借助 Gemini API 上的托管式智能体，您可以使用自己的指令、技能和数据来扩展 Antigravity 智能体。您可以在 互动时内嵌自定义智能体，也可以将 配置保存为托管式智能体，并通过 ID 调用该智能体。
自定义 Antigravity 智能体
构建自定义智能体的最快方法是在创建新互动时内嵌传递配置，无需执行注册步骤。您可以通过以下几种主要方式扩展智能体：
- 模型选择：通过
agent_config选择底层 Gemini 模型（默认为 Gemini 3.8 Flash）。 - 系统指令：通过
system_instruction传递内嵌文本，以塑造行为。 - 工具：替换默认工具（代码执行、搜索、网址上下文）、注册远程 MCP 服务器或定义自定义函数（函数调用）。
- 文件和技能：将
AGENTS.md和SKILL.md等文件装载到环境中。
以下示例展示了如何内嵌传递所有这三项：
Python
from google import genai
client = genai.Client()
interaction = client.interactions.create(
agent="antigravity-preview-05-2026",
input="Analyze the Q1 revenue data and create a slide deck.",
system_instruction="You are a data analyst. Always include visualizations and export results as PDF.",
environment={
"type": "remote",
"sources": [
{
"type": "inline",
"target": ".agents/AGENTS.md",
"content": "Always use matplotlib for charts. Include a summary table in every report.",
},
{
"type": "inline",
"target": ".agents/skills/slide-maker/SKILL.md",
"content": "---\nname: slide-maker\n---\n# Slide Maker\nCreate HTML slide decks from data analysis results.",
},
],
},
)
print(interaction.output_text)
JavaScript
import { GoogleGenAI } from "@google/genai";
const client = new GoogleGenAI({});
const interaction = await client.interactions.create({
agent: "antigravity-preview-05-2026",
input: "Analyze the Q1 revenue data and create a slide deck.",
system_instruction: "You are a data analyst. Always include visualizations and export results as PDF.",
environment: {
type: "remote",
sources: [
{
type: "inline",
target: ".agents/AGENTS.md",
content: "Always use matplotlib for charts. Include a summary table in every report.",
},
{
type: "inline",
target: ".agents/skills/slide-maker/SKILL.md",
content: "---\nname: slide-maker\n---\n# Slide Maker\nCreate HTML slide decks from data analysis results.",
},
],
},
}, { timeout: 300000 });
console.log(interaction.output_text);
Java
import com.google.genai.Client;
import com.google.genai.gaos.models.interactions.AgentOption;
import com.google.genai.gaos.models.interactions.CreateAgentInteraction;
import com.google.genai.gaos.models.interactions.Interaction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
Client client = new Client();
CreateAgentInteraction params =
CreateAgentInteraction.builder()
.agent(AgentOption.of("antigravity-preview-05-2026"))
.input(InteractionsInput.of("Build a simple REST API server in Node.js."))
.build();
Interaction interaction =
client.interactions.create(CreateInteractionRequestBody.of(params)).interaction().get();
System.out.println(interaction.outputText().orElse(""));
REST
curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "Content-Type: application/json" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-d '{
"agent": "antigravity-preview-05-2026",
"input": "Analyze the Q1 revenue data and create a slide deck.",
"system_instruction": "You are a data analyst. Always include visualizations and export results as PDF.",
"environment": {
"type": "remote",
"sources": [
{
"type": "inline",
"target": ".agents/AGENTS.md",
"content": "Always use matplotlib for charts. Include a summary table in every report."
},
{
"type": "inline",
"target": ".agents/skills/slide-maker/SKILL.md",
"content": "---\nname: slide-maker\n---\n# Slide Maker\nCreate HTML slide decks from data analysis results."
