Agents API

The Agents API allows external applications, scripts, and services to communicate with CompanyGPT agents programmatically. CompanyGPT is based on LibreChat and exposes two API-compatible interfaces.

Overview

The Agents API provides two interfaces:

• OpenAI-compatible Chat Completions — POST /api/agents/v1/chat/completions
• Open Responses API — POST /api/agents/v1/responses

Both interfaces are authenticated via API keys and support streaming responses, making it easy to integrate CompanyGPT agents into existing workflows that already use the OpenAI SDK or similar tooling.

Prerequisites

To use the Agents API, the following prerequisites must be met:

1. API access must be enabled — An administrator must enable the remoteAgents configuration.
2. Generate an API key — Once access is enabled, you can create an API key in the CompanyGPT interface under Settings.
3. Find your agent ID — Each agent has a unique ID (e.g. agent_ulS_lcjGw...) that you use as the model parameter.

Tip

You can find the agent ID in the URL when you open an agent in CompanyGPT, or via the GET /api/agents/v1/models endpoint which lists all available agents as models.

Caution

Agents that use MCP servers with OAuth authentication may not work via the API. OAuth flows require an interactive browser session, which cannot be performed through the API.

Authentication

All requests to the Agents API must be authenticated with a Bearer token:

Authorization: Bearer sk-your-api-key

API keys are generated in the CompanyGPT interface and follow the format sk-....

Endpoints

Chat Completions (OpenAI-compatible)

POST /api/agents/v1/chat/completions

Compatible with the OpenAI Chat Completions format. The model parameter corresponds to the agent ID.

JavaScript (OpenAI SDK)

import { OpenAI } from "openai";

const client = new OpenAI({
    baseURL: "https://<COMPANYGPT URL>/api/agents/v1",
    apiKey: "sk-your-api-key",
});

const stream = await client.chat.completions.create({
    model: "agent_ulS_lcjGw...", // Agent ID
    messages: [
        {
            role: "user",
            content: "What can you help me with?",
        },
    ],
    stream: true,
});

let contentBuffer = "";
const toolCalls = new Map();

for await (const event of stream) {
    const delta = event.choices?.[0]?.delta;
    if (!delta) continue;

    // Stream text content
    if (delta.content) {
        contentBuffer += delta.content;
        process.stdout.write(delta.content);
    }

    // Handle tool calls
    if (delta.tool_calls) {
        for (const toolCall of delta.tool_calls) {
            const toolId = toolCall.index || 0;
            if (!toolCalls.has(toolId)) {
                toolCalls.set(toolId, {
                    id: toolCall.id,
                    name: toolCall.function?.name || "",
                    arguments: "",
                });
            }
            if (toolCall.function?.arguments) {
                toolCalls.get(toolId).arguments += toolCall.function.arguments;
            }
        }
    }
}

console.log(`\nDone. Tool calls: ${toolCalls.size}`);

curl

curl -X POST https://<COMPANYGPT URL>/api/agents/v1/chat/completions \
  -H "Authorization: Bearer sk-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "agent_ulS_lcjGwTAG2Ly3zTcgz",
    "messages": [
      {"role": "user", "content": "What can you help me with?"}
    ],
    "stream": true
  }'

Open Responses API

POST /api/agents/v1/responses

The Open Responses API follows the Open Responses standard — an open inference standard designed for agentic workflows with native support for tool use, structured outputs, and streaming. This is the primary interface going forward.

JavaScript (OpenAI SDK)

import { OpenAI } from "openai";

const client = new OpenAI({
    baseURL: "https://<COMPANYGPT URL>/api/agents/v1",
    apiKey: "sk-your-api-key",
});

const stream = await client.responses.create({
    model: "agent_ulS_lcjGwTAG2Ly3zTcgz", // Agent ID
    input: [
        {
            role: "user",
            content: "What can you help me with?",
        },
    ],
    stream: true,
});

for await (const event of stream) {
    console.log(event);
}

curl

curl -X POST https://<COMPANYGPT URL>/api/agents/v1/responses \
  -H "Authorization: Bearer sk-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "agent_ulS_lcjGwTAG2Ly3zTcgz",
    "input": "What can you help me with?"
  }'

List Available Agents

GET /api/agents/v1/models

Returns all agents accessible with your API key as a list of models.

JavaScript (OpenAI SDK)

import { OpenAI } from "openai";

const client = new OpenAI({
    baseURL: "https://<COMPANYGPT URL>/api/agents/v1",
    apiKey: "sk-your-api-key",
});

const models = await client.models.list();
console.log(models);

curl

curl https://<COMPANYGPT URL>/api/agents/v1/models \
  -H "Authorization: Bearer sk-your-api-key"

Token Usage

All Agents API requests are counted against the user’s token balance (when token spending is configured). Both input and output tokens are tracked, including cache tokens for providers that support them (OpenAI, Anthropic).

Related Documentation

• Agents — Creating and configuring agents in CompanyGPT
• MCP Servers — MCP server integrations