Leyline Sorcery
← Catalogue
runtimeseed

Grok (xAI)

Reasoning and tool-using models plus a CLI harness. Leyline's own intake processor runs on the Grok Heavy subscription.

MCP declaredAPI declaredCost seatLicence proprietary

Interface

mcp

Model Context Protocol server

Interface

http

HTTP API

Plan with Grok (xAI)Open homepageRead docs

[ Observed sample ]

Frequency in Leyline's observed sample

The count is distinct observed stacks. It is not a Score input.

This component is not in Leyline's observed sample.

Record cmp_grok-xai

Open ranks

[ Score explain ]

Why the Score is 21

How Score works

Score v2 uses only observed signals. The displayed contribution is weight × value × 100. Missing factors are insufficient evidence.

Score factor

GitHub health

18% weight. A licence is declared. Documentation is available.

Value 0.30 · 5.4 points

18% weight × 0.30 value

5.4 points

A licence is declared. Documentation is available.

Score factor

Agent use

16% weight. insufficient evidence

insufficient evidence

insufficient evidence

insufficient evidence

insufficient evidence

Score factor

Human notes

14% weight. 1 stored human notes (component-record).

Value 0.09 · 1.2 points

14% weight × 0.09 value

1.2 points

1 stored human notes (component-record).

Score factor

Composability

16% weight. insufficient evidence

insufficient evidence

insufficient evidence

insufficient evidence

insufficient evidence

Score factor

Checklist

10% weight. An MCP surface is declared. An API is declared. Cost is seat. 3 of 3 checklist fields are complete.

Value 1.00 · 10.0 points

10% weight × 1.00 value

10.0 points

An MCP surface is declared. An API is declared. Cost is seat. 3 of 3 checklist fields are complete.

Score factor

Evidence quality

14% weight. 2 sources cover 2 evidence types. The latest dated evidence is 2026-09-12. Freshness is omitted unless observed as a signal.

Value 0.33 · 4.6 points

14% weight × 0.33 value

4.6 points

2 sources cover 2 evidence types. The latest dated evidence is 2026-09-12. Freshness is omitted unless observed as a signal.

Score factor

Benchmarks

12% weight. insufficient evidence

insufficient evidence

insufficient evidence

insufficient evidence

insufficient evidence

Total21.21 → 21 after rounding

Agent use: insufficient evidence

Composability: insufficient evidence

Benchmarks: insufficient evidence

[ Claims ]

Publisher-asserted record

Claims are what the publisher declares. Score uses observed signals, not these assertions, except for checklist fields derived from interfaces. MCP, API, cost, and license claims are marked verified, unverified, or contradicted from intake evidence.

Kind
runtime
Interfaces

Interface

mcp

Model Context Protocol server

Interface

http

HTTP API

Functions

Function

Generate

produce new text, code, or media

Generate Browse Generate

Function

Reason

plan or chain steps

Reason Browse Reason

Function

Code

write or edit programs

Code Browse Code

Function

Tool-call

invoke an external action

Tool-call Browse Tool-call

Function

Connect

speak a protocol (MCP, API, CLI)

Connect Browse Connect
Tags
None recorded

[ Capability slices ]

Compose the useful parts.

reason

Grok Heavy CLI

Local grok-heavy --single for structured jobs

Heavy subscription quotaCompose with this
search

Search

Reasoning and tool-using models plus a CLI harness. Leyline's own intake processor runs on the Grok Heavy subscription.

seatCompose with this
code

Code

Reasoning and tool-using models plus a CLI harness. Leyline's own intake processor runs on the Grok Heavy subscription.

seatCompose with this
tool-call

Tool-call

Reasoning and tool-using models plus a CLI harness. Leyline's own intake processor runs on the Grok Heavy subscription.

seatCompose with this
connect

Connect

Reasoning and tool-using models plus a CLI harness. Leyline's own intake processor runs on the Grok Heavy subscription.

seatCompose with this

CLI --single, JSON schema, MCP/skills. Subscription quota is the operational bound, not an API glue problem.

[ Relations ]

Derived alternatives and shared slots

  • Alternative to
    Codex Shared functions code, connect, reason, tool-call. Same kind and overlapping capability.
  • Alternative to
    Claude Code Shared functions code, connect, reason, tool-call. Same kind and overlapping capability.
  • Alternative to
    Cursor Shared functions code, connect, reason, tool-call. Same kind and overlapping capability.
  • Fills the same slot as
    kogiQA MCP Web Browser Shared functions code, connect, generate, search. Can fill the same function slot.
  • Fills the same slot as
    Monid Shared functions connect, search, tool-call. Can fill the same function slot.
  • Fills the same slot as
    41 Open-Source LLMs Evaluated on 19 Benchmarks Shared functions generate, reason, search. Can fill the same function slot.
  • Fills the same slot as
    Exa Shared functions connect, search, tool-call. Can fill the same function slot.
  • Fills the same slot as
    Executor Shared functions code, connect. Can fill the same function slot.

[ Signals ]

Observed evidence and source claims

Signals carry source, method, and observedAt. Source review dates and evidence basis are shown separately. Unobserved metrics stay insufficient evidence.

  • docs
    xAI docs

    Evidence basis unknown · Check date unknown · Source date 2026-09-12

  • web
    x.ai

    Evidence basis unknown · Check date unknown · Source date 2026-09-12

Introducing Grok Bot, now in early beta. Bots are AI teammates that do real work for you. They sign in to your tools, use them just like you do, and come back ...

Source: x.com

Grok 4.5 is described by xAI as its flagship model for code and general work, with agentic tool calling, configurable reasoning, and support for long-context ...

Source: x.com

Some of Grok Build's most foundational tools are not xAI's at all. The third-party notices are explicit: `apply_patch`, `grep_files`, `list_dir`, and `read_file ...

Source: x.com
Suggest a correction

Propose a change with a public source. Corrections wait for review before the card changes.

[ Notes ]

humanLeyline intake uses grok-heavy --single the way Soundcheck's planner does.