}
]
}
}'
所有内容都在互动时定义。无需先注册任何内容。Antigravity 智能体 Harness 提供运行时（代码执行、文件管理、网络访问），以及您在运行时之上配置的层。
工具和系统指令
您可以使用 system_instruction 和 tools 参数自定义智能体针对特定互动的行为和功能。
- 系统指令：使用
system_instruction参数传递内嵌文本，以塑造智能体的行为。如果您想针对每次调用进行快速调整，此方法非常理想。system_instruction和AGENTS.md是累加的；如果两者都存在，则两者都适用。 - 工具：默认情况下，Antigravity 智能体可以访问
code_execution、google_search和url_context。您可以在互动时传递tools参数来替换此列表。您还可以注册 远程 MCP 服务器 或定义 自定义函数（函数调用），以将智能体连接到您自己的 API 和数据库。如需详细了解可用工具，请参阅 Antigravity 智能体：支持的工具。
基于文件的自定义
智能体目录结构
虽然您可以内嵌传递配置，但我们建议您在结构化目录中整理智能体的文件。这样可以更轻松地管理、进行版本控制和装载到智能体的环境中。
典型的智能体项目目录如下所示：
my-agent/
├── AGENTS.md # Instructions on how the agent should operate
├── skills/ # Custom skills (subfolders and SKILL.md files)
│ └── slide-maker/
│ └── SKILL.md
└── workspace/ # Initial data files and knowledge
Antigravity 运行时会扫描 .agents/（以及环境的根目录）以查找这些文件。
AGENTS.md
智能体会在启动时自动从环境中加载 .agents/AGENTS.md（或 /.agents/AGENTS.md）作为系统指令。对于您想要与代码一起进行版本控制的长篇角色定义、详细准则和指令，请使用 AGENTS.md。
使用内嵌来源装载 AGENTS.md：
Python
from google import genai
client = genai.Client()
interaction = client.interactions.create(
agent="antigravity-preview-05-2026",
input="Analyze the Q1 revenue data and create a report.",
system_instruction="You are a data analyst. Always include visualizations and export results as PDF.",
environment={
"type": "remote",
"sources": [
{
"type": "inline",
"target": ".agents/AGENTS.md",
"content": "Always use matplotlib for charts. Include a summary table in every report.",
},
],
},
)
print(interaction.output_text)
JavaScript
import { GoogleGenAI } from "@google/genai";
const client = new GoogleGenAI({});
const interaction = await client.interactions.create({
agent: "antigravity-preview-05-2026",
input: "Analyze the Q1 revenue data and create a report.",
system_instruction: "You are a data analyst. Always include visualizations and export results as PDF.",
environment: {
type: "remote",
sources: [
{
type: "inline",
target: ".agents/AGENTS.md",
content: "Always use matplotlib for charts. Include a summary table in every report.",
},
],
},
}, { timeout: 300000 });
console.log(interaction.output_text);
Java
import com.google.genai.Client;
import com.google.genai.gaos.models.interactions.AgentOption;
import com.google.genai.gaos.models.interactions.CreateAgentInteraction;
import com.google.genai.gaos.models.interactions.Interaction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
Client client = new Client();
CreateAgentInteraction params =
CreateAgentInteraction.builder()
.agent(AgentOption.of("antigravity-preview-05-2026"))
.input(InteractionsInput.of("Build a simple REST API server in Node.js."))
.build();
Interaction interaction =
client.interactions.create(CreateInteractionRequestBody.of(params)).interaction().get();
System.out.println(interaction.outputText().orElse(""));
REST
curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "Content-Type: application/json" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-d '{
"agent": "antigravity-preview-05-2026",
"input": "Analyze the Q1 revenue data and create a report.",
"system_instruction": "You are a data analyst. Always include visualizations and export results as PDF.",
"environment": {
"type": "remote",
"sources": [
{
"type": "inline",
"target": ".agents/AGENTS.md",
"content": "Always use matplotlib for charts. Include a summary table in every report."
}
]
}
}'
技能：SKILL.md
技能是扩展智能体功能的文件。将它们放在 .agents/skills/<skill-name>/SKILL.md 下，框架会自动发现并注册它们。
.agents/
├── AGENTS.md
└── skills/
└── slide-maker/
└── SKILL.md
使用内嵌来源装载技能：
Python
from google import genai
client = genai.Client()
interaction = client.interactions.create(
agent="antigravity-preview-05-2026",
input="Create a presentation about our Q1 results.",
system_instruction="You create presentations from data.",
environment={
"type": "remote",
"sources": [
{
"type": "inline",
"target": ".agents/skills/slide-maker/SKILL.md",
"content": "---\nname: slide-maker\ndescription: Create HTML slide decks\n---\n# Slide Maker\n\nWhen asked to create a presentation:\n1. Analyze the input data\n2. Create an HTML slide deck with reveal.js\n3. Save to /workspace/output/slides.html",
},
],
},
)
print(interaction.output_text)
JavaScript
import { GoogleGenAI } from "@google/genai";
const client = new GoogleGenAI({});
const interaction = await client.interactions.create({
agent: "antigravity-preview-05-2026",
input: "Create a presentation about our Q1 results.",
system_instruction: "You create presentations from data.",
environment: {
type: "remote",
sources: [
{
type: "inline",
target: ".agents/skills/slide-maker/SKILL.md",
content: "---\nname: slide-maker\ndescription: Create HTML slide decks\n---\n# Slide Maker\n\nWhen asked to create a presentation:\n1. Analyze the input data\n2. Create an HTML slide deck with reveal.js\n3. Save to /workspace/output/slides.html",
},
],
},
}, { timeout: 300000 });
console.log(interaction.output_text);
Java
import com.google.genai.Client;
import com.google.genai.gaos.models.interactions.AgentOption;
import com.google.genai.gaos.models.interactions.CreateAgentInteraction;
import com.google.genai.gaos.models.interactions.Interaction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
Client client = new Client();
CreateAgentInteraction params =
CreateAgentInteraction.builder()
.agent(AgentOption.of("antigravity-preview-05-2026"))
.input(InteractionsInput.of("Build a simple REST API server in Node.js."))
