tigusigalpa/ai-kit repository overview

⁠AI-KIT

Give your AI coding agents persistent project context, reusable skills and a consistent engineering workflow.

AI-KIT installs portable project instructions, stack profiles, client configuration and optional skills into your repository. It helps coding agents understand your project, preserve decisions, follow your conventions and verify their work.

The Docker image packages the installer and CLI helpers with Python, Git, templates and integration resources. You can use AI-KIT without installing Python on your host.

Current image: tigusigalpa/ai-kit:1.4.3

Published platform: linux/amd64

Source: github.com/tigusigalpa/ai-kit⁠

⁠What AI-KIT provides

AI-KIT installs instructions and supporting tools. Your coding client performs the development work.

⁠What changed in v1.4.3

This image refresh includes the 1.4.2 and 1.4.3 CLI, packaging and release improvements since the previous Docker Hub image, 1.4.1.

• Versioned CLI: aikit --version reports aikit 1.4.3; the package version and image label must agree.
• Python package availability: AI-KIT is also published as ai-kit-python on PyPI⁠. The image already includes the CLI and resources; host Python installation is optional.
• Owner-approved package releases: a stable GitHub Release runs checks and prepares the Python package, then waits for the owner's approval before Trusted Publishing. Future canonical release tags are supported; manual validation remains available. Running this container does not publish a package.
• Packaging checks: isolated builds and regression tests verify archive resources, metadata, licenses, private-file exclusion and fresh installation. Published PyPI wheel/source hashes were checked against the successful workflow artifacts.
• Updated documentation: current package status, release and recovery instructions, a live PyPI badge, and this refreshed Docker guide.

⁠Project privacy and existing features

Root AI-KIT maintainer AGENTS.md, PROJECT_CONTEXT.md and WIKI.md are excluded from the build context and Python distributions. Their application template counterparts remain included. Private dialogue memory, journals, design output, credentials and personal client configuration also stay outside the image.

Shared dialogue memory, Web Design, Context7, both security integrations and preservation-aware installation remain available. Existing image versions remain usable.

⁠Image verification

Verified on 2026-10-16: 368 packaged Linux tests, 366 passed and two Windows-only skips. Docker smoke passed offline/read-only operation, installation and refusal, all optional modules, file preservation, stable reruns, actual context exclusions and SIGTERM. Root maintainer files were absent, template counterparts present, and prepared file hashes matched the installed image.

The public registry digest, Linux manifest and configuration match the tested build. Pulling by digest and running aikit --version and the bundled kit check succeeded. The published tag⁠ and immutable pull example below identify this build.

⁠Pull and check the image

Docker must be running with Linux-container support.

docker pull tigusigalpa/ai-kit:1.4.3

Check the CLI version and help:

docker run --rm --init --network none --read-only tigusigalpa/ai-kit:1.4.3 --version

docker run --rm --init --network none --read-only \
  --cap-drop ALL \
  --security-opt no-new-privileges \
  --tmpfs /tmp:rw,nosuid,nodev,size=256m \
  tigusigalpa/ai-kit:1.4.3 --help

Arguments after the image name go directly to aikit. Running the image without arguments displays CLI help.

The commands below disable runtime networking. Pulling the image still requires registry access.

⁠Install into a project: Linux or Bash

Choose an existing application directory. Run as an ordinary host user so the forwarded UID/GID is non-root.

app_path="$(cd /absolute/path/to/my-app && pwd)"
image="tigusigalpa/ai-kit:1.4.3"

runtime=(
  --rm --init
  --network none
  --read-only
  --cap-drop ALL
  --security-opt no-new-privileges
  --tmpfs /tmp:rw,nosuid,nodev,size=256m
  --user "$(id -u):$(id -g)"
)

Preview the installation with a read-only project mount:

docker run "${runtime[@]}" \
  --mount "type=bind,source=$app_path,target=/workspace,readonly" \
  "$image" install /workspace --agent codex

After reviewing the preview, apply using a writable project mount:

docker run "${runtime[@]}" \
  --mount "type=bind,source=$app_path,target=/workspace" \
  "$image" install /workspace --agent codex --apply --check

Check the installed project later:

docker run "${runtime[@]}" \
  --mount "type=bind,source=$app_path,target=/workspace,readonly" \
  "$image" doctor /workspace

Files written into /workspace persist in the mounted host directory after the container exits.

⁠Install into a project: Windows PowerShell

Use an existing application folder accessible to Docker Desktop.

