Tenki Cloud Agents

Tenki Cloud agents run in disposable Linux microVMs — provisioned in seconds, torn down when done.

Quick Start

Set the API key

export TENKI_API_KEY="your-tenki-api-key"

TENKI_AUTH_TOKEN works too. Install the extra with pip install "praisonai[tenki]".

Simplest agent

from praisonaiagents import Agent
from praisonai.integrations.managed_agents import ManagedAgent, ManagedConfig

managed = ManagedAgent(
    provider="local",
    config=ManagedConfig(model="gpt-4o-mini", name="TenkiAgent"),
    compute="tenki",  # requires TENKI_API_KEY
)
agent = Agent(name="tenki-agent", backend=managed)

agent.start("Run `python3 -c 'print(2**10)'` and tell me the answer.")

With pip packages pre-installed

import asyncio
from praisonai.integrations.managed_agents import ManagedAgent, ManagedConfig

managed = ManagedAgent(
    provider="local",
    config=ManagedConfig(model="gpt-4o-mini"),
    compute="tenki",
    compute_config={"packages": {"pip": ["pandas"]}},
)

info = asyncio.run(managed.provision_compute())
result = asyncio.run(managed.execute_in_compute(
    "python3 -c 'import pandas; print(pandas.__version__)'"
))
print(result["stdout"])
asyncio.run(managed.shutdown_compute())

How It Works

Tenki boots a fresh Linux microVM per sandbox. Commands run through ephemeral exec; files move as base64 over the same channel. The stock image ships python3 — everything else installs on demand.

Configuration Options

Authenticate with an API key. One of the two token variables is required.

Env var	Purpose	Required
`TENKI_API_KEY` or `TENKI_AUTH_TOKEN`	Auth against Tenki Cloud	Yes (one of)
`TENKI_WORKSPACE_ID`	Pin sandboxes to a specific workspace	No (auto-picks first)

ComputeConfig fields honoured by Tenki:

Field	Type	Default	Effect on Tenki
`cpu`	`float`	`1.0`	microVM CPU cores (`cpu_cores`)
`memory_mb`	`int`	`512`	microVM RAM
`env`	`dict \| None`	`None`	Environment variables inside the VM
`networking`	`dict`	`{"type": "unrestricted"}`	Only `"unrestricted"` allows outbound; anything else disables it
`image`	`str`	(SDK default)	Ignored unless explicitly changed; Tenki has no Docker-pull
`metadata["tenki_image"]`	`str`	—	Boot a prebaked Tenki snapshot (takes precedence over `image`)
`auto_shutdown`	`bool`	`True`	Enables idle timeout
`idle_timeout_s`	`int`	`300`	Converted to `idle_timeout_minutes` (min 1)
`packages["pip"]`	`list[str]`	`[]`	Installed at provision (`pip3` bootstrapped if missing)
`packages["npm"]`	`list[str]`	`[]`	Installed at provision (`npm` bootstrapped if missing)

Only stable Tenki primitives are used: ephemeral exec and base64 file I/O. No volumes, snapshot creation, or template management from PraisonAI.

Common Patterns

Data analysis with pandas

import asyncio
from praisonai.integrations.managed_agents import ManagedAgent, ManagedConfig

managed = ManagedAgent(
    provider="local",
    config=ManagedConfig(model="gpt-4o-mini"),
    compute="tenki",
    compute_config={"packages": {"pip": ["pandas"]}},
)

info = asyncio.run(managed.provision_compute())
result = asyncio.run(managed.execute_in_compute(
    "python3 -c 'import pandas as pd; print(pd.Series([1,2,3,4,5]).mean())'"
))
print(result["stdout"])
asyncio.run(managed.shutdown_compute())

Web scraping

import asyncio
from praisonai.integrations.managed_agents import ManagedAgent, ManagedConfig

managed = ManagedAgent(
    provider="local",
    config=ManagedConfig(model="gpt-4o-mini"),
    compute="tenki",
    compute_config={"packages": {"pip": ["requests", "beautifulsoup4"]}},
)

info = asyncio.run(managed.provision_compute())
result = asyncio.run(managed.execute_in_compute(
    "python3 -c \"import requests; print(requests.get('https://httpbin.org/get').status_code)\""
))
print(result["stdout"])
asyncio.run(managed.shutdown_compute())

Custom Tenki image

import asyncio
from praisonai.integrations.managed_agents import ManagedAgent, ManagedConfig

managed = ManagedAgent(
    provider="local",
    config=ManagedConfig(model="gpt-4o-mini"),
    compute="tenki",
    compute_config={"metadata": {"tenki_image": "my-prebaked-snapshot"}},
)

info = asyncio.run(managed.provision_compute())
result = asyncio.run(managed.execute_in_compute("python3 --version"))
print(result["stdout"])
asyncio.run(managed.shutdown_compute())

Best Practices

Pick the right provider

Tenki gives ephemeral microVMs with no template registry — ideal for short, disposable runs. Use E2B for instant pre-built templates, or Docker for local, reproducible containers.

Package installs happen at provision

A failed install tears the sandbox down. Don’t rely on the pip field for large dependency sets — bake them into a prebaked snapshot and boot it via metadata["tenki_image"] instead.

Sandboxes bill while alive

Always call shutdown_compute() when done, and set idle_timeout_s so an idle microVM self-terminates.

Network policy is boolean

Tenki cannot express per-host allowlists. networking={"type": "unrestricted"} allows outbound; anything else (including "limited") disables it entirely.

Managed Agents

Overview of managed agent providers

E2B Cloud

Compare with the E2B sandbox provider

Getting Started

Install

Core Concepts

Guides

Features

Models

Databases

Observability

Memory

Telemetry & Analytics

Knowledge

RAG

Persistence

Tools

Other Features

Developers

Configuration

Best Practices

Getting Started (No Code)

Tenki Cloud Agents

Quick Start

How It Works

Configuration Options

Common Patterns

Data analysis with pandas

Web scraping

Custom Tenki image

Best Practices

Managed Agents

E2B Cloud

​Quick Start

​How It Works

​Configuration Options

​Common Patterns

​Data analysis with pandas

​Web scraping

​Custom Tenki image

​Best Practices

​Related

Managed Agents

E2B Cloud

Quick Start

How It Works

Configuration Options

Common Patterns

Data analysis with pandas

Web scraping

Custom Tenki image

Best Practices

Related