.build();
Interaction interaction =
client.interactions.create(CreateInteractionRequestBody.of(params)).interaction().get();
System.out.println(interaction.outputText().orElse(""));
REST
curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "Content-Type: application/json" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-d '{
"agent": "antigravity-preview-05-2026",
"input": "Create a presentation about our Q1 results.",
"system_instruction": "You create presentations from data.",
"environment": {
"type": "remote",
"sources": [
{
"type": "inline",
"target": ".agents/skills/slide-maker/SKILL.md",
"content": "---\nname: slide-maker\ndescription: Create HTML slide decks\n---\n# Slide Maker\n\nWhen asked to create a presentation:\n1. Analyze the input data\n2. Create an HTML slide deck with reveal.js\n3. Save to /workspace/output/slides.html"
}
]
}
}'
从 .agents/skills/ 和 /.agents/skills/ 加载的技能都会自动被发现。
创建托管式智能体
对配置进行迭代后，您可以使用 agents.create 将其创建为托管式智能体。这样，您就可以通过 ID 调用智能体，而无需每次都重复配置。
创建托管式智能体时指定的 id 必须在您的项目中是唯一的，并且不得以保留的前缀（例如 google-、gemini-）开头。如需查看受限前缀的完整列表，请参阅 智能体 ID 限制。
从来源配置
使用来源指定 base_agent、id、agent_config、system_instruction 和 base_environment。平台会在每次调用时预配一个包含您的文件的全新沙盒。如需了解可用的来源类型（Git、GCS、内嵌），请参阅环境。
Python
from google import genai
client = genai.Client()
agent = client.agents.create(
id="data-analyst",
base_agent="antigravity-preview-05-2026",
agent_config={
"type": "antigravity",
"model": "gemini-3.8-flash",
},
system_instruction="You are a data analyst. Always include visualizations and export results as PDF.",
base_environment={
"type": "remote",
"sources": [
{
"type": "inline",
"target": ".agents/AGENTS.md",
"content": "Always use matplotlib for charts. Include a summary table in every report.",
},
{
"type": "inline",
"target": ".agents/skills/slide-maker/SKILL.md",
"content": "---\nname: slide-maker\n---\n# Slide Maker\nCreate HTML slide decks from data analysis results.",
},
{
"type": "repository",
"source": "https://github.com/my-org/analysis-templates",
"target": "/workspace/templates",
},
],
},
)
print(f"Created agent: {agent.id}")
JavaScript
import { GoogleGenAI } from "@google/genai";
const client = new GoogleGenAI({});
const agent = await client.agents.create({
id: "data-analyst",
base_agent: "antigravity-preview-05-2026",
agent_config: {
type: "antigravity",
model: "gemini-3.8-flash",
},
system_instruction: "You are a data analyst. Always include visualizations and export results as PDF.",
base_environment: {
type: "remote",
sources: [
{
type: "inline",
target: ".agents/AGENTS.md",
content: "Always use matplotlib for charts. Include a summary table in every report.",
},
{
type: "inline",
target: ".agents/skills/slide-maker/SKILL.md",
content: "---\nname: slide-maker\n---\n# Slide Maker\nCreate HTML slide decks from data analysis results.",
},
{
type: "repository",
source: "https://github.com/my-org/analysis-templates",
target: "/workspace/templates",
},
],
},
});
console.log(`Created agent: ${agent.id}`);
Java
import com.google.genai.Client;
import com.google.genai.gaos.models.interactions.AgentOption;
import com.google.genai.gaos.models.interactions.CreateAgentInteraction;
import com.google.genai.gaos.models.interactions.Interaction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
Client client = new Client();
CreateAgentInteraction params =
CreateAgentInteraction.builder()
.agent(AgentOption.of("antigravity-preview-05-2026"))
.input(InteractionsInput.of("Build a simple REST API server in Node.js."))
