HarnessMatch
Menu

Coding agent

OpenCode

Model-agnostic coding agent with a broad, configurable surface.

Status
Active
License
MIT
Evidence
Documented + code-verifiable, 25 sources
Product record checked
2026-07-27
Compare harnessesInspect sources

At a glance

An open-source, client-server coding agent across terminal, desktop, IDE, local web, SDK, and headless modes, with broad provider and subscription support, local models, granular permissions, MCP, parallel subagents, Git-backed undo and redo, and GitHub automation.

Good choice if

  • Developers who switch between providers and subscription paths
  • Local-model and custom-endpoint workflows
  • Teams that want configurable primary agents, subagents, and permissions

Check before choosing

  • Execution is host-first with no built-in OS or container sandbox; shell commands, plugins, custom tools, and local MCP servers inherit the user's privileges
  • The default Build agent has full tool access and most permission classes default to allow; granular ask/deny rules are application policy rather than an isolation boundary, and --auto approves every non-denied request
  • Git-backed undo and redo require a Git repository, omit ignored files and untracked files over 2 MB from snapshots, and cannot reverse network, process, database, or other external side effects
See 3 more considerations
  • The local web/server surface has no password unless OPENCODE_SERVER_PASSWORD is set; localhost binding is safe for ordinary local use, but network exposure needs deliberate authentication and CORS configuration
  • Browser automation is not built in: web fetch and web search retrieve content, while interactive browsing needs an external MCP or custom tool
  • Provider breadth improves choice but adds model, credential, routing, and privacy decisions; optional public sharing uploads the full conversation and remains accessible until unshared

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.

    EvidenceOpenCode introduction

  • Repository tool execution

    Documented

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

    EvidenceBuilt-in and custom tools

  • Task-aware context management

    Documented

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

    EvidenceAgents and permissions

  • Model-independent runtime control

    Documented

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

    EvidencePermission policy

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 & isolationHost processDocumented mechanism, not a performance score.
  • Tooling & integrationsExtensible toolsDocumented mechanism, not a performance score.
  • Context & stateManaged contextDocumented mechanism, not a performance score.
  • Lifecycle & recoveryCheckpoint/rewindDocumented 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.

Public code audit

4/5public artifacts present
Security policy
Present at inspected commit
CI workflow
Present at inspected commit
Automated tests
Present at inspected commit
Evaluation assets
Not found
Contributor documentation
Present at inspected commit

The 1.18.5 tree contains 901 test-like files and 26 workflows. Two UI performance benchmark paths measure application rendering, not coding-task success; no independent or complete model × harness evaluation record is inferred from them.

Inspect commit e5cc278dec9294a627a7b05f47ce6a564408c1a2, 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

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.
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
Not documentedNo first-class support established by the current recordAbsence of current documentation is not proof that the capability is impossible.
Isolated execution
No built-in supportHost execution; permission rules are not process isolationSource · checked 2026-07-27The official security policy explicitly states that OpenCode has no sandbox.
Undo file changes
DocumentedProduct-supported file or session rollbackSource · checked 2026-07-27The source establishes the mechanism, not its quality or availability in every mode.

Primary evidence

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

Product record checked 2026-07-27
OpenCode introductionTerminal, desktop, IDE, installation, and basic provider setupOfficial docsProvidersMore than 75 cloud, subscription, gateway, OpenAI-compatible, and local providersOfficial docsModelsProvider and model selection, local models, variants, defaults, and model-quality warningOfficial docsAgents and permissionsPrimary agents, parallel subagents, built-in roles, compaction, models, and per-agent permissionsOfficial docsPermission policyAllow, ask, deny, permissive defaults, command patterns, external paths, and auto modeOfficial docsTerminal interfaceSessions, compaction, export, sharing, and Git-dependent undo and redoOfficial docsCommand-line interfaceInteractive, run, server, attach, session fork, auto approval, and automation commandsOfficial docsBuilt-in and custom toolsHost tools, web retrieval, permission controls, custom tools, MCP, and ignore behaviorOfficial docs
View 17 additional sources
Product and interfaces2 sources
Headless serverOpenAPI server, localhost default, optional Basic auth, event stream, and client APIsOfficial docsLocal web interfaceBrowser client, local binding, optional password, network exposure, CORS, and shared stateOfficial docs
Execution and control1 sources
Pinned security policyExplicit absence of a sandbox, permission-policy boundary, local server authentication default, and security disclosure processOfficial repository
Agents, state and recovery3 sources
Rules and project instructionsAGENTS.md hierarchy, reusable instructions, compatibility files, and context scopeOfficial docsGit snapshot implementationSnapshot storage, Git-only enablement, ignored and large-file exclusions, restore, and pruningOfficial repositorySession revert implementationMessage undo and redo, snapshot restoration, patch reversal, and session-state cleanupOfficial repository
Automation and extensions6 sources
MCP serversLocal and remote MCP transports, OAuth, enablement, environment, permissions, and context costOfficial docsPluginsLocal and npm plugins, hooks, custom authentication, tool interception, and execution scopeOfficial docsSkillsProject and user skills, discovery, permissions, metadata, and lazy loadingOfficial docsLSP integrationLanguage-server diagnostics, supported servers, custom configuration, and disablementOfficial docsSDKTyped programmatic client, server lifecycle, sessions, messages, events, and automationOfficial docsGitHub automationIssue and pull-request agents, schedules, workflow permissions, secrets, branches, and reviewsOfficial docs
Enterprise and operations3 sources
Conversation sharingManual, automatic, and disabled sharing, public-link retention, deletion, and privacy guidanceOfficial docsEnterprise deploymentCentral configuration, SSO, gateway restrictions, data path, sharing caveat, and roadmap limitsOfficial docsProvider policiesExperimental provider allow and deny policy, precedence, wildcard matching, and scopeOfficial docs
Releases and public code audit2 sources
OpenCode 1.18.5 releaseCurrent stable distribution release used for product-version verificationOfficial announcementOpenCode source treePinned 1.18.5 implementation, security policy, tests, workflows, clients, and licenseOfficial repository