Mengbi
Quality score 66Ctackle.jordandalton.com#agents#coding

Laravel Tackle — AI Coding Agents for Laravel

Laravel Tackle is an AI agent harness for Laravel: coding agents that read your codebase, run your tests, review your PRs, upgrade dependencies, and heal failed jobs — installed via Composer.

Visit website

About this tool

Laravel Tackle is an AI agent harness for Laravel: coding agents that read your codebase, run your tests, review your PRs, upgrade dependencies, and heal failed jobs — installed via Composer.

Key Capabilities

  • Coding agents: Classes implementing CodingAgent receive a prompt, call tools, and return a result.
  • Command suite: ai:code, ai:upgrade, ai:eval, ai:explain, ai:fix, ai:onboard, ai:respond, ai:review, ai:run, ai:test.
  • Dependency upgrades: ai:upgrade audits, plans, resolves, fixes, and verifies safe major version upgrades for Composer dependencies in an isolated worktree, delivered as a PR.
  • Code review: ai:review is a read-only agent that reviews git diffs and surfaces real issues with severity levels.
  • Test generation: ai:test generates a Pest test file for any class or method.
  • Issue fixing: ai:fix accepts a pasted exception, a Sentry issue (--sentry=ID), or a GitHub issue (--issue=N); the agent diagnoses, patches, and verifies the fix.
  • CI and cron: ai:run runs the same agent with no terminal attached: one task, a JSON result, and an exit code.
  • PR interaction: ai:respond acts on a /tackle comment left on a pull request: applies the requested change, pushes it to the PR branch, and replies in the thread.
  • Developer onboarding: ai:onboard provides a guided, read-only tour of the codebase and answers questions.
  • Benchmarking: ai:eval benchmarks the agent against seeded bugs — fix rate, false-fix rate, tokens, cost.

Architecture and Safety

  • Built on top of laravel/ai and provider-agnostic like it: Tackle runs on any provider laravel/ai supports with tool calling.
  • Every agent runs through the same tool infrastructure and safety layer.
  • NetworkExfiltrationGuard flags the exfiltration transport: outbound HTTP in agent-authored code, curl ... | sh, external curl/wget. Mode block (default), confirm, or off.

Usage and Configuration

  • Installed via Composer.
  • Publish the config: php artisan vendor:publish --provider="Laravel\Ai\AiServiceProvider".
  • Run php artisan ai:code and type a small test task to confirm everything connects.
  • Major upgrades are long sessions — consider raising AI_CODE_BUDGET beyond the default $1 before starting one.
  • Requires laravel/ai >=0.1 <0.11; laravel/ai 0.1.x itself requires PHP ^8.4; on PHP 8.3 Composer will resolve 0.2 or newer.

Open Source and Commercialization

  • Open-source, free.
  • Learning curve: medium.
Use cases
  • [ ] Publish the laravel/ai config: php artisan vendor:publish --provider="Laravel\Ai\AiServiceProvider"
  • [ ] Run php artisan ai:code and type a small test task to confirm everything connects.
  • 4' } - run: composer install --no-interaction --no-scripts - run: | php artisan ai:upgrade pestphp/pest \ --headless --output=json --no-worktree \ --ref-issue=${{ github
  • a human stays the trigger — read it and run php artisan ai:upgrade <package> to turn it into a PR, or wire up the unattended mode below
  • AgentsClasses implementing CodingAgent that receive a prompt, call tools, and return a result
  • ai:evalBenchmarks the agent against seeded bugs — fix rate, false-fix rate, tokens, cost
  • ai:explainExplains what a file, class, or method does in plain English
  • ai:fixA focused fix session: paste an exception, point it at a Sentry issue (--sentry=ID) or GitHub issue (--issue=N), and the agent diagnoses, patches, and verifies the fix

Features & use cases

[ ] Publish the laravel/ai config: php artisan vendor:publish --provider="Laravel\Ai\AiServiceProvider"[ ] Run php artisan ai:code and type a small test task to confirm everything connects.4' } - run: composer install --no-interaction --no-scripts - run: | php artisan ai:upgrade pestphp/pest \ --headless --output=json --no-worktree \ --ref-issue=${{ githuba human stays the trigger — read it and run php artisan ai:upgrade <package> to turn it into a PR, or wire up the unattended mode belowAgentsClasses implementing CodingAgent that receive a prompt, call tools, and return a resultai:evalBenchmarks the agent against seeded bugs — fix rate, false-fix rate, tokens, costai:explainExplains what a file, class, or method does in plain Englishai:fixA focused fix session: paste an exception, point it at a Sentry issue (--sentry=ID) or GitHub issue (--issue=N), and the agent diagnoses, patches, and verifies the fixai:onboardOnboards a new developer: a guided, read-only tour of the codebase — what it is, how it's put together, how to run it, where to be careful — then answers their questionsai:respondActs on a /tackle comment left on a pull request: applies the requested change, pushes it to the PR branch, and replies in the threadai:reviewA read-only agent that reviews git diffs and surfaces real issues with severity levelsai:runThe same agent with no terminal attached: one task, a JSON result, and an exit code — for CI and cron

At a glance

Monetization
  • Free
Maturity signals
  • Open source
Learning curve
  • Medium

Resources

⬆️Careful major upgradesai:upgrade audits what is upgradable, plans from the package's own upgrade guide, fixes the breaking changes, and verifies with your test suite — one reviewable PR per package.Guide

Sources

Every profile keeps its sources and latest verification date.
01https://tackle.jordandalton.com/

Similar tools

IRIS X AI
irisxai.in
88

IRIS X AI is a cross-platform voice assistant for desktop (IRIS-AI) and mobile (IRIS-MX) that uses hybrid cloud and local AI for hands-free automation. It controls media, system settings, scheduling, messaging, and web tasks by voice.

Paid · $20/mo

Open details
OSpec
ospec.ai
69

OSpec is a document-driven workflow for organizing AI-assisted development, validation, deployment, and delivery into a clear, trackable process. It uses natural language prompts with AI coding agents and CLIs, supporting spec-driven development (SDD).

Open details
Luma
lumalabs.ai
83

Luma is a Palo Alto-based multimodal AI system that combines reasoning and generation within a single model architecture. It offers an AI video generator, video from image, prompt-driven audio generation, and camera movement integration (crane, tracking shot, dolly). Creative agents embed in workflows to advance work end-to-end with shared context, enabling teams to work in parallel.

Paid · $30+/mo

Open details
Figma
figma.com
73

Figma is a build tool that connects design, code, and AI agents to help teams ship faster from prompt to PR.

Open details