Development environments / Ellipsis alternative

An Ellipsis.dev alternative for the execution layer you control

Ellipsis supplies a managed coding-agent platform, including repository agents, event triggers, persistent conversations, and environment configuration. Sandbox0 supplies the agent’s compute runtime. Replacing an agent application requires more than changing its underlying sandbox.

Start buildingCompare capabilities ↓

Reviewed 2026-10-18 · Published by the Sandbox0 team

When Ellipsis fits

Ellipsis fits teams that want ready coding agents connected to GitHub, Slack, Linear, or other supported events, with steering, session history, and repository-defined setup. Its managed and own-AWS offers run the broader platform.

When to consider Sandbox0

Consider Sandbox0 when building that agent application yourself and requiring a durable complete writable RootFS, automatic online growth, and supported file operations during compute pauses. Provide conversations, triggers, review workflows, and user-facing controls separately.

Capabilities

Ellipsis and Sandbox0: what persists?

Feature comparison with documentation and verification status
Environment and runtime lifetimeEllipsisNot established in this reviewSandbox0ttl and hard_ttl default to 0 (disabled). Configure idle pause and deletion policies for the same persistent sandbox identity; an idle running sandbox still accrues compute charges.Read documentation →
Persistent filesEllipsisReusable setup/images and conversation history do not establish a general retained machine-disk contract.View evidence ↗Sandbox0The writable RootFS survives successful checkpoints, including software, system configuration, dependencies, and user data.Read documentation →
Whole RootFSEllipsisCached dependencies in a base image are not evidence that all subsequent writable RootFS changes return across sessions.View evidence ↗Sandbox0Persistence extends beyond /workspace to paths such as /usr/local, /etc, and /home. Runtime tmpfs and virtual filesystems are excluded.Read documentation →
Release compute, keep stateEllipsisPersistent agent conversations do not establish compute-release and same-machine checkpoint semantics.View evidence ↗Sandbox0Pause compute between tasks; resume on available capacity. Default resume starts fresh processes from the saved filesystem.Read documentation →
Memory and process stateEllipsisThe reviewed environment product does not establish retained arbitrary process memory.View evidence ↗Sandbox0Experimental memory checkpoints can preserve compatible process state. Use memory: true on both pause and resume on a compatible deployment. A filesystem checkpoint alone does not preserve running processes.Read documentation →

Online RootFS growth

On growth-enabled images, Sandbox0 automatically expands the writable RootFS as free space runs low, within a configured sparse logical ceiling up to 64 TiB. Agent processes keep running. Growth is enabled in the qualified Cloud region; confirm activation for other regions. Existing images and snapshots retain their captured storage geometry. The ceiling is logical capacity, not preallocated host disk.

Reusable images and agent-session history do not establish automatic online expansion of the active complete writable RootFS. Sandbox0 addresses that compute/storage layer, while the broader coding-agent workflow remains separate.

Files while compute is paused

Sandbox0's Files API reads persistent files without resuming compute. Filesystem-only pauses also permit edits; retained-memory pauses are read-only and reject mutations with 409. SSH, SFTP, file watching, and runtime-only mounts require running compute.

See paused file operations →

A reusable environment image is different from an evolving user machine

Ellipsis describes caching installed dependencies in an image and keeping environment setup in git so sessions start from a shared configuration. The price page separately advertises durable agent conversations. Neither statement establishes that arbitrary machine-global changes or process memory survive every new agent session.

Source 1 ↗Source 2 ↗

Managed SaaS and own-AWS costs have different boundaries

The current price table gives managed CPU/RAM rates, while the own-AWS option leaves those resources billed by AWS. Both list a percentage platform fee on token cost and no per-seat fee. An AWS deployment is an Ellipsis product entitlement; it does not imply Sandbox0 currently offers Self Host or released BYOC.

Source 1 ↗

Support packages are optional, not the price of basic access

The price page explicitly says enterprise support packages are not required to use the platform. Do not add a support-package minimum to every self-service agent bill or assume a token-only headline includes all CPU and RAM. Check the effective model/subscription path and compute runtime.

Source 1 ↗

Pricing

Compare billing models, then price your workload

CPU allocation, memory, billing minimums, disk, plan fees, and supported workload differ. These meters are not equal-performance machine quotes. Confirm region, resource units, and included allowances before estimating a total.

Ellipsis

Pricing reviewed 2026-10-18

Managed CPU
$0.142 per vCPU-hour
Rate source ↗
Managed RAM
$0.024 per GB-hour
Rate source ↗
Platform fee
10% of token cost
Managed token cost is listed separately; supported interactive subscription paths have their own terms.
Rate source ↗
Per-seat fee
$0
Rate source ↗
Own-AWS resources
AWS resource charges plus platform usage
Rate source ↗

Token cost, the percentage platform fee, and managed CPU/RAM are separate lines. Support packages are optional. Preserve GB units and verify effective interactive-model subscription terms, retained state, and own-AWS costs; no feature-equivalent savings claim follows from unit rates.

Check current Ellipsis pricing ↗

Sandbox0

$0.015/GiB-hour compute (billed by the second at approximately $0.000004167/GiB-second), plus $0.02/GiB-month of retained incremental RootFS and memory checkpoint data. Shared base images and platform recovery retention are excluded; paused sandboxes accrue storage charges only.

Compute / GiB-hour
$0.015
Retained data / GiB-month
$0.02
Paused compute
$0.00

A 4 GiB agent, 100 running hours

$6.00 compute

4 GiB × 100 hours, billed by the second. Keeping 20 GiB of billable incremental data for a full billing month adds $0.40. CPU is derived from memory by the platform; choose a tier that fits your workload.

Understand storage billing →

Before migrating from Ellipsis

  1. Inventory agent definitions, triggers, repository setup, model paths, secrets, session history, and required environment outputs.
  2. Rebuild compatible tools in Sandbox0 and implement or retain the surrounding agent loop, event routing, review interface, and conversation storage.
  3. Validate equivalent workflows alongside system-state retention, RootFS growth, paused file access, and full token, platform, compute, and infrastructure cost.

Common questions

Is Sandbox0 a drop-in Ellipsis replacement?

Evaluate API compatibility and product scope. These products serve different core workflows, so a change may require a different architecture.

Does keeping files also keep a running agent?

Filesystem state and volatile process state are separate. Sandbox0 requires explicit compatible memory checkpoints to preserve running processes; its default filesystem resume starts fresh processes.

Sources and review scope

The Boat team's Battleships directory is the discovery source. References below describe the product and plan discussed on this page. Check current availability, regional terms and billing units before migrating. Where the cited material does not establish a capability or price, the comparison identifies that uncertainty.

Battleships research record ↗www.ellipsis.dev/platform/environments ↗www.ellipsis.dev/pricing ↗Sandbox0 RootFS capacity →

Related comparisons

Agency Tool Company vs Sandbox0 →Amp Orbs vs Sandbox0 →Bitrise RDE vs Sandbox0 →boxes.dev vs Sandbox0 →Capy vs Sandbox0 →Claw 2 Agent vs Sandbox0 →