$appPath = (Resolve-Path -LiteralPath 'C:\Projects\my-app').Path
$image = 'tigusigalpa/ai-kit:1.4.3'

$runtime = @(
    '--rm', '--init',
    '--network', 'none',
    '--read-only',
    '--cap-drop', 'ALL',
    '--security-opt', 'no-new-privileges',
    '--tmpfs', '/tmp:rw,nosuid,nodev,size=256m'
)

Preview:

docker run @runtime `
  --mount "type=bind,source=$appPath,target=/workspace,readonly" `
  $image install /workspace --agent codex

Apply after reviewing the preview:

docker run @runtime `
  --mount "type=bind,source=$appPath,target=/workspace" `
  $image install /workspace --agent codex --apply --check

Check the installed project:

docker run @runtime `
  --mount "type=bind,source=$appPath,target=/workspace,readonly" `
  $image doctor /workspace

The image uses UID/GID 10001:10001 by default. Docker Desktop file sharing must permit access to the mounted folder.

⁠Enable optional modules

Optional modules are selected explicitly and remain independent of installation presets.

For example, in the Bash session above, preview a Codex and Claude Code installation with all four modules:

docker run "${runtime[@]}" \
  --mount "type=bind,source=$app_path,target=/workspace,readonly" \
  "$image" install /workspace \
  --agent codex --agent claude \
  --with-web-design \
  --with-context7 \
  --with-security-audit \
  --with-strix

To apply that selection, use a writable project mount and append --apply --check, keeping the same agent and module options.

Installing these modules does not start a security scan, connect an MCP server or invoke a model. External tools and client activation are configured separately.

⁠Shared context from conversations

AI-KIT can import two local dialogues and prepare a shared reference state.

Supported inputs include:

• ChatGPT-style conversation JSON with explicit conversation or branch selection when needed.
• OpenRouter-style messages JSON.
• UTF-8 text or Markdown transcripts from other clients.

The workflow is:

1. Import each conversation into a private workspace.
2. Merge the imports and generate a review worksheet.
3. Review claims and resolve explicit contradictions.
4. Export ChatGPT Markdown and/or an OpenRouter JSON request fragment.

Explore the commands without mounting any project:

docker run "${runtime[@]}" "$image" memory --help
docker run "${runtime[@]}" "$image" memory import --help
docker run "${runtime[@]}" "$image" memory merge --help
docker run "${runtime[@]}" "$image" memory export --help

Imports, merges and exports preview by default; --apply writes local artifacts. Use a writable mount for the workspace and readable mounts for source transcripts.

Normal exports require review. Explicit draft exports can retain pending claims and unresolved alternatives. Free-form semantic disagreements require human review.

ChatGPT output is reference Markdown for manual use. OpenRouter output contains a reference message for your own client to include in a request. This workflow does not synchronize accounts, upload conversations or execute API calls.

See the shared dialogue context guide⁠.

⁠Other useful commands

Using the Bash runtime options defined above:

# Show CLI help.
docker run "${runtime[@]}" "$image" --help

# Validate the bundled AI-KIT distribution.
docker run "${runtime[@]}" "$image" check

# Inspect a routing recommendation.
docker run "${runtime[@]}" "$image" route "review an interface"

# Show provider records.
docker run "${runtime[@]}" "$image" providers

check validates the bundled distribution. doctor /workspace examines an installed application project.

For a project with Web Design enabled:

docker run "${runtime[@]}" \
  --mount "type=bind,source=$app_path,target=/workspace,readonly" \
  "$image" context select /workspace --workflow web-design

Context selection reports the relevant files and their scope. It does not send them to a model.

⁠Runtime contract

The image is a CLI workload. Each invocation runs a command and exits.

Python, Git and AI-KIT resources are bundled. Application toolchains, browsers, Node.js, Composer, model runtimes, MCP connections and the Strix executable are separate.

The examples use a read-only container root and explicit project mounts. Preview commands can use read-only mounts; installation and other explicit writes require writable mounts.

⁠Updates and reproducible references

To update a project, pull the selected image version, preview installation against the same project folder and review any conflicts before applying.

Existing project documents, settings, private dialogue memory and local edits retain the normal preservation rules.

For an immutable reference to this verified build:

docker pull tigusigalpa/ai-kit@sha256:0fd8de4396438e6250d29b44d342642bd4593b325eaf9983de2b637a3df12ea6

Use the explicit version tag or digest. Existing 1.4.0/1.4.1 tags were retained; this release did not assign a latest tag. Publication receipts added after building are a later documentation snapshot than the bundled files.

⁠Documentation and license

• Source repository and README⁠
• Docker usage⁠
• Web Design⁠
• Shared dialogue context⁠
• OpenRouter guidance⁠

AI-KIT is licensed under MIT. Bundled Cloudflare references retain MIT licensing; bundled Strix references retain Apache-2.0 licensing.