Skip to content

[env] Cloud sandbox providers — Modal, Daytona, Northflank/e2b #144

Description

@0bserver07

Background

Chimera has chimera/env/ with Local, Docker, Git, Remote, Cloud, PersistentShell abstractions. The "Cloud" backend is largely a placeholder — actual cloud sandbox provider integration (Modal, Daytona, Northflank, e2b, Coder Cloud) was scoped in earlier session memory but never built.

For the ferret sandbox-first CLI and for ProgramBench-style benchmarks (which require isolated containers), cloud sandboxes would let users run agents without setting up Docker locally — and would unlock the "agent runs in cleanroom, no network" path that some benchmarks require.

Scope

Three providers, each as an Environment subclass:

  1. Modal — Python-native sandboxes, pay-per-second compute. chimera/env/modal_env.py.
  2. Daytona — workspace-as-code, supports custom images. chimera/env/daytona.py.
  3. Northflank or e2b — pick whichever has cleaner Python SDK.

Each:

  • Implements Environment ABC (provision, exec, read, write, teardown)
  • Has its own optional extra: pip install "chimera-run[modal]", etc.
  • Includes mocked unit tests + 1 live-gated integration test
  • Doc: docs/env/{modal,daytona}.md

Acceptance criteria

  • At least 2 of 3 providers shipped
  • Wired into chimera ferret --env modal etc.
  • Tests green; live-gated tests pass when credentials provided
  • Docs for each provider with quickstart + cost expectations

Estimated effort

Large — ~2 weeks. Could be broken into 3 issues (one per provider).

Why this matters

Cloud sandboxes are how teams scale agent benchmarks (each instance gets a fresh container). chimera ferret without cloud sandboxes is local-only; with them, it's competitive with the existing open-swe-agent workflow.

Metadata

Metadata

Assignees

No one assigned

    Labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions