REPOGEO REPORT · LITE
a16z-infra/companion-app
Default branch main · commit a50c9371 · scanned 6/26/2026, 7:18:07 AM
GitHub: 5,960 stars · 956 forks
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.
3 ready scans. Expand the table below for newest-first rows (10 per page, paginated).
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 a16z-infra/companion-app, 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.
- hightopics#1Add relevant topics to the repository
Why:
COPY-PASTE FIXai-companions, chatbot, llm, tutorial, stack, memory, personalization, replicate, generative-ai
- highreadme#2Reposition the README's main heading to clearly state its purpose