Skip to main content
Instead of writing custom tools based on Acontext low-level SDKs, Acontext provides ready-to-use tools that integrate seamlessly with popular LLM providers.

​
Available Tool Sets

Tool SetDescription
Sandbox ToolsExecute code, edit files, export results
Disk ToolsRead and write files to persistent storage
Skill ToolsAccess agent skills and knowledge

​
How It Works

​
Quick Example

1

Init resources

from acontext import AcontextClient
from acontext.agent.sandbox import SANDBOX_TOOLS

client = AcontextClient()
sandbox = client.sandboxes.create()
disk = client.disks.create()
2

Create context for this session

ctx = SANDBOX_TOOLS.format_context(client, sandbox.sandbox_id, disk.id)
3

Inject prompt

context_prompt = ctx.get_context_prompt()
messages = [
    {"role": "system", "content": f"You have sandbox access.\n\n{context_prompt}"},
    {"role": "user", "content": "Run a hello world script"}
]
4

Pass tools to LLM

tools = SANDBOX_TOOLS.to_openai_tool_schema()
response = openai_client.chat.completions.create(
    model="gpt-4.1", messages=messages, tools=tools
)
5

Execute tools

for tc in response.choices[0].message.tool_calls:
    result = SANDBOX_TOOLS.execute_tool(ctx, tc.function.name, json.loads(tc.function.arguments))

​
Next Steps

Sandbox Tools

Execute code in isolated containers

Disk Tools

Persistent file storage for agents

Skill Tools

Access reusable agent skills

Agent Skills

Create and manage skills