AgentsAgent orchestrationAgent orchestration program

Agent orchestration fleet and recovery comparison

Preserves the durable multicode fleet strengths and the containment and recovery comparison across adjacent systems.

Summary

multicode demonstrates a strong fleet control plane, while Hazmat and Docker Sandboxes clarify the containment, credential, network, service, and recovery boundaries that fleet scale must not obscure.

Question and scope

Which comparative strengths constrain the current containment, fleet, and recovery design?

Method

This chapter retains qualitative findings and comparison dimensions from the products cataloged in the source chapter.

Findings

Multicode strengths

  1. Live observability of the agent. multicode derives status and resource columns from runtime state and displays them as the main operator surface.
  2. Per-workspace persistent SQLite. A small store underpins GitHub status, custom links, and telemetry.
  3. The tag protocol. <multicode:issue>, <multicode:pr>, and <multicode:repo> turn agent output into structured operator state without making the agent runtime itself part of the orchestrator.
  4. Resource limits as config. Memory, CPU, and file descriptor limits are declared near isolation config instead of being hidden in launch scripts.
  5. Operator extension points. Editor launchers, review tools, and custom hotkeys make the TUI an operator surface rather than a fixed dashboard.

jackin differentiators

  • Cross-platform Docker substrate instead of Linux-only bwrap.
  • Per-instance multi-runtime instead of one provider assumption.
  • Role repos as distribution units instead of ad-hoc skill/config mounts.
  • CLI-first with jackin console as the simplified front instead of a TUI-only product.
  • Toolchain-neutral orchestration instead of Micronaut/Java defaults baked into the orchestrator.
  • Security boundary honesty. multicode's README is explicit that its isolation is for safety and convenience, not security. jackin docs should preserve that kind of bluntness for every backend: dind is useful, but it is not a microVM; microVM is stronger, but still has workspace and credential policy caveats.

Containment and recovery comparison

Hazmat and Docker Sandboxes provide complementary containment and recovery evidence without defining jackin's product shape.

ConcernHazmatDocker Sandboxesjackin direction
Boundary explanationSession contract plus hazmat explainSecurity model docs and sandbox policy outputSession contract and explain mode
Strong local isolationmacOS user + seatbelt + pf; VM tier for hardest casesPer-sandbox microVMSelectable sandbox backends
Docker workflowsPrivate-daemon tier only; shared daemon rejected in containmentPrivate Docker Engine inside VMKeep DinD explicit, add microVM/private-daemon backend, reject silent host socket exposure
Network policypf plus DNS blocklist; exact-domain caveats documentedHost-side proxy, deny-by-default, non-HTTP blockedNetwork egress policy
Service portsService access appears in session contractsbx ports publishes host-to-sandbox traffic; host services use policy-approved aliasAdd service access and port mappings to session contract + network policy
Credential deliveryHost-owned secret store, materialized/brokered per harnessHost proxy injects credentials; values stay outside VMContainer credential exposure and host bridge
Stack ergonomicsIntegration manifests with strict "cannot widen trust" rulesTemplates/kits and agent-specific setupStack integration contracts plus role repos
RecoveryPre-session snapshots, restore, formal backup invariantsPersistent VM state; sbx rm cleanupSession snapshot and rollback plus disk/state budgets
Parallel Git workNot the main product focusDirect mode plus .sbx/ branch worktreesPer-mount isolation with jackin-owned worktree/clone modes
Proof / governanceTLA+ for setup, policy, backup, launch invariantsProduct security docsADRs and behavioral specs for host-side effects

Implications for jackin

Combine live fleet visibility with explicit containment contracts. Preserve CLI-first operation, role repositories, runtime neutrality, and honest per-backend risk descriptions.

Limitations and unknowns

Current jackin delivery commitments belong to linked roadmap and reference pages, not this comparative chapter.

Sources

On this page