OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Agent Infrastructure

Takovm

Takovm is a self-hosted Python service that gives agents file-system access and code execution in isolated Docker containers, with ephemeral workspaces, job queues, retries and execution history.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Takovm — OpenViST project profile in Agent Infrastructure.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Takovm when an agent workflow needs Python and file execution with built-in job handling and a self-hosted deployment model.

Who it is for

  • Developers building agents that need to execute Python code or manage files in a per-job workspace.
  • Teams that want queues, retries and execution records as part of their agent execution infrastructure.

Documented uses

  • Run agent-generated Python code in a separate container for each job.
  • Provide a temporary workspace for file operations during execution.
  • Queue jobs, retry executions and retain output and timing history.
  • Replay previous jobs to support debugging.
Before you choose

Requirements & limits

The project is self-hosted and open source under the Apache-2.0 license. Installation requires Docker and Python 3.10 or later.

  • Execution containers and workspaces are single-use and ephemeral; persistent per-agent workspaces are described as a roadmap item.
  • Network access is disabled by default, with optional allowlists per job type.
  • The default strict security mode requires gVisor; the documented permissive fallback to standard Docker removes the userspace-kernel boundary and is not intended for untrusted code.
  • The README documents an API server, worker pool and PostgreSQL-backed execution history.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install and start the Takovm server

Install the server package, prepare its executor image and start the API server.

Before you start

  • Docker
  • Python 3.10 or later

Steps

  1. Install the server extra with the command below.

    Documented command
    pip install "tako-vm[server]"

  2. Run tako-vm setup to pull the executor Docker image.

  3. Run tako-vm server to start the server; the documented command auto-starts PostgreSQL via Docker.

Expected outcome

The Takovm API server starts with PostgreSQL managed via Docker.

Guide limitations

  • This setup recipe does not cover submitting an execution job.
  • The project’s default strict security mode requires the gVisor userspace-kernel boundary.
Documentation 1 ↗
Source-based practical guide

Submit a Python execution request

Send a Python code snippet to a running local Takovm server.

Before you start

  • A running Takovm server at http://localhost:8000

Steps

  1. Send a POST request to http://localhost:8000/execute.

  2. Set the Content-Type header to application/json.

  3. Provide a JSON body with a code field, such as {"code": "print(1 + 1)"}.

Expected outcome

The example submits Python code for execution through the REST API.

Guide limitations

  • The README’s example does not document how to inspect or interpret the response.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
12 October 2026
Original website title
Tako-Research/TakoVM · Official homepage title · retained in its source language
How we review sourcesSuggest a correction