AI Agent Control Plane · Package Registry for AI Assets

The Package Registry & Control Plane for AI Agents

Stop copying and pasting prompts between laptops. AgentHub publishes, cryptographically signs, versions, and deploys AI agents, skills, and tools across your entire enterprise engineering organization.

Universal
Claude, OpenCode, Cursor
Signed Bundles
SHA-256 Digest Verification
Lockfile Driven
agenthub.lock.json
EU AI Act Ready
Full Audit Trail & Air-Gap

Enterprise Control for Modern AI Engineering

Built for engineering leaders who need disciplined version control, cryptographic supply chain security, and compliance across all AI workflows.

Immutable Versioned Asset Bundles

Publish AI prompts, agent personas, skill toolsets, and slash-commands as immutable, content-addressed bundles. What npm and crates.io do for code, AgentHub delivers for AI agents.

Cryptographic Publisher Signatures & Verifications

Every asset bundle is signed with enterprise cryptographic keys. Consumers and CI pipelines verify publisher identity and SHA-256 digests before anything touches developer machines.

Deterministic Dependency Locking (`agenthub.lock.json`)

Pin exact asset versions, manifest digests, and tool configurations in version-controlled lockfiles to ensure byte-identical agent behavior across developer laptops and CI/CD runners.

Universal Multi-Harness Deployment

Install published skills and agents into any agent harness with a single command: Claude Code, OpenCode, Cursor, Codex CLI, and GitHub Copilot each get the assets formatted for their native conventions.

Enterprise RBAC, Namespaces & Audit Logs

Granular namespace isolation, permission manifests, and complete audit logging of who published, approved, or downloaded each agent asset, ensuring full compliance with AI governance frameworks.

Air-Gapped Federation & Sovereignty (EU AI Act)

Federate between private internal hubs and export self-contained archive bundles across secure air gaps without leaking prompts or proprietary tools to public cloud registries.

CLI & CI/CD Workflow

One Unified CLI: `agenthub`

Define the skills and agent personas your project requires in `agenthub.json`. The CLI resolves exact dependencies, verifies cryptographic signatures, and generates the target layout for your team's coding agent of choice.

  • Immutable bundle downloads verified before writing to disk
  • Synchronizes prompt updates across entire engineering fleets
  • Connect API for automated CI/CD publishing and validation
# Add verified skill to repository
$ agenthub add core/skills/kubernetes-audit
✔ Resolved core/skills/kubernetes-audit@1.4.0
✔ Verified SHA-256 digest: 8f3a9e...
✔ Updated agenthub.lock.json
# Install into local agent harness
$ agenthub install
Installed 1 skill into .claude/skills/
Installed 1 skill into .opencode/skills/

How AgentHub Compares

Compare AgentHub against ad-hoc AI prompt management and unvetted tool sprawl.

FeatureAgentHub (PiLAB)Ad-Hoc / Shadow AI Tooling
Asset ManagementCentralized package registry with content-addressing & immutable versionsPrompts & skills copy-pasted in Slack, wiki docs, or untracked local folders
Security & ProvenanceCryptographic signatures, permission manifests, SHA-256 digest checksZero provenance: impossible to tell who wrote or modified a running prompt
ReproducibilityDeterministic lockfiles (`agenthub.lock.json`) guarantee byte-identical executionSilent drift across team members running different unversioned prompt files
Multi-Tool SupportOne command installs across Claude Code, OpenCode, Cursor, and CopilotManual reformatting required for each IDE and AI CLI tool layout
Governance (EU AI Act / NIS2)Immutable audit trail, role-based publish permissions, air-gap readyZero compliance visibility; shadow AI tool usage unchecked across organization
Hosting & Sovereignty100% Self-hosted Go service (`agenthub.pilab.hu`), on-premise or private cloudVendor lock-in on proprietary SaaS platforms with third-party prompt ingestion

Govern Your Enterprise AI Assets with AgentHub

Bring disciplined software engineering practices to your AI agent adoption. Deploy AgentHub internally, eliminate prompt drift, and maintain full compliance.

Follow us
All Rights Reserved
© 2011-2026
Progressive Innovation
LAB