The Agent Directory (dir) allows publication, exchange, and discovery of information about AI agents over a distributed peer-to-peer network. It leverages OASF to describe agents and provides a set of APIs and tools to build, store, publish, and discover agents across the network by their attributes and constraints. Directory also leverages CSIT for continuous system integration and testing across different versions, environments, and features.
- Data Models - Defines a standard schema for data representation and exchange.
- Dev Kit - Provides CLI tooling to simplify development workflows and facilitate API interactions.
- Plugins - Pluggable components to extend the build process of agent data models for custom use cases.
- Announce - Allows publication of agent data models to the network.
- Discover - Listen, search, and retrieve agents across the network by their attributes and constraints.
- Security - Relies on well-known security principles to provide data provenance, integrity, and ownership.
Check the USAGE file for a full walkthrough of all the Directory features.
- api - gRPC specification for data models and services
- cli - command line client for interacting with system components
- builder - common data model build tools and plugins
- client - client SDK for development and API workflows
- e2e - end-to-end testing framework
- server - API services to manage storage, routing, and networking operations
To build the project and work with the code, you will need the following installed in your system
Make sure Docker is installed with Buildx.
Use Taskfile for all related development operations such as testing, validating, deploying, and working with the project.
git clone https://github.com/agntcy/dir
cd dirThis step will fetch all project dependencies and prepare the environment for development.
task depsMake the changes to the source code and rebuild for later testing.
task buildThe local testing pipeline relies on Golang to perform unit tests, and Docker to perform E2E tests in an isolated Kubernetes environment using Kind.
task test:unit
task test:e2eAll artifacts are tagged using the Semantic Versioning and follow the checked-out source code tags. It is not advised to use artifacts with mismatched versions.
All container images are distributed via GitHub Packages.
docker pull ghcr.io/agntcy/dir-ctl:v0.2.0
docker pull ghcr.io/agntcy/dir-apiserver:v0.2.0All helm charts are distributed as OCI artifacts via GitHub Packages.
helm pull oci://ghcr.io/agntcy/dir/helm-charts/dir --version v0.2.0All release binaries are distributed via GitHub Releases.
Directory API services can be deployed either using the Taskfile or directly via the released Helm chart.
This will start the necessary components such as storage and API services.
task server:startThis will deploy Directory services into an existing Kubernetes cluster.
helm pull oci://ghcr.io/agntcy/dir/helm-charts/dir --version v0.2.0
helm upgrade --install dir oci://ghcr.io/agntcy/dir/helm-charts/dir --version v0.2.0Distributed under Apache 2.0 License. See LICENSE for more information. Copyright AGNTCY Contributors (https://github.com/agntcy)