RRepoGEO

REPOGEO REPORT · LITE

semanser/codel

Default branch main · commit fe1e846c · scanned 6/19/2026, 10:41:51 PM

GitHub: 2,453 stars · 202 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
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 semanser/codel, 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 core identity statement as a prominent H1

    Why:

    CURRENT
    <div align="center">Fully autonomous AI Agent that can perform complicated tasks and projects using terminal, browser, and editor.</div>
    COPY-PASTE FIX
    # Codel: Fully Autonomous AI Agent
    Codel is a self-hosted AI agent designed to autonomously perform complex software development tasks and projects by interacting with the terminal, browser, and editor.
  • mediumcomparison#2
    Add a 'Comparison' section to the README

    Why:

    COPY-PASTE FIX
    # Comparison
    Codel is a self-hosted, fully autonomous AI agent, distinct from: 
    - **Code Editors/IDEs (e.g., Cursor, VS Code):** Codel is not an editor; it's an agent that *uses* an editor, terminal, and browser to complete tasks autonomously.
    - **LLM APIs (e.g., OpenAI API, GPT-4):** Codel is an application built *on top of* LLMs, providing a complete, sandboxed environment for task execution, not just an API endpoint.
    - **Other AI Agents (e.g., OpenDevin, AutoGPT):** Codel focuses on secure, sandboxed execution with automatic Docker image picking and a modern UI for self-hosted complex development tasks.
  • lowtopics#3
    Add more specific topics to reinforce 'self-hosted' and 'development agent'

    Why:

    CURRENT
    agent, ai, autonomous-agents, bot, devin, llama2, llms, ollama, openai
    COPY-PASTE FIX
    agent, ai, autonomous-agents, bot, devin, llama2, llms, ollama, openai, self-hosted, development-agent, dev-tools

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 semanser/codel
Avg rank
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
GitHub Copilot
Recommended in 1 of 2 queries
COMPETITOR LEADERBOARD
  1. GitHub Copilot · recommended 1×
  2. GitHub Copilot X · recommended 1×
  3. Cursor · recommended 1×
  4. OpenAI API · recommended 1×
  5. GPT-4 · recommended 1×
  • CATEGORY QUERY
    How can I automate complex software development tasks using an AI agent?
    you: not recommended
    AI recommended (in order):
    1. GitHub Copilot
    2. GitHub Copilot X
    3. Cursor
    4. OpenAI API
    5. GPT-4
    6. GPT-3.5 Turbo
    7. Anthropic Claude
    8. LangChain
    9. LlamaIndex
    10. Smol-developer
    11. Auto-GPT
    12. CodiumAI

    AI recommended 12 alternatives but never named semanser/codel. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    Looking for a self-hosted AI agent that interacts with terminal, browser, and editor.
    you: not recommended
    AI recommended (in order):
    1. OpenDevin
    2. GPT-Engineer
    3. Smol-Developer
    4. AutoGPT
    5. AgentGPT
    6. SuperAGI
    7. LangChain Agents

    AI recommended 7 alternatives but never named semanser/codel. 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 semanser/codel?
    pass
    AI named semanser/codel explicitly

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

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

Subscribe to Pro for deep diagnoses

semanser/codel — 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