Suggestions appear as you type. Use the up and down arrows to choose one and Enter to open it.

This page's audience our own tag's counts — open to see them
–Visits
–Page views
–Clicks to vendors
–Time on page
–Reading now
Clicks to vendors, by tool
  • –
Top countries
  • –
Devices
  • –

– · visits, page views and clicks counted by our own tag, which counts more than our checked analytics; every figure rounded down · how we count

Tank review

Free#31 of 92 in Package Managers

A specialized, open-source package manager for distributing AI-agent packages.

6.2/10Editor score
Visit Tank
Tank6.2 Visit Tank

Reviewed by iTechGuides Editors · Editorial team · Updated Oct 2026

Tank is an open-source package manager and registry built for AI-agent skills and reusable agent packages. It supports packages such as instructions, hooks, tools, agents, rules, resources, prompts, and bundles. CLI installation, public and self-hosted registries, API access, and private registry authentication make it relevant to individuals and organizations distributing agent components across Claude Code, Cursor, GitHub Copilot, Codex, Windsurf, OpenCode, Cline, and Roo Code.

Its strongest case is controlled package distribution. Tank resolves transitive dependencies, applies semantic versioning, and creates deterministic tank.lock lockfiles. SHA-512 package integrity verification adds a defined check on package contents, while permission budgets cover network, filesystem, and subprocess access. The six-stage security scanning pipeline and escalation detection add further controls, and the Credential Vault is designed to protect agent credentials. These features suit teams that need reproducible installations and explicit boundaries around what agent packages can access.

The published offering is open source, with the registry, CLI, and security scanner available free under the MIT license. GitHub Actions publishing, an MCP server for AI editors, and integrations across the listed coding environments extend Tank beyond a local installer. Its narrow focus is also the main constraint: teams seeking a general-purpose package manager, broader software ecosystem, or offline workflows should choose another tool. Tank is a fit for developers and organizations standardizing AI-agent package delivery, especially where dependency control and security checks matter more than broad package coverage or established maturity.

Tank pros and cons

  • Where it wins
    • Deterministic tank.lock files with SHA-512 integrity verification
    • Permission budgets and a six-stage security scanning pipeline
    • Works across major AI editors with public or self-hosted registries
  • Where it doesn't
    • Focused on AI-agent packages rather than general software dependencies
    • No offline support for package workflows
    • Maturity is still unverified for teams needing an established ecosystem

Tank fact sheet, pricing and score →

Advertiser disclosure: iTechGuides is reader-supported. Vendors can pay for top positions in our rankings and for a place on other products' pages, and we may earn a commission when you click some links. Bought places stand at the number bought; this page and our disclosure say so. Paying vendors may get a fuller, more detailed review from our editors, and that review can change their score. How we rank.

Last updated · How we research and update