Coding agent

Slate

Proprietary terminal harness for long tasks, parallel agents, skills, and headless execution.

Status
Active
License
Proprietary
Evidence
Documented, 8 sources
Product record checked
2026-08-08

At a glance

A proprietary coding harness from Random Labs for repository-scale terminal work, with provider and model-slot selection, granular tool permissions, session steering and resume, parallel and background subagents, reusable skills, MCP, long-running shells, headless structured output, and an HTTP server mode. Execution is host-first: permissions govern tool calls but the reviewed documentation does not establish an operating-system sandbox.

Good choice if

  • Long repository tasks that need deliberate context management, project instructions, session continuation, and active steering
  • Parallel research, implementation, and verification workflows using child sessions, background agents, and trace views
  • A shared interactive and scripted workflow through the TUI, one-shot structured headless runs, queues, or the HTTP server

Check before choosing

  • Slate is proprietary and the published npm package exposes no official public source repository, so HarnessMatch could not perform an immutable implementation audit
  • Shells, workspace paths, and local MCP subprocesses execute on the host; no operating-system sandbox is documented, and --yolo bypasses every permission check
  • Server mode binds to 0.0.0.0 by default according to the current documentation, so remote exposure requires deliberate password, network, and host controls
See 4 more considerations
  • External workspaces, long-running shells, environment variables, skills, and MCP servers widen the trusted input and execution boundary and need separate review
  • Documented tests, reviewer agents, trace cards, and changed-file summaries support inspection but do not independently prove task success or benchmark quality
  • Session resume and queue persistence restore interaction state rather than rolling back files, shell effects, network actions, or external services; no checkpoint mechanism is documented
  • The quickstart warns that Windows may not work and recommends WSL, and it reports significant terminal flicker when Slate runs inside tmux

Capability support

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

External tools (MCP)
DocumentedProduct-supported MCP integrationSource · checked 2026-08-08The source establishes the mechanism, not its quality or availability in every mode.
Reusable skills
DocumentedProduct-supported reusable skill packagesSource · checked 2026-08-08Support does not establish portability, package quality, safety, or adoption.
Local models
Not documentedNo first-class support established by the current recordAbsence of current documentation is not proof that the capability is impossible.
Agent parallelism
DocumentedDelegated or parallel agent workflowSource · checked 2026-08-08The source establishes the mechanism, not its quality or availability in every mode.
Runs without an open UI
DocumentedNon-interactive or automation surfaceSource · checked 2026-08-08The 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
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.

Getting started

Install @randomlabs/slate 1.0.44, authenticate with Random Labs, choose a subscription or credit-backed model source, review project and global permission rules, avoid --yolo for untrusted work, and constrain any server or headless deployment externally.

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

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 & 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.

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

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
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
  • OpenRouter 30d tokens5.23B#78 coding app; 2026-08-09 to 2026-09-07Open app page
  • npm last-month downloads727Package: @randomlabs/slateOpen 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.

8 first-party sourcesProduct record checked

Product and interfaces

1 source

Execution and control

2 sources
View 1 more source

Agents, state and recovery

3 sources
View 2 more sources

Automation and extensions

1 source

Releases and public code audit

1 source

Ecosystem context

OpenRouter app profile Discovery and usage context only; Slate membership and capabilities are established from Random Labs documentation and immutable package metadata. Observed 2026-08-08.