RRepoGEO

REPOGEO REPORT · LITE

MinishLab/semble

Default branch main · commit 49bd6e21 · scanned 6/8/2026, 3:12:06 PM

GitHub: 4,937 stars · 208 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)

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

AI VISIBILITY SCORE
40 /100
Critical
Category recall
0 / 2
Not recommended in any query
Rule findings
2 pass · 0 warn · 0 fail
Objective metadata checks
AI knows your name
3 / 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 MinishLab/semble, 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
    Reposition the README's opening to explicitly differentiate from generic code search and vector databases

    Why:

    CURRENT
    Semble is a code search library built for agents. It returns the exact code snippets they need instantly, using ~98% fewer tokens than grep+read. Indexing and searching a full codebase end-to-end takes under a second, with ~200x faster indexing and ~10x faster queries than a code-specialized transformer, at 99% of its retrieval quality (see [benchmarks](#benchmarks)). Everything runs on CPU with no API keys, GPU, or external services. Use it as an MCP server, a CLI tool via AGENTS.md, or a dedicated sub-agent, and any coding agent (Claude Code, Cursor, Codex, OpenCode, etc.) gets instant access to any repo.
    COPY-PASTE FIX
    Semble is a code search library built for AI agents. Unlike generic code search tools (e.g., `grep`, `ripgrep`) or general-purpose vector databases (e.g., Faiss, Weaviate), it returns the exact code snippets they need instantly, using ~98% fewer tokens than `grep`+read. Indexing and searching a full codebase end-to-end takes under a second, with ~200x faster indexing and ~10x faster queries than a code-specialized transformer, at 99% of its retrieval quality (see [benchmarks](#benchmarks)). Everything runs on CPU with no API keys, GPU, or external services. Use it as an MCP server, a CLI tool via AGENTS.md, or a dedicated sub-agent, and any coding agent (Claude Code, Cursor, Codex, OpenCode, etc.) gets instant access to any repo.
  • mediumabout#2
    Refine the 'about' description to emphasize agent-specific, token-efficient, local code search

    Why:

    CURRENT
    Fast and Accurate Code Search for Agents. Uses ~98% fewer tokens than grep+read
    COPY-PASTE FIX
    Fast, accurate, and token-efficient code search for AI agents. Runs locally, providing instant, relevant code snippets without external APIs or GPUs.
  • mediumreadme#3
    Add a dedicated 'Comparison' section to the README

    Why:

    COPY-PASTE FIX
    ## Comparison

Semble is purpose-built for AI agents, offering a distinct advantage over both general-purpose code search tools and vector databases. Unlike tools such as `grep` or `ripgrep`, Semble returns precise, context-aware code snippets, drastically reducing token usage for agents. Compared to vector databases like Faiss or Weaviate, Semble operates entirely locally, requiring no external services, GPUs, or API keys, and is optimized for instant, relevant code retrieval within an agent's workflow.

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
0 / 2
0% of queries surface MinishLab/semble
Avg rank
—
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
facebookresearch/faiss
Recommended in 1 of 2 queries
COMPETITOR LEADERBOARD
  1. facebookresearch/faiss · recommended 1×
  2. weaviate/weaviate · recommended 1×
  3. Pinecone · recommended 1×
  4. elastic/elasticsearch · recommended 1×
  5. chromadb/chroma · recommended 1×
  • CATEGORY QUERY
    How to enable efficient and token-saving code search for my AI coding assistant?
    you: not recommended
    AI recommended (in order):
    1. Faiss (facebookresearch/faiss)
    2. Weaviate (weaviate/weaviate)
    3. Pinecone
    4. Elasticsearch (elastic/elasticsearch)
    5. Chroma (chromadb/chroma)

    AI recommended 5 alternatives but never named MinishLab/semble. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    What are fast, local code search solutions for integrating with an autonomous agent?
    you: not recommended
    AI recommended (in order):
    1. ripgrep
    2. The Silver Searcher
    3. GNU grep
    4. ack
    5. VS Code
    6. ctags

    AI recommended 6 alternatives but never named MinishLab/semble. This is the gap to close.

    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 MinishLab/semble?
    pass
    AI named MinishLab/semble explicitly

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

  • If a team adopts MinishLab/semble in production, what risks or prerequisites should they evaluate first?
    pass
    AI named MinishLab/semble 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 MinishLab/semble solve, and who is the primary audience?
    pass
    AI named MinishLab/semble 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 MinishLab/semble. 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/MinishLab/semble.svg)](https://repogeo.com/en/r/MinishLab/semble)
HTML
<a href="https://repogeo.com/en/r/MinishLab/semble"><img src="https://repogeo.com/badge/MinishLab/semble.svg" alt="RepoGEO" /></a>
Pro

Subscribe to Pro for deep diagnoses

MinishLab/semble — 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