General-purpose agent

goose

Open standards, native apps, and broad workflow automation.

Status
Active
License
Apache-2.0
Evidence
Documented + code-verifiable, 21 sources
Product record checked
2026-08-22

At a glance

An open-source general agent with desktop, CLI, and headless use, broad provider, subscription, and local-model access, plus built-in skills, MCP extensions, recipes, subagents, browser control, configurable approvals, and platform-specific isolation.

Good choice if

  • Open-standard and MCP-heavy workflows
  • Users who want desktop, CLI, headless, local-model, and subscription choices
  • Reusable automation through built-in skills, recipes, extensions, and subagents

Check before choosing

  • Broader than a code-only specialist
  • Developer tools run autonomously with user privileges by default unless approval policies are configured
  • The documented native OS sandbox is specific to goose Desktop on macOS; other isolation paths are optional
See 5 more considerations
  • Adversary Mode is optional, reviews only configured tools, and fails open when its reviewer fails; prompt-injection detection is also optional and cannot catch every threat
  • ML-based prompt-injection detection can send tool-call content and recent messages to the configured classifier endpoint, while allowed commands still run with the user's full permissions
  • goose CLI versions before 1.44.0 are affected by a high-severity arbitrary-command-execution advisory in goose review and should not be treated as equivalent to the verified release
  • Built-in skills can be disabled, but enabled skill instructions remain content to review separately from the harness capability
  • Large-repository support uses analysis tools and context guards, not a documented persistent repository index or scale guarantee

Capability support

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

External tools (MCP)
DocumentedProduct-supported MCP integrationSource · checked 2026-07-27The source establishes the mechanism, not its quality or availability in every mode.
Reusable skills
DocumentedProduct-supported reusable skill packagesSource · checked 2026-08-01Support does not establish portability, package quality, safety, or adoption.
Local models
DocumentedLocal or self-hosted model pathSource · checked 2026-07-27The source establishes the mechanism, not its quality or availability in every mode.
Agent parallelism
DocumentedDelegated or parallel agent workflowSource · checked 2026-07-27The source establishes the mechanism, not its quality or availability in every mode.
Runs without an open UI
DocumentedNon-interactive or automation surfaceSource · checked 2026-07-27The source establishes the mechanism, not its quality or availability in every mode.
Browser control
DocumentedBuilt-in or product-supported browser controlSource · checked 2026-07-27The source establishes the mechanism, not its quality or availability in every mode.
Isolated execution
DocumentedDocumented execution-isolation mechanismSource · checked 2026-07-27The source establishes the mechanism, not its quality or availability in every mode.
Undo file changes
Not documentedNo first-class support established by the current recordAbsence of current documentation is not proof that the capability is impossible.

Getting started

Install the desktop app or CLI, select a provider, configure approval or sandbox controls, and enable only the extensions needed for the workflow.

Open official documentation

Classification and operating model

Category fit and technical mechanisms are evidence records, not product-quality scores.

Category fit
Qualifies, 4/4 criteria
Operating model
7/7 layers documented
Inspect category criteria and operating mechanismsFirst-party records

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.

  • Repository tool execution

    Documented

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

  • Task-aware context management

    Documented

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

  • Model-independent runtime control

    Documented

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

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 + browserDocumented mechanism, not a performance score.
  • Context & stateManaged contextDocumented mechanism, not a performance score.
  • Lifecycle & recoverySession resumeDocumented mechanism, not a performance score.
  • ObservabilityLogs/transcriptsDocumented mechanism, not a performance score.
  • VerificationTool-assistedDocumented mechanism, not a performance score.
  • Governance & permissionsPolicy controlsDocumented mechanism, not a performance score.

Measured and public context

Configuration-specific measurements and source-native activity stay separate from general product capability.

Inspect code audit, measured configurations, and ecosystem signalsContext, not a product 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 repository contains project-owned Harbor and Terminal-Bench tooling with one-attempt snapshots; these are auditable artifacts, not independent benchmark evidence.

Inspect commit 2855b87a659536a441ecf117ce9bd10b6053f55a, checked 2026-07-27

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
Context, not quality

Public ecosystem signals

Source-native observations for exact mapped artifacts and reviewed stable release trains. Different units and populations stay separate, and missing coverage is never treated as zero.

View this harness in Usage
  • Latest stable releasev1.49.0Released 2026-09-03; 12 stable releases in 90 daysOpen release
  • OpenRouter 30d tokens170.54B#22 coding app; 2026-08-09 to 2026-09-07Open app page
  • Homebrew 30d events2.03KFormula: block-goose-cliOpen artifact
  • Release asset downloads711.04K120 stable releases; 797 matched assetsOpen artifact
  • GitHub stars54.02KFull-source repository; 6.21K forksOpen artifact

Routing, package retrievals, release downloads, editor installs, and repository interest observe different populations. They are never added together and never affect capability evidence, classification, or measured results.

Interpretation rulesSignals checked

First-party evidence

Each capability claim links to the first-party record that supports it.

21 first-party sourcesProduct record checked

Product and interfaces

2 sources
View 1 more source

Execution and control

7 sources
View 6 more sources

Agents, state and recovery

4 sources
View 3 more sources

Automation and extensions

2 sources
View 1 more source

Enterprise and operations

2 sources
View 1 more source

Releases and public code audit

4 sources
View 3 more sources