Show HN: TakoVM – open-source sandboxing for your agent's code

Tako Research released TakoVM, an open-source sandboxing tool for AI agent code execution that provides Docker isolation, job queues, execution history, and retry logic out of the box. The tool aims to simplify secure code execution for enterprise teams deploying AI agents by bundling infrastructure components that standalone sandbox solutions lack.

File system and python execution for your agents. Job queues and Docker isolation built-in. Used by teams deploying in enterprise. English | 日本語 /Tako-Research/TakoVM/blob/main/README.ja.md A secure file system for your agents to execute code. Every job runs in its own isolated Docker container, with an ephemeral workspace, optional gVisor sandboxing, job queues, retries, and execution history included. Where this is headed:durable, per-agent workspaces that persist and rehydrate across runs, a serverless filesystem for agents. Today each container is single-use; persistent workspaces are on the roadmap. gVisor remains the sole isolation boundary. Documentation https://tako-research.github.io/TakoVM/ · · https://tako-research.github.io/TakoVM/getting-started/quickstart/ Quick Start API Reference Install requires Docker + Python 3.10+ pip install "tako-vm server " tako-vm setup pull the executor Docker image tako-vm server start server auto-starts PostgreSQL via Docker Execute code curl -X POST http://localhost:8000/execute \ -H "Content-Type: application/json" \ -d '{"code": "print 1 + 1 "}' Sandbox solutions like e2b https://e2b.dev , daytona https://daytona.dev and microsandbox https://github.com/microsandbox/microsandbox give you isolated code execution, but that's it. You still need to build: | You build | With sandbox-only | With Tako VM | |---|---|---| | Job queue | Redis + Celery/Bull | Built-in | | Execution history | Postgres + schema | PostgreSQL included | | Retry logic | Custom code | Automatic | | Idempotency | Deduplication logic | idempotency key | | Replay/debugging | Custom tooling | Rerun/fork API | Tako VM is the complete package: Job queue + workers - Async execution with worker pool, no Redis/Celery setup Execution history - Every job persisted with stdout, stderr, timing, artifacts Replay to debug - Rerun past jobs with exact same code and inputs Docker isolation - Each job in its own container with seccomp filtering Network isolation - No network by default, optional allowlist per job type Self-hosted - Your machine, offline-capable, zero per-execution cost tako-vm setup Pull executor image and verify Docker tako-vm server Start the API server tako-vm server --port 9000 Custom port tako-vm dev up Start local PostgreSQL for development tako-vm dev up --with-server Start PostgreSQL + API server tako-vm dev status Check local PostgreSQL status tako-vm dev down Stop local PostgreSQL tako-vm config Show current configuration tako-vm config --json Output as JSON tako-vm validate Validate current config tako-vm validate my.yaml Validate specific file tako-vm status Check server health tako-vm version Show version tako-vm --config my.yaml server Use specific config file | Topic | Link | |---|---| | Installation | | docs/getting-started/quickstart.md /Tako-Research/TakoVM/blob/main/docs/getting-started/quickstart.md docs/getting-started/configuration.md /Tako-Research/TakoVM/blob/main/docs/getting-started/configuration.md docs/api/rest.md /Tako-Research/TakoVM/blob/main/docs/api/rest.md docs/api/sdk.md /Tako-Research/TakoVM/blob/main/docs/api/sdk.md docs/guide/environments.md /Tako-Research/TakoVM/blob/main/docs/guide/environments.md docs/guide/filesystem-and-caches.md /Tako-Research/TakoVM/blob/main/docs/guide/filesystem-and-caches.md docs/deployment/security.md /Tako-Research/TakoVM/blob/main/docs/deployment/security.md docs/deployment/how-to-deploy.md /Tako-Research/TakoVM/blob/main/docs/deployment/how-to-deploy.md tako vm.yaml.example /Tako-Research/TakoVM/blob/main/tako vm.yaml.example Tako VM runs untrusted, often AI-generated, code, so isolation is the core of the project. It uses layered defenses: gVisor userspace kernel , per-job ephemeral Docker containers, a default-deny seccomp profile, network isolation --network=none by default , capability dropping, non-root execution, and enforced resource and input limits. For untrusted workloads in production, set security mode: strict with container runtime: runsc . The default permissive mode falls back to standard Docker runc if gVisor is unavailable, which removes the userspace-kernel boundary. See SECURITY.md /Tako-Research/TakoVM/blob/main/SECURITY.md for the threat model and hardening guidance, and docs/deployment/security.md /Tako-Research/TakoVM/blob/main/docs/deployment/security.md for full details. Found a vulnerability? Report it privately via the Security tab https://github.com/Tako-Research/TakoVM/security → Report a vulnerability . Please do not open public issues for security findings. Contributions are welcome See CONTRIBUTING.md /Tako-Research/TakoVM/blob/main/CONTRIBUTING.md for dev setup, testing, and PR conventions. Good entry points are issues labeled good first issue https://github.com/Tako-Research/TakoVM/issues?q=is%3Aissue+is%3Aopen+label%3A%22good+first+issue%22 , and Discussions https://github.com/Tako-Research/TakoVM/discussions is open for questions and ideas. Questions, feedback, or partnership inquiries? Reach out to seiji@intencion.io mailto:seiji@intencion.io . Apache License 2.0