Agent Manifest

GET

agents

{name}

Agent Manifest

curl --request GET \
  --url http://localhost:8000/agents/{name}

{
  "name": "chat",
  "description": "Conversational agent with memory, supporting real-time search, Wikipedia lookups, and weather updates through integrated tools",
  "input_content_types": [
    "<string>"
  ],
  "output_content_types": [
    "<string>"
  ],
  "metadata": {
    "annotations": {},
    "documentation": "The agent is a conversational system designed to process user messages, maintain context, and generate...",
    "license": "Apache-2.0",
    "programming_language": "Python",
    "natural_languages": [
      "en"
    ],
    "framework": "BeeAI",
    "capabilities": [
      {
        "name": "Conversational AI",
        "description": "Handles multi-turn conversations with memory."
      },
      {
        "name": "Vacation Request",
        "description": "Handles submission and tracking of vacation requests."
      }
    ],
    "domains": [
      "finance",
      "healthcare",
      "supply-chain"
    ],
    "tags": [
      "Chat"
    ],
    "created_at": "2023-11-07T05:31:56Z",
    "updated_at": "2023-11-07T05:31:56Z",
    "author": {
      "name": "John Smith",
      "email": "[email protected]",
      "url": "https://example.com"
    },
    "contributors": [
      {
        "name": "John Smith",
        "email": "[email protected]",
        "url": "https://example.com"
      }
    ],
    "links": [
      {
        "type": "source-code",
        "url": "https://github.com/i-am-bee/beeai-platform.git"
      },
      {
        "type": "homepage",
        "url": "https://agentcommunicationprotocol.dev"
      }
    ],
    "dependencies": [
      {
        "type": "tool",
        "name": "weather"
      }
    ],
    "recommended_models": [
      "llama3.3:70b-instruct-fp16",
      "llama3.3"
    ]
  },
  "status": {
    "avg_run_tokens": 1,
    "avg_run_time_seconds": 1,
    "success_rate": 50
  }
}

Path Parameters

name

string

required

The name of the agent to retrieve. A unique identifier for the agent following the RFC 1123 DNS label naming convention.

Required string length: 1 - 63

Example:

"chat"

Response

Agent manifests

name

string

required

A unique identifier for the agent following the RFC 1123 DNS label naming convention.

Required string length: 1 - 63

Example:

"chat"

description

string

required

Human-readable description of the agent.

Example:

"Conversational agent with memory, supporting real-time search, Wikipedia lookups, and weather updates through integrated tools"

input_content_types

string[]

required

List of supported MIME content types for input Messages. Defines what formats of content the agent can consume.

Minimum array length: 1

output_content_types

string[]

required

List of supported MIME content types for output Messages. Defines what formats of content the agent can produce.

Minimum array length: 1

metadata

object

Static details about the agent, for discovery, classification, and cataloging.

Show child attributes

metadata.annotations

object

Key-value annotation metadata.

metadata.documentation

string

Full agent documentation in markdown.

Example:

"The agent is a conversational system designed to process user messages, maintain context, and generate..."

metadata.license

string

SPDX license ID.

Example:

"Apache-2.0"

metadata.programming_language

string

Programming language (per GitHub language support).

Example:

"Python"

metadata.natural_languages

string[]

Supported human languages (ISO 639-1 codes).

metadata.framework

string

Agent framework, e.g. BeeAI, crewAI, Autogen, AG2.

Example:

"BeeAI"

metadata.capabilities

object[]

A structured list describing capabilities supported by the agent. Each capability includes a human-readable name and a brief description. This information might be consumed and interpreted by large language models (LLMs).

Show child attributes

metadata.capabilities.name

string

required

Human-readable name of the capability.

Example:

"Conversational AI"

metadata.capabilities.description

string

required

Brief description of what the capability provides or enables.

Example:

"Handles multi-turn conversations with memory."

Example:

[
  {
    "name": "Conversational AI",
    "description": "Handles multi-turn conversations with memory."
  },
  {
    "name": "Vacation Request",
    "description": "Handles submission and tracking of vacation requests."
  }
]

metadata.domains

string[]

Domains or functional areas applicable to the agent, such as 'finance', 'healthcare', 'supply-chain', or custom-defined domains relevant to your organization or team.

