Persistent agent dev environments

Scores as of 2026-09-14 (43 days old; Depot marks scores stale after 30 days). The pick is still Depot's current editorial pick; it has not been re-reviewed since. Prices below carry their own dates.

Depot Pick

Daytona · 8.24/10 for this job (curated estimate, high confidence)

capability persistence + dx.

Runner-up

E2B · 8.56/10

Scores higher than the pick on: Capability fit, Latency / reliability, Developer & agent DX, Privacy / data retention, Maturity / track record.

When not to use the pick

Disposable single-run code — E2B.

Lock-in / migration

The pick has lower stored lock-in risk than runner-up E2B (3 vs 4). Pick exit signals: open source (provider tag `oss`). Self-host fallback listed for this job: Development Container Specification.

Sourced price (usd_per_vcpu_hour)

Pick's lowest sourced SKU: vCPU $0.0504 (usd_per_vcpu_hour) — source, as of 2026-10-27, re-checked 2026-10-27

Cheapest matching SKU: Daytona vCPU $0.0504 — source, as of 2026-10-27, re-checked 2026-10-27. The pick is the cheapest.

Price history: first seen 2026-10-03 · last changed no change recorded · history JSON

Free option

• Development Container Specification (oss) — source, as of 2026-10-25

Failure modes to watch

• Context overflow: If the input exceeds the window, say so and retrieve a narrower slice. Do not answer from a truncated head as if it were the whole source.
• Benchmark protocol mismatch: Store assisted-or-not, subset, and harness version beside every cited score. Refuse a ranking that mixes those fields.
• Collateral side effects: Snapshot the workspace or app state, then diff it against an allowlist. A passing check plus an unexpected diff is a failure.
• Eval contamination: Keep gold labels out of the agent prompt. Store the harness version beside the score. Do not compare a number across a benchmark revision without saying the revision changed.
• Hallucinated tool arguments: Reject a call that fails the current schema or names an unknown id, and do that before the tool runs a side effect.
• Instruction drift: Restate the stop condition in the trace. End the run when it is met. Review long traces for steps that do not serve the original task.

Reported outcomes (submitted reports only)

This job: loading… JSON · reports never change scores · seed/test records excluded

Depot Pick (Daytona) on this job: loading… JSON · reports never change scores · seed/test records excluded

Cite: Agent Provider Depot, Depot Pick for persistent-dev-env: daytona, scores as of 2026-09-14. Agents: GET /api/decide?jtbd=persistent-dev-env