": "low"
},
{
"file": "skills/kirocrew-commands/SKILL.md",
"line": 219,
"type": "secret-exfiltration",
"message": "Instruction appears to send credentials/secrets to an external endpoint",
"severity": "medium"
},
{
"file": "src/kiro_crew/builtin_skills/artifacts/SKILL.md",
"line": 184,
"type": "prompt-injection",
"message": "Possible concealment directive: \"never tell the user\"",
"severity": "medium"
}
],
"status": "PASSED",
"scannedAt": "2026-08-05T06:27:21.249Z",
"npmAuditRan": true,
"pipAuditRan": true,
"promptInjectionRan": true
}KiroCrew is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by kirodotdev. A persistent workspace for development work that self-improves and continues beyond one session. It has 2,945 GitHub stars.
Yes. KiroCrew passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.
Clone the repository with "git clone https://github.com/kirodotdev/KiroCrew" and add it to your Claude Code skills directory (see the Installation section above).
KiroCrew is primarily written in Python. It is open-source under kirodotdev on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh KiroCrew against similar tools.
No comments yet. Be the first to share your thoughts!
You choose how to run Kiro Crew: the desktop app with automatic updates, a
one-line install on your machine or a remote host, the Docker image for
always-on servers, or a build from source. Every path runs on kiro-cli
underneath, so the first launch installs it if needed and guides Kiro
device-code sign-in.
The desktop app starts a bundled Gateway when no local Gateway is already running, updates itself on the channel you download, and can connect to a remote Gateway over an SSH tunnel. See the desktop app guide.
Not sure which Linux file you need? uname -m prints it — x86_64 or aarch64.
Every architecture below is a first-class lane: each gets its own build, its own
auto-update feed, and its own SLSA provenance attestation.
| Install path | x86_64 | aarch64 (ARM64) |
|---|---|---|
| Desktop AppImage | yes | yes |
| CLI one-liner / wheel | yes | yes (the wheel is py3-none-any; native libraries are vendored per architecture) |
| Docker image | yes | yes (linux/amd64 and linux/arm64 under every tag, so docker pull picks yours) |
Take Stable unless you have a reason not to — the table below says who each channel is for.
Every install path — desktop app, CLI, Docker image — offers the same three channels. Pick by how much churn you can absorb, not by version number:
| Channel | Who it's for | Built from | Cadence |
|---|---|---|---|
| Stable | Everyone. The default on every install path. | The Insider build that baked long enough to be promoted | On promotion, no calendar commitment |
| Insider | Power users who want features days to weeks early and accept the new bugs that come with them | Release-branch release-candidate tags | Every RC |
| Nightly | Us and contributors. Untested main HEAD — expect breakage. |
main, 06:00 UTC daily |
Daily |
Stable and Insider are two update lanes of the same app. The desktop app
switches between them in Settings → About, a CLI install switches by re-running
the installer with --channel, and a container switches by pulling a different
tag. Either way, the other lane's current version then arrives as an ordinary
update.
Nightly is a separate app with its own name and icon, so it installs alongside
a Stable or Insider one rather than replacing it. It is not a sandbox, though: it
reads the same ~/.kiro/crew data home unless you point it elsewhere with
KIROCREW_HOME.
Running Insider or Nightly is a real contribution. When something looks wrong, please open an issue so it gets fixed before it reaches Stable.
Install the prebuilt, SHA-256-verified wheel from the release CDN without
cloning the repository or running npm and a local build.
Stable, the default:
curl -fsSL https://download.crew.kiro.dev/cli.sh | sh
Track a faster channel, insider or nightly (see
Release channels for who each one is for):
curl -fsSL https://download.crew.kiro.dev/cli.sh | sh -s -- --channel insider
Pin an exact version:
curl -fsSL https://download.crew.kiro.dev/cli.sh | sh -s -- --version 0.1.0
Open http://localhost:5476 and start a conversation. The web dashboard works
without messaging credentials. Add a messaging channel —
Slack,
Discord,
Telegram,
Teams,
Webex,
WeCom, or
WeChat — when you want to continue
working with the same agent away from the dashboard. Apart from Teams (which
needs a public HTTPS webhook — see its guide), these channels connect
outbound, so you do not need to expose the dashboard port publicly.
For always-on servers, the Gateway ships as a public multi-arch image on GHCR:
docker run -d --name kirocrew \
-p 127.0.0.1:5476:5476 \
-v kirocrew-home:/home/kirocrew \
ghcr.io/kirodotdev/kirocrew:stable
See the Docker guide for first-run login, channel tags, and the container security model.
macOS and Linux require Python 3.10+, Node.js 22+ (24 LTS recommended), npm, and
kiro-cli. The first desktop or dashboard launch
can install Kiro CLI on the Gateway host and guide device-code sign-in before
chat opens. Windows is supported through a native source install; follow the
Windows guide instead of the shell steps below.
# 1. Clone and build Kiro Crew
git clone https://github.com/kirodotdev/KiroCrew.git
cd KiroCrew
make build
source .venv/bin/activate
# 2. Configure, verify, and start
kirocrew setup
kirocrew doctor
kirocrew gateway
Most agent sessions end when the chat closes. Kiro Crew runs continuously on hardware you control and keeps working between conversations.
Persistent. Sessions, memory, schedules, and task checkpoints survive Gateway restarts, and scheduled or reactive work continues without someone at the terminal.
Self-learning. Corrections and task failures become durable lessons. Preferences and project context carry into new sessions.
Self-evolving. Repeated patterns become reusable skills. Memory, lessons, and skills stay visible and editable, so each Kiro Crew grows more tailored to the person and work around it.
Runs where you choose. Your Mac, a local container, or a remote machine you control.
One Gateway, many surfaces. Work directly in the desktop app or web dashboard, or continue the same work from the CLI and messaging surfaces like Slack and Discord.
| Capability | What it gives you |
|---|---|
| Persistent sessions | Run concurrent, isolated conversations, resume them after Gateway restarts, search prior sessions, and carry recent context into new work. |
| Self-learning | Turn corrections and task failures into durable lessons that change late |