HarnessMatch

Search 52 product records by name, workflow, interface, or documented capability.

Quick access
Use ↑ ↓ to move, Enter to open, Esc to close.

Quick access links shown.

Menu

Agent platform

OpenSquilla

Broad open-source agent platform with policy modes, subagents, replay, and channels.

Status
Active
License
Apache-2.0
Evidence
Documented + code-verifiable, 9 sources
Product record checked
2026-07-28
Compare harnessesInspect sources

At a glance

An Apache-licensed general agent platform that qualifies as a coding harness through its adaptive tool loop, repository and shell tools, managed session context, and runtime permission modes. It adds delegated sessions, MCP bridging, one-shot CLI runs, replay diagnostics, memory, web and desktop surfaces, and multiple messaging channels.

Good choice if

  • Users who want one open agent runtime across terminal, web, desktop, and messaging channels
  • Automated workflows that need one-shot JSON output, durable sessions, and diagnostic replay
  • Teams that want explicit permission modes and platform-dependent sandbox enforcement

Check before choosing

  • OpenSquilla is a broad general-agent platform rather than a coding-only tool, so setup and surface area are larger than a focused CLI
  • Sandbox enforcement is platform-dependent; bypass and full-access permission modes deliberately weaken policy controls and must not be treated as equivalent to restricted mode
  • Subagents use isolated session contexts and MCP is exposed as a bridge, but neither mechanism is evidence of task quality
See 2 more considerations
  • Web-search tools do not establish full browser automation, and transcript or planning checkpoints are not represented as file rollback
  • The repository's tests, router experiments, and evaluation-like assets are project-owned; no comparative score is imported

Why it qualifies as a coding harness

This confirms category fit, not product quality. Every required criterion links back to first-party evidence.

Qualifies4 of 4 required criteria evidenced

  • Adaptive agent loop

    Documented

    The system repeatedly observes results and chooses the next action instead of following a fixed one-pass graph.

    EvidenceOpenSquilla agents

  • Repository tool execution

    Documented

    The system can use tools to inspect and change a repository or its execution environment.

    EvidenceOpenSquilla tools and sandbox

  • Task-aware context management

    Documented

    The runtime assembles, updates, compacts, retrieves, or persists task-relevant context while work proceeds.

    EvidenceOpenSquilla sessions

  • Model-independent runtime control

    Documented

    Permissions, budgets, interruption, policy, or stop controls operate outside the model's own text generation.

    EvidenceOpenSquilla approvals and permissions

Membership establishes category fit only. It does not score quality, safety, autonomy, model capability, or benchmark performance. · Read the membership rule.

How it works under the hood

Seven mechanisms mapped from first-party records. These labels describe what the harness provides, not how intelligent its model is.

7/7layers documented
  • Execution & isolationSandbox availableDocumented mechanism, not a performance score.
  • Tooling & integrationsExtensible toolsDocumented mechanism, not a performance score.
  • Context & statePersistent stateDocumented mechanism, not a performance score.
  • Lifecycle & recoverySession resumeDocumented mechanism, not a performance score.
  • ObservabilityStructured tracesDocumented mechanism, not a performance score.
  • VerificationTool-assistedDocumented mechanism, not a performance score.
  • Governance & permissionsPolicy controlsDocumented mechanism, not a performance score.

Public code audit

5/5public artifacts present
Security policy
Present at inspected commit
CI workflow
Present at inspected commit
Automated tests
Present at inspected commit
Evaluation assets
Present at inspected commit
Contributor documentation
Present at inspected commit

The inspected tree contains 3,807 files, 13 workflows, 1,584 test-like paths, security and contributor documentation, and a small set of evaluation-like assets. Router experiments and project-owned tests are development evidence rather than independent harness measurements, so no comparative score is imported.

Inspect commit f569e05de52dcc1e3954bbcbebe1b10106cdba6e, checked 2026-07-28

Measured configurations

No benchmark run passes the full metadata admission policy for this harness yet. Missing data is not scored as zero.

Benchmark policy and all runs

Capability support

Documented first-class product support, checked against the sources below.

External tools (MCP)
DocumentedProduct-supported MCP integrationSource · checked 2026-07-28The source establishes the mechanism, not its quality or availability in every mode.
Local models
DocumentedLocal or self-hosted model pathSource · checked 2026-07-28The source establishes the mechanism, not its quality or availability in every mode.
Agent parallelism
DocumentedDelegated or parallel agent workflowSource · checked 2026-07-28The source establishes the mechanism, not its quality or availability in every mode.
Runs without an open UI
DocumentedNon-interactive or automation surfaceSource · checked 2026-07-28The source establishes the mechanism, not its quality or availability in every mode.
Browser control
Not documentedNo first-class support established by the current recordAbsence of current documentation is not proof that the capability is impossible.
Isolated execution
Depends on surfaceOS- and permission-mode-dependent execution isolationSource · checked 2026-07-28Availability and enforcement vary by platform; bypass and full-access modes deliberately weaken the boundary.
Undo file changes
Not documentedNo first-class support established by the current recordAbsence of current documentation is not proof that the capability is impossible.

Primary evidence

Each capability claim is tied to a first-party record and a verification date.

Product record checked 2026-07-28
OpenSquilla overviewAgent platform surfaces, providers, memory, coding tools, channels, installation, and product boundariesOfficial repositoryOpenSquilla tools and sandboxFilesystem, shell, Git, web, memory and session tools plus platform-dependent sandbox behaviorOfficial repositoryOpenSquilla approvals and permissionsRestricted, on-request, bypass and full-access modes, approval flow, workspace policy, and control limitationsOfficial repositoryOpenSquilla sessionsDurable session records, resume, abort, export, delegated session handling, and operational stateOfficial repositoryOpenSquilla agentsAgent configuration, iterative execution, context, tools, skills, memory, and delegationOfficial repositoryOpenSquilla CLIInteractive terminal use, one-shot prompts, JSON output, remote access, and automation surfacesOfficial repositoryOpenSquilla MCP serverMCP bridge lifecycle, transports, exposed tools, client configuration, and security considerationsOfficial repositoryOpenSquilla diagnostics and replayStructured diagnostic bundles, event timelines, replay, redaction, and troubleshooting boundariesOfficial repository
View 1 additional sources
Additional first-party evidence1 sources
OpenSquilla inspected source treePinned source, security and contributor policies, CI, tests, application surfaces, and project-owned evaluation assetsOfficial repository

Ecosystem context

OpenRouter coding app directory Used as a discovery lead only; capability and lifecycle claims are pinned to the official repository. Observed 2026-07-28.