RRepoGEO

REPOGEO REPORT · LITE

pguso/agents-from-scratch

Default branch main · commit 6edce9dd · scanned 6/14/2026, 11:47:51 AM

GitHub: 828 stars · 211 forks

AI VISIBILITY SCORE
35 /100
Critical
Category recall
0 / 2
Not recommended in any query
Rule findings
1 pass · 1 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 pguso/agents-from-scratch, 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 README opening to emphasize educational, agent-building focus

    Why:

    CURRENT
    # AI Agents from Scratch
    
    A gentle, local-first introduction to AI agents.
    COPY-PASTE FIX
    # AI Agents from Scratch: A Local-First Educational Guide
    
    This repository is a comprehensive, local-first educational guide for building AI agents from first principles using a local LLM. Learn agent architecture step-by-step with no frameworks, no cloud APIs, and no hidden reasoning.
  • mediumhomepage#2
    Add a homepage URL to the repository metadata

    Why:

    COPY-PASTE FIX
    https://github.com/pguso/agents-from-scratch
  • lowreadme#3
    Remove incorrect placeholder links in 'Related Projects'

    Why:

    CURRENT
    ## Related Projects
    
    ### AI Product from Scratch
    
    [](https://www.typescriptlang.org/)
    [](https://reactjs.org/)
    [](https://nodejs.org/)
    
    Learn AI product development fundamentals with local LLMs. Covers prompt engineering, structured output, multi-step reasoning, API design, and frontend integration through 10 comprehensive lessons with visual diagrams.
    
    ### AI Agents from Scratch in JavaScript
    COPY-PASTE FIX
    ## Related Projects
    
    ### AI Product from Scratch
    [Add actual link to AI Product from Scratch repo/page here]
    
    Learn AI product development fundamentals with local LLMs. Covers prompt engineering, structured output, multi-step reasoning, API design, and frontend integration through 10 comprehensive lessons with visual diagrams.
    
    ### AI Agents from Scratch in JavaScript
    [Add actual link to AI Agents from Scratch in JavaScript repo/page here]

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 pguso/agents-from-scratch
Avg rank
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
ollama/ollama
Recommended in 2 of 2 queries
COMPETITOR LEADERBOARD
  1. ollama/ollama · recommended 2×
  2. LM Studio · recommended 1×
  3. abetlen/llama-cpp-python · recommended 1×
  4. Python · recommended 1×
  5. psf/requests · recommended 1×
  • CATEGORY QUERY
    How can I implement AI agents from scratch using a local LLM, avoiding frameworks?
    you: not recommended
    AI recommended (in order):
    1. Ollama (ollama/ollama)
    2. LM Studio
    3. llama-cpp-python (abetlen/llama-cpp-python)
    4. Python
    5. requests (psf/requests)
    6. json
    7. re
    8. sqlite3
    9. chroma (chroma-core/chroma)
    10. subprocess
    11. BeautifulSoup4 (crummy/BeautifulSoup4)
    12. pandas (pandas-dev/pandas)

    AI recommended 12 alternatives but never named pguso/agents-from-scratch. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    Seeking educational resources to understand AI agent architecture using only local language models.
    you: not recommended
    AI recommended (in order):
    1. LlamaIndex (run-llama/llama_index)
    2. LangChain (langchain-ai/langchain)
    3. Hugging Face Transformers Library (huggingface/transformers)
    4. ollama (ollama/ollama)
    5. llama.cpp (ggerganov/llama.cpp)
    6. vLLM (vllm-project/vllm)
    7. DeepLearning.AI
    8. Coursera
    9. fast.ai

    AI recommended 9 alternatives but never named pguso/agents-from-scratch. This is the gap to close.

    Show full AI answer

Objective checks

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

  • Metadata completeness
    warn

    Suggestion:

  • 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 pguso/agents-from-scratch?
    pass
    AI named pguso/agents-from-scratch explicitly

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

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

Subscribe to Pro for deep diagnoses

pguso/agents-from-scratch — 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