.build();
Interaction interaction =
client.interactions.create(CreateInteractionRequestBody.of(params)).interaction().get();
System.out.println(interaction.outputText().orElse(""));
REST
curl -X POST "https://generativelanguage.googleapis.com/v1beta/agents" \
-H "Content-Type: application/json" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-d '{
"id": "data-analyst",
"base_agent": "antigravity-preview-05-2026",
"agent_config": {
"type": "antigravity",
"model": "gemini-3.8-flash"
},
"system_instruction": "You are a data analyst. Always include visualizations and export results as PDF.",
"base_environment": {
"type": "remote",
"sources": [
{
"type": "inline",
"target": ".agents/AGENTS.md",
"content": "Always use matplotlib for charts. Include a summary table in every report."
},
{
"type": "inline",
"target": ".agents/skills/slide-maker/SKILL.md",
"content": "---\nname: slide-maker\n---\n# Slide Maker\nCreate HTML slide decks from data analysis results."
},
{
"type": "repository",
"source": "https://github.com/my-org/analysis-templates",
"target": "/workspace/templates"
}
]
}
}'
从现有环境（派生）
使用基本 Antigravity 智能体进行迭代，直到环境正确（软件包已安装，文件已就位），然后将其派生为托管式智能体。
Python
from google import genai
client = genai.Client()
# Step 1: set up the environment interactively
interaction = client.interactions.create(
agent="antigravity-preview-05-2026",
input="Install pandas, matplotlib, and seaborn. Create an analysis template at /workspace/template.py.",
environment="remote",
)
# Step 2: fork that environment into a managed agent
agent = client.agents.create(
id="my-data-analyst",
base_agent="antigravity-preview-05-2026",
system_instruction="You are a data analyst. Use the template at /workspace/template.py for all reports.",
base_environment=interaction.environment_id,
)
print(f"Forked agent successfully: {agent.id}")
JavaScript
import { GoogleGenAI } from "@google/genai";
const client = new GoogleGenAI({});
const interaction = await client.interactions.create({
agent: "antigravity-preview-05-2026",
input: "Install pandas, matplotlib, and seaborn. Create an analysis template at /workspace/template.py.",
environment: "remote",
}, { timeout: 300000 });
const agent = await client.agents.create({
id: "my-data-analyst",
base_agent: "antigravity-preview-05-2026",
system_instruction: "You are a data analyst. Use the template at /workspace/template.py for all reports.",
base_environment: interaction.environment_id,
});
console.log(`Forked agent successfully: ${agent.id}`);
Java
import com.google.genai.Client;
import com.google.genai.gaos.models.interactions.AgentOption;
import com.google.genai.gaos.models.interactions.CreateAgentInteraction;
import com.google.genai.gaos.models.interactions.Interaction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
Client client = new Client();
CreateAgentInteraction params =
CreateAgentInteraction.builder()
.agent(AgentOption.of("antigravity-preview-05-2026"))
.input(InteractionsInput.of("Build a simple REST API server in Node.js."))
.build();
Interaction interaction =
client.interactions.create(CreateInteractionRequestBody.of(params)).interaction().get();
System.out.println(interaction.outputText().orElse(""));
REST
curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "Content-Type: application/json" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-d '{
"agent": "antigravity-preview-05-2026",
"input": "Install pandas, matplotlib, and seaborn. Create an analysis template at /workspace/template.py.",
"environment": "remote"
}'
使用网络规则
您可以在保存托管式智能体时锁定出站访问权限或注入凭据。如需查看完整的许可名单架构、凭据模式和通配符，请参阅环境：网络配置。
以下示例创建了一个只能访问 GitHub 和 PyPI 的 issue-resolver 智能体，并为 GitHub 注入了凭据：
Python
from google import genai
client = genai.Client()
agent = client.agents.create(
id="issue-resolver",
base_agent="antigravity-preview-05-2026",
system_instruction="You resolve GitHub issues. Clone the repo, find the bug, write the fix, run the tests, and open a PR.",
base_environment={
"type": "remote",
"sources": [
{
"type": "repository",
"source": "https://github.com/my-org/backend",
"target": "/workspace/repo",
}
],
"network": {
"allowlist": [
{
"domain": "api.github.com",
"transform": {
"Authorization": "Basic YOUR_BASE64_TOKEN"
},
},
{"domain": "pypi.org"},
]
},
},
)
print(f"Created issue-resolver agent successfully: {agent.id}")
JavaScript
import { GoogleGenAI } from "@google/genai";
const client = new GoogleGenAI({});
const agent = await client.agents.create({
id: "issue-resolver",
base_agent: "antigravity-preview-05-2026",
system_instruction: "You resolve GitHub issues. Clone the repo, find the bug, write the fix, run the tests, and open a PR.",
base_environment: {
type: "remote",
sources: [
{
type: "repository",
source: "https://github.com/my-org/backend",
target: "/workspace/repo",
}
],
network: {
allowlist: [
{
domain: "api.github.com",
transform: {
"Authorization": "Basic YOUR_BASE64_TOKEN"
},
},
{ domain: "pypi.org" },
]
}
},
});
console.log(`Created issue-resolver agent successfully: ${agent.id}`);
Java
import com.google.genai.Client;
import com.google.genai.gaos.models.interactions.AgentOption;
import com.google.genai.gaos.models.interactions.CreateAgentInteraction;
import com.google.genai.gaos.models.interactions.Interaction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
Client client = new Client();
CreateAgentInteraction params =
CreateAgentInteraction.builder()
.agent(AgentOption.of("antigravity-preview-05-2026"))
.input(InteractionsInput.of("Build a simple REST API server in Node.js."))
