RRepoGEO

REPOGEO REPORT · LITE

TsinghuaC3I/MARTI

Default branch main · commit a2fe2c7b · scanned 6/2/2026, 5:02:58 AM

GitHub: 517 stars · 49 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 TsinghuaC3I/MARTI, 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's core value proposition

    Why:

    CURRENT
    > **MARTI** is an open-source framework for training LLM-based Multi-Agent Systems (MAS) with Reinforcement Learning (RL).
    COPY-PASTE FIX
    Replace the first sentence of the README's introductory paragraph with: 'MARTI is the leading open-source framework for **LLM-based Multi-Agent Reinforced Training and Inference**, specifically designed to enhance reasoning capabilities for complex tasks like code generation using tree search-augmented RL.'
  • mediumhomepage#2
    Add homepage URL to About section

    Why:

    COPY-PASTE FIX
    Add the official project website or documentation URL to the repository's 'About' section (homepage field).
  • mediumreadme#3
    Add explicit 'Key Features' section to README

    Why:

    COPY-PASTE FIX
    Add a dedicated 'Key Features' or 'What MARTI Solves' section to the README, using bullet points to highlight:
*   Training LLM-based Multi-Agent Systems with Reinforcement Learning.
*   Enhancing reasoning for complex tasks like code generation via tree search-augmented RL.
*   Supporting ultra-long sequences (up to 32K tokens) and heterogeneous multi-agent training.

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 TsinghuaC3I/MARTI
Avg rank
—
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
LangChain
Recommended in 2 of 2 queries
COMPETITOR LEADERBOARD
  1. LangChain · recommended 2×
  2. ray-project/ray · recommended 1×
  3. Farama-Foundation/PettingZoo · recommended 1×
  4. DLR-RM/stable-baselines3 · recommended 1×
  5. Farama-Foundation/Gymnasium · recommended 1×
  • CATEGORY QUERY
    What frameworks exist for training multi-agent LLM systems using reinforcement learning?
    you: not recommended
    AI recommended (in order):
    1. RLlib (ray-project/ray)
    2. PettingZoo (Farama-Foundation/PettingZoo)
    3. Stable Baselines3 (DLR-RM/stable-baselines3)
    4. Farama Gymnasium (Farama-Foundation/Gymnasium)
    5. Acme (deepmind/acme)
    6. TorchRL (pytorch/rl)

    AI recommended 6 alternatives but never named TsinghuaC3I/MARTI. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    How can I enhance LLM agent reasoning for complex tasks like code generation using tree search?
    you: not recommended
    AI recommended (in order):
    1. AlphaCode
    2. Guidance
    3. LangChain
    4. Tree-of-Thoughts
    5. Graph-of-Thoughts
    6. OpenAI API
    7. LangChain
    8. DreamCoder
    9. DeepProbLog
    10. AlphaFold

    AI recommended 10 alternatives but never named TsinghuaC3I/MARTI. 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 TsinghuaC3I/MARTI?
    pass
    AI named TsinghuaC3I/MARTI explicitly

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

  • If a team adopts TsinghuaC3I/MARTI in production, what risks or prerequisites should they evaluate first?
    pass
    AI named TsinghuaC3I/MARTI 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 TsinghuaC3I/MARTI solve, and who is the primary audience?
    pass
    AI named TsinghuaC3I/MARTI 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 TsinghuaC3I/MARTI. 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/TsinghuaC3I/MARTI.svg)](https://repogeo.com/en/r/TsinghuaC3I/MARTI)
HTML
<a href="https://repogeo.com/en/r/TsinghuaC3I/MARTI"><img src="https://repogeo.com/badge/TsinghuaC3I/MARTI.svg" alt="RepoGEO" /></a>
Pro

Subscribe to Pro for deep diagnoses

TsinghuaC3I/MARTI — 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