Example:

["finance", "healthcare", "supply-chain"]

metadata.tags

(string | enum<string>)[]

Simple tag or enum for classifying agents.

Example:

"Chat"

metadata.created_at

string<date-time>

Timestamp in RFC3339/ISO8601 format.

metadata.updated_at

string<date-time>

Timestamp in RFC3339/ISO8601 format.

metadata.author

object

Show child attributes

metadata.author.name

string

required

Example:

"John Smith"

metadata.author.email

string<email>

Example:

"[email protected]"

metadata.author.url

string<uri>

Example:

"https://example.com"

metadata.contributors

object[]

Show child attributes

metadata.contributors.name

string

required

Example:

"John Smith"

metadata.contributors.email

string<email>

Example:

"[email protected]"

metadata.contributors.url

string<uri>

Example:

"https://example.com"

metadata.links

object[]

Show child attributes

metadata.links.type

enum<string>

required

Available options:

source-code,

container-image,

homepage,

documentation

metadata.links.url

string<uri>

required

Example:

[
  {
    "type": "source-code",
    "url": "https://github.com/i-am-bee/beeai-platform.git"
  },
  {
    "type": "homepage",
    "url": "https://agentcommunicationprotocol.dev"
  }
]

metadata.dependencies

object[]

Show child attributes

metadata.dependencies.type

enum<string>

Type of dependency:

agent: Another agent instance required to fulfill certain functionalities.
tool: External tool or utility needed by the agent.
model: Specific AI model that the agent depends on.

Available options:

agent,

tool,

model

Example:

"tool"

metadata.dependencies.name

string

Identifier or name of the dependency, such as an agent name, tool identifier, or model name.

Example:

"weather"

metadata.recommended_models

string[]

List of recommended model names (see providers such as Ollama, OpenAI, etc.).

Example:

["llama3.3:70b-instruct-fp16", "llama3.3"]

status

object

Real-time dynamic metrics and state provided by the system managing the agent.

Show child attributes

status.avg_run_tokens

number

Required range: x >= 0

status.avg_run_time_seconds

number<float>

Required range: x >= 0

status.success_rate

number

Percentage of successful runs (0-100).

Required range: 0 <= x <= 100

Create a new runCreate and start a new run for the specified agent.

⌘I

Agent Manifest

curl --request GET \
  --url http://localhost:8000/agents/{name}

{
  "name": "chat",
  "description": "Conversational agent with memory, supporting real-time search, Wikipedia lookups, and weather updates through integrated tools",
  "input_content_types": [
    "<string>"
  ],
  "output_content_types": [
    "<string>"
  ],
  "metadata": {
    "annotations": {},
    "documentation": "The agent is a conversational system designed to process user messages, maintain context, and generate...",
    "license": "Apache-2.0",
    "programming_language": "Python",
    "natural_languages": [
      "en"
    ],
    "framework": "BeeAI",
    "capabilities": [
      {
        "name": "Conversational AI",
        "description": "Handles multi-turn conversations with memory."
      },
      {
        "name": "Vacation Request",
        "description": "Handles submission and tracking of vacation requests."
      }
    ],
    "domains": [
      "finance",
      "healthcare",
      "supply-chain"
    ],
    "tags": [
      "Chat"
    ],
    "created_at": "2023-11-07T05:31:56Z",
    "updated_at": "2023-11-07T05:31:56Z",
    "author": {
      "name": "John Smith",
      "email": "[email protected]",
      "url": "https://example.com"
    },
    "contributors": [
      {
        "name": "John Smith",
        "email": "[email protected]",
        "url": "https://example.com"
      }
    ],
    "links": [
      {
        "type": "source-code",
        "url": "https://github.com/i-am-bee/beeai-platform.git"
      },
      {
        "type": "homepage",
        "url": "https://agentcommunicationprotocol.dev"
      }
    ],
    "dependencies": [
      {
        "type": "tool",
        "name": "weather"
      }
    ],
    "recommended_models": [
      "llama3.3:70b-instruct-fp16",
      "llama3.3"
    ]
  },
  "status": {
    "avg_run_tokens": 1,
    "avg_run_time_seconds": 1,
    "success_rate": 50
  }
}

Introduction

Core Concepts

How To

REST API

Integrations

About

Path Parameters

Response