> ## Documentation Index > Fetch the complete documentation index at: https://docs.agentvolumes.org/llms.txt > Use this file to discover all available pages before exploring further. # Introduction to Agent Volumes > Agent Volumes is the open standard for packaging, distributing, and verifying components for AI agent runtimes — skills, tools, hooks, MCP servers, and more. Agent Volumes Organization logo banner Agent Volumes Organization logo banner Agent Volumes defines a runtime-neutral packaging and distribution standard for AI agent components. AI agent runtimes — Claude Code, Codex, Gemini CLI, Cursor, and others — increasingly rely on skills, tools, hooks, MCP servers, and LSP servers to extend their capabilities. Agent Volumes gives those components a shared package format, identity model, versioning model, and verification path. Use the version selector to jump to a published release archive, or use this page to understand the standard before browsing the current release candidate. Release-specific reference pages live under immutable `/spec//...` archive paths. Open the archive index for release evidence, citations, and historical lookup. Browse the current non-draft archive for Agent Volumes `v0.1.0-rc.1`. Create your first volume and understand the validation path before publishing. Map the v0.1.0-rc.1 artifacts to client, bibliotheca, validator, and exporter work. Route specification feedback, pull requests, security reports, and community conduct concerns. Read the current Registry API orientation, then follow the frozen release archive for details. ## What Agent Volumes is Agent Volumes functions analogously to established package ecosystems such as npm for JavaScript, PyPI for Python, and crates.io for Rust. The difference is that instead of packaging libraries or binaries, you package **agent components** — the skills, tools, agents, hooks, commands, MCP servers, and LSP servers that run inside AI agent runtimes. The distribution unit is a **volume**: a versioned package that usually exports agent components, or that can bundle dependencies without mandatory components when it uses `role = "meta"`. Registries that host and serve volumes are called **bibliothecas**. You interact with them using compatible client tooling such as the `shelf` CLI. ```bash theme={null} shelf add research-agent-pack ``` ## The three problems Agent Volumes solves Each runtime defines its own component layout. Developers rewrite the same skill, tool, or MCP server for every runtime they want to support. Agent Volumes gives you one package format that compatible runtimes can consume. Agent components have no standard identifier, versioning model, or provenance chain. Organizations cannot audit what runs inside their agent systems. Agent Volumes assigns every volume and component a globally unique, purl-compatible identifier. Without content integrity verification or publisher identity, every installation is an implicit trust decision with no revocation or advisory mechanism. Agent Volumes treats supply chain integrity as a first-class concern. ## Key terminology | Term | Description | | ------------------ | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **Agent Volumes** | This specification. The open standard for packaging and distributing AI agent components. | | **Volume** | The distribution unit. A versioned package that usually exports agent components, or a dependency bundle when `role = "meta"`. Analogous to an npm package or Python wheel. | | **Bibliotheca** | A registry that indexes, hosts, and serves volumes. Analogous to npmjs.com or PyPI. | | **volume.toml** | The package manifest file. Declares the volume's metadata, components, dependencies, and compatibility. Analogous to `package.json` or `Cargo.toml`. | | **pkg:volume/...** | The [purl](https://github.com/package-url/purl-spec)-compatible identifier scheme for volumes and components. For example: `pkg:volume/research-agent-pack@1.4.0`. | ## The seven component types Volumes that export components use one or more of seven component types: An autonomous runtime actor with a system prompt, tool bindings, and the ability to make multi-step decisions independently. Instructional knowledge loaded into an agent's context. Teaches the runtime how to perform a specific task without executing code directly. A user-invokable slash command, such as `/review`. Triggered explicitly by the user, not called programmatically by the agent. A function-call endpoint the agent calls programmatically during task execution. Has defined inputs and outputs and is stateless per invocation. A lifecycle event handler triggered automatically by the runtime at specific points, such as `PreToolUse`, `SessionStart`, or `FileChanged`. A service endpoint implementing the [Model Context Protocol](https://modelcontextprotocol.io/). Runs as a long-running process communicating over stdio, SSE, or streamable HTTP. A service endpoint implementing the [Language Server Protocol](https://microsoft.github.io/language-server-protocol/). Provides code intelligence for language-aware runtime operations. For full semantics, invocation rules, and entrypoint formats for each type, see [Component Types](/spec/0.1.0-rc.1/components/overview). ## Release and archive routes * `/spec/latest/` and `/spec/current/` redirect to the latest non-draft release archive. * The current non-draft release archive is [`/spec/0.1.0-rc.1/`](/spec/0.1.0-rc.1/). * The archive selector is [`/spec/`](/spec). * Older non-draft release archives remain reachable after newer releases are published. * Use versioned archive pages as durable citation targets. `/spec/latest/` and `/spec/current/` are convenience aliases only. ## Implementation projects The **shelf** CLI is the reference client implementation maintained by Windlass. It is intended to demonstrate [the Agent Volumes client contract](/spec/latest/specification-authority), including publishing volumes, resolving dependencies, verifying content integrity, and managing trust metadata. The **Alexandria** bibliotheca is the reference registry implementation, also maintained by Windlass. It is intended to demonstrate [the Agent Volumes Registry API](/spec/latest/api/overview), including package operations, version discovery, trust upload, and capability metadata endpoints. shelf and Alexandria are downstream implementation projects, not governance artifacts of the Agent Volumes Organization. They demonstrate the specification in practice but do not define it. ## Related standards Agent Volumes builds on and integrates with established standards rather than reinventing them: | Standard | Relationship | | --------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------- | | [Package URL (purl)](https://github.com/package-url/purl-spec) | Volume identifiers are purl-compatible using the `volume` type. | | [Semantic Versioning 2.0.0](https://semver.org/) | All volume versions follow SemVer. | | [CycloneDX](https://cyclonedx.org/) | The normative BOM exchange format for Agent Volumes interoperability. | | [SLSA](https://slsa.dev/) | The baseline provenance model for publish and verification workflows. | | [Sigstore](https://www.sigstore.dev/) | The baseline trust mechanism for signing and verifying provenance-attached artifacts. | | [Model Context Protocol (MCP)](https://modelcontextprotocol.io/) | MCP Server is a first-class component type; protocol compatibility declarations reference MCP versions. | | [Language Server Protocol (LSP)](https://microsoft.github.io/language-server-protocol/) | LSP Server is a first-class component type. | | [Agent Skills Specification](https://agentskills.io/specification.md) | Skill component entrypoints follow the Agent Skills SKILL.md format. `volume.toml` is a package-level addition, not a replacement. | ## Explore the current documentation Understand volumes, component types, bibliothecas, and the identity scheme. Read the frozen `volume.toml` manifest reference for `v0.1.0-rc.1`. Build an experimental client, bibliotheca, validator, exporter, or runtime adapter from the canonical artifacts. Learn how to propose specification changes, route issues, report vulnerabilities, and participate respectfully. Learn about agents, skills, commands, tools, hooks, MCP servers, and LSP servers in the release archive. Use the archived fixture corpus and role-scoped requirements without treating them as certification.