.build();
Interaction interaction =
client.interactions.create(CreateInteractionRequestBody.of(params)).interaction().get();
System.out.println(interaction.outputText().orElse(""));
REST
curl -X POST "https://generativelanguage.googleapis.com/v1beta/agents" \
-H "Content-Type: application/json" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-d '{
"id": "issue-resolver",
"base_agent": "antigravity-preview-05-2026",
"system_instruction": "You resolve GitHub issues. Clone the repo, find the bug, write the fix, run the tests, and open a PR.",
"base_environment": {
"type": "remote",
"sources": [
{
"type": "repository",
"source": "https://github.com/my-org/backend",
"target": "/workspace/repo"
}
],
"network": {
"allowlist": [
{
"domain": "api.github.com",
"transform": {
"Authorization": "Basic YOUR_BASE64_TOKEN"
}
},
{"domain": "pypi.org"}
]
}
}
}'
调用智能体
通过创建新互动，使用智能体 ID 调用托管式智能体。每次调用都会派生基本环境，因此每次运行都是从头开始。
Python
result = client.interactions.create(
agent="data-analyst",
input="Analyze Q1 revenue data from /workspace/templates/sample.csv and create a slide deck.",
environment="remote",
)
print(result.output_text)
JavaScript
const result = await client.interactions.create({
agent: "data-analyst",
input: "Analyze Q1 revenue data from /workspace/templates/sample.csv and create a slide deck.",
environment: "remote",
}, { timeout: 300000 });
console.log(result.output_text);
Java
import com.google.genai.Client;
import com.google.genai.gaos.models.interactions.AgentOption;
import com.google.genai.gaos.models.interactions.CreateAgentInteraction;
import com.google.genai.gaos.models.interactions.Interaction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
Client client = new Client();
CreateAgentInteraction params =
CreateAgentInteraction.builder()
.agent(AgentOption.of("antigravity-preview-05-2026"))
.input(InteractionsInput.of("Build a simple REST API server in Node.js."))
.build();
Interaction interaction =
client.interactions.create(CreateInteractionRequestBody.of(params)).interaction().get();
System.out.println(interaction.outputText().orElse(""));
REST
curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "Content-Type: application/json" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-d '{
"agent": "data-analyst",
"input": "Analyze Q1 revenue data from /workspace/templates/sample.csv and create a slide deck.",
"environment": "remote"
}'
如需了解多轮对话和流式传输，请参阅快速入门。相同的 previous_interaction_id 和 environment 模式适用于托管式智能体。
托管式智能体还支持后台执行和取消。如需了解详情和查看代码示例，请参阅 Antigravity 智能体：后台执行。
在调用时替换配置
您可以在创建互动时替换智能体的默认 system_instruction、tools 和 environment 网络配置。这样，您就可以针对特定运行修改智能体的行为、功能或凭据，而无需更改存储的智能体定义。
替换系统指令和工具
Python
result = client.interactions.create(
agent="data-analyst",
input="Analyze Q1 revenue data, but do not create a slide deck. Just output a summary table.",
system_instruction="You are a data analyst. Focus ONLY on summary tables. Ignore default instructions about slides.",
tools=[{"type": "code_execution"}], # Override to only use code execution
environment="remote",
)
print(result.output_text)
JavaScript
const result = await client.interactions.create({
agent: "data-analyst",
input: "Analyze Q1 revenue data, but do not create a slide deck. Just output a summary table.",
system_instruction: "You are a data analyst. Focus ONLY on summary tables. Ignore default instructions about slides.",
tools: [{ type: "code_execution" }], // Override to only use code execution
environment: "remote",
}, { timeout: 300000 });
console.log(result.output_text);
Java
import com.google.genai.Client;