Extensible harness

PostQode

Modular coding-agent stack for IDE, terminal, browser tools, and headless CI.

Status
Active
License
Proprietary
Evidence
Documented, 8 sources
Product record checked
2026-07-28

At a glance

A proprietary product with public versioned npm packages for its multi-turn agent loop, coding tool pack, persistent memory, headless runner, MCP client, browser automation, and lightweight terminal UI, plus an IDE-oriented product surface spanning multiple model providers.

Good choice if

  • TypeScript teams assembling a coding agent from public, modular runtime packages
  • Headless or GitHub Actions workflows that need turn, cost, retry, and session controls
  • IDE users who need provider choice, MCP, and optional browser automation in one product family

Check before choosing

  • The public website still advertises the retired unscoped postqode package; the current installable artifacts use scoped @postqode package names
  • The repository URL declared by the npm packages was not publicly accessible when checked, so the product is documented from immutable package publications but is not classified as code-verifiable by the repository audit
  • No execution sandbox is established by the reviewed public packages; filesystem, terminal, browser, and MCP tools therefore enlarge the host-side trust boundary
See 2 more considerations
  • The product markets a multi-agent architecture, but the public package record establishes a configurable single-agent loop and parallel tools rather than a documented delegated-agent mechanism; subagents therefore remain uncredited
  • Vendor claims, package tests, and promotional material are not benchmark evidence and do not affect the recommendation score directly

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

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 + browserDocumented mechanism, not a performance score.
  • Context & statePersistent stateDocumented 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.

Public code audit

No official public repository was located for a code-level audit.

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
Depends on surfacePrivate or self-hosted model paths on enterprise deploymentsSource · checked 2026-07-28The source establishes the mechanism, not its quality or availability in every mode.
Agent parallelism
Not documentedNo first-class support established by the current recordAbsence of current documentation is not proof that the capability is impossible.
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
OptionalOptional browser-automation tool packageSource · checked 2026-07-28The source establishes the mechanism, not its quality or availability in every mode.
Isolated execution
Not documentedNo first-class support established by the current recordAbsence of current documentation is not proof that the capability is impossible.
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

Ecosystem context

OpenRouter coding app directory Used to discover PostQode; the OpenRouter listing is not used to establish product capability. Observed 2026-07-28.