APAI.runv0.1
v0.1 - see honest status before you trust anything here

Secure installs. Agent-ready by design.

Install LLM apps, tools, and skills with confidence. Every install gets a Capability Passport, an llm.txt manifest for agent discoverability, and optional MCP Gateway protection - so your agents can find and use what you install, safely.

$ apai search
$ apai install <package>
$ apai passport <package>
$ apai audit <package>
$ apai rollback <package>

Native install (Codex, Claude Code, Gemini CLI, Cursor, Local CLI). v0.1 CLI is scaffolded; real install behavior lands in Phase 1.

Install card (paste into chat)

Paste this into any LLM that does not have shell access to your machine - chatgpt.com, claude.ai, gemini.google.com, grok.com - and the model will load the Capability Passport and apply the package protocol. If you are using Claude Code, Codex, Cursor, Gemini CLI, or another tool-enabled agent, use apai install instead - it produces a durable install receipt.

Install https://apai.run/packages/prompt-preflight-starter for this chat. Load the capability passport, apply the protocol, and report what changed. Do not call paid APIs, request secrets, or perform destructive actions.

Install card source: https://apai.run/packages/prompt-preflight-starter/llms.txt

The problem

Most LLM tools are installed... but never truly used by agents.

You can download models, add frameworks, and connect tools easily. But when your agents try to discover or use them safely, especially in teams or production, things break down.

Microsoft APM, MCP Registry, OpenAI Apps SDK, Claude custom connectors, xAI Grok remote MCP, Gemini CLI extensions, GitHub agent skills. The install surfaces are multiplying. But the trust layer is missing.

Result: fragmented setups, credential sprawl, weak governance, and agents that underperform despite powerful tools installed.

How it works

Install securely. Agents discover intelligently. Execute safely.

1

Browse and install

Discover curated, verified LLM apps, tools, and skills in the registry. Every entry has a Capability Passport.

2

Secure by default

Every install is verified. Route through an MCP Gateway for governance, RBAC, and audit logging when needed.

3

Agent-ready instantly

Automatic llm.txt manifests and MCP wiring. Agents discover what you installed without manual configuration.

4

Govern and scale

Gateway dashboard for permissions, usage monitoring, audit log review, and team-scale control.

The differentiator

Capability Passport

Every APAI package has a passport: a plain-English declaration of what it can read, write, access, spend, expose, what approval it needs, what the scanner found, and how to roll it back. Read it before you install.

Capability Passport Spec v0.1 ->
APAI.passport.v0.1
reads: Current user prompt
writes: Local transcript only
accesses: No secrets, no paid APIs
spends: No direct spend
exposes: No prompt collection
approvals: Human approval before destructive actions
rollback: Remove adapter, no persistent state
scanner: clean

The trust stack

Three layers, one platform.

APAI combines verified installation, automatic agent discovery, and governed execution. Each layer works alone; together they make installed capabilities production-safe.

1

Verified installation

Curated directory. Capability Passport per package. Permission review before install. Install receipt with rollback command.

2

Agent discovery

Automatic llm.txt manifests for every install. Agents discover what is available without manual configuration. Combined with MCP for execution.

3

Governed execution

Optional MCP Gateway adds centralized RBAC, credential injection, audit logging, rate limits, and threat detection. Zero Trust for AI agents.

Install modes

Where the install lands.

LLMs install software all the time - npm, pip, brew, cargo, gh skill, gemini extensions, claude connectors. The honest distinction between install modes is not whether the LLM can install (it can), but where the install lands and who controls that storage.

Local-tool install

Lands on your machine. The agent executes the install (npm, pip, brew, cargo, gh skill, gemini extensions, or the APAI registry directly) and APAI wraps it with a Capability Passport, scanner findings, install receipt, and rollback command. Works in any LLM environment with shell access.

Claude CodeCodexCursorGemini CLIAiderLocal CLI

Cloud-sandbox install

Lands in the LLM provider's ephemeral sandbox. ChatGPT code interpreter, Claude.ai code execution, Gemini Workspace tools - the install happens in a session-scoped container the user does not own. APAI ships an install card the agent loads into the conversation; the agent runs the install inside the sandbox and APAI tracks the Passport but cannot persist a receipt outside the session.

ChatGPT webClaude.ai webGemini webGrok web

Remote-connector install

No software fetched anywhere. The agent adds a URL pointing at a remote MCP server, custom GPT, or ChatGPT app. APAI catalogs public connectors with their Capability Passports so users can read what the connector can do before adding it. Phase 6: mcp.apai.run as a governed gateway hosting APAI packages behind RBAC + audit logging.

Claude connectorsChatGPT Apps SDKGrok MCPCustom GPTs

APAI wraps the underlying installer on every source. apai install npm:left-pad runs npm install left-pad and attaches the Passport + receipt + scanner. Same pattern for pip:, brew:, cargo:, gh:, gemini:, claude:, hf:, mcp:. Multi-source routing lands in Phase 1; v0.1 ships the scaffold.

Seed registry

Ten reference packages

v0.1 seed registry. Each has a full Capability Passport and LLM-readable install card. External MCP servers, Claude connectors, Gemini extensions, and ChatGPT apps we track but do not review are at /catalog.

View all 10 ->

Built for how you ship

Three personas. One platform.

Individual developers

  • ·One-click installs for popular tools
  • ·Automatic llm.txt + MCP wiring
  • ·Strong local-first (Ollama, LM Studio)
  • ·Clean, auditable install history

Teams and startups

  • ·Shared approved package catalog
  • ·MCP Gateway with RBAC
  • ·Collaboration + audit logs
  • ·Fast onboarding for new members

Enterprise

  • ·Self-hosted and air-gapped deploy
  • ·Advanced RBAC and policy controls
  • ·SSO + corporate identity
  • ·Private tool registries

Beta open

Private team registry

Approved package catalogs, install receipts, role-based approvals, blocked-package lists, and audit exports. Built for teams that need to control what their AI agents can install, access, run, remember, spend, and change.

Specifications

APAI v0.1 spec set

Five versioned spec documents. Manifest, Capability Passport, Install Receipt, Policy Pack, and Prompt-URL-Install. JSON Schemas available at /spec.

Ready to make your LLM tools agent-native, securely?

Install with confidence. Give your agents the ability to discover and act safely.