RRepoGEO

REPOGEO REPORT · LITE

withcatai/node-llama-cpp

Default branch master · commit f655fd9f · scanned 6/19/2026, 7:11:57 AM

GitHub: 2,104 stars · 199 forks

Scan history for this repo

Score trend below includes all ready runs (older left, newer right; scroll horizontally if needed). The table is collapsed by default—expand for newest-first rows, 10 per page.

Score trend (left → right: older → newer)

2 ready scans. Expand the table below for newest-first rows (10 per page, paginated).

AI VISIBILITY SCORE
75 /100
Needs work
Category recall
2 / 2
Avg rank #4.5 when recommended
Rule findings
2 pass · 0 warn · 0 fail
Objective metadata checks
AI knows your name
2 / 3
Direct prompts that named your repo
HOW TO READ THIS REPORT

Action plan is what to do next — copy-pasteable changes prioritized by impact. Category visibility is the real GEO test: when a user asks an AI a brand-free question that should surface withcatai/node-llama-cpp, does the AI actually recommend you — or your competitors? Objective checks verify the metadata signals AI engines weight first. Self-mention check detects whether AI even knows you exist by name.

Action plan — copy-paste fixes

3 prioritized changes generated by gemini-2.5-flash. Mark items done after you ship the fix.

OVERALL DIRECTION
  • highreadme#1
    Strengthen the README's opening statement to highlight unique features

    Why:

    CURRENT
    <p>Run AI models locally on your machine</p>
    COPY-PASTE FIX
    <p>Run AI models locally on your machine with Node.js bindings for llama.cpp, featuring advanced capabilities like JSON schema enforcement and function calling.</p>
  • mediumabout#2
    Refine the 'About' description to emphasize key differentiators

    Why:

    CURRENT
    Run AI models locally on your machine with node.js bindings for llama.cpp. Enforce a JSON schema on the model output on the generation level
    COPY-PASTE FIX
    Node.js bindings for llama.cpp to run AI models locally, with advanced features like JSON schema enforcement and function calling.
  • lowreadme#3
    Add a 'Why node-llama-cpp?' section to summarize differentiators

    Why:

    COPY-PASTE FIX
    Add a new section, e.g., `## Why node-llama-cpp?` before the `## Features` section, with a concise summary like: "While many tools run LLMs locally, `node-llama-cpp` stands out by offering robust Node.js bindings for `llama.cpp` with unique capabilities such as strict JSON schema enforcement and powerful function calling, tailored for JavaScript/TypeScript developers."

Category GEO backends resolved for this scan: google/gemini-2.5-flash, deepseek/deepseek-v4-flash

Category visibility — the real GEO test

Brand-free queries asked to google/gemini-2.5-flash. Did AI recommend you, or someone else?

Same questions for every model — switch tabs to compare answers and rankings.

Recall
2 / 2
100% of queries surface withcatai/node-llama-cpp
Avg rank
#4.5
Lower is better. #1 = top recommendation.
Share of voice
13%
Of all named tools, what % are you?
Top rival
Ollama.js
Recommended in 1 of 2 queries
COMPETITOR LEADERBOARD
  1. Ollama.js · recommended 1×
  2. Ollama · recommended 1×
  3. Llama.cpp · recommended 1×
  4. llama-cpp-js · recommended 1×
  5. MLC LLM · recommended 1×
  • CATEGORY QUERY
    How to run large language models locally in Node.js with structured JSON output?
    you: #4
    AI recommended (in order):
    1. Ollama.js
    2. Ollama
    3. Llama.cpp
    4. node-llama-cpp ← you
    5. llama-cpp-js
    6. MLC LLM
    7. Transformers.js
    8. ONNX Runtime Node.js
    9. LangChain.js
    Show full AI answer
  • CATEGORY QUERY
    Need a JavaScript library for local LLM inference, with GPU support and easy setup.
    you: #5
    AI recommended (in order):
    1. Transformers.js (huggingface/transformers.js)
    2. MLC LLM (mlc-ai/mlc-llm)
    3. llama.cpp (ggerganov/llama.cpp)
    4. llama-cpp-web (with-webgpu/llama-cpp-web)
    5. node-llama-cpp (with-webgpu/node-llama-cpp) ← you
    6. ONNX Runtime Web (microsoft/onnxruntime)
    7. TensorFlow.js (tensorflow/tfjs)
    Show full AI answer

Objective checks

Rule-based audits of metadata signals AI engines weight most.

  • Metadata completeness
    pass

  • README presence
    pass

Self-mention check

Does AI even know your repo exists when asked about it directly?

  • Compared to common alternatives in this category, what is the core differentiator of withcatai/node-llama-cpp?
    pass
    AI did not name withcatai/node-llama-cpp — likely talking about a different project

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

  • If a team adopts withcatai/node-llama-cpp in production, what risks or prerequisites should they evaluate first?
    pass
    AI named withcatai/node-llama-cpp explicitly

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

  • In one sentence, what problem does the repo withcatai/node-llama-cpp solve, and who is the primary audience?
    pass
    AI named withcatai/node-llama-cpp explicitly

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

Embed your GEO score

Drop this badge into the README of withcatai/node-llama-cpp. It auto-updates whenever the report is rescanned and links back to the latest report — easy public proof that you care about AI discoverability.

RepoGEO badge previewLive preview
MARKDOWN (README)
[![RepoGEO](https://repogeo.com/badge/withcatai/node-llama-cpp.svg)](https://repogeo.com/en/r/withcatai/node-llama-cpp)
HTML
<a href="https://repogeo.com/en/r/withcatai/node-llama-cpp"><img src="https://repogeo.com/badge/withcatai/node-llama-cpp.svg" alt="RepoGEO" /></a>
Pro

Subscribe to Pro for deep diagnoses

withcatai/node-llama-cpp — Lite scans stay free; this card itemizes Pro deep limits vs Lite.

  • Deep reports10 / month
  • Brand-free category queries5 vs 2 in Lite
  • Prioritized action items8 vs 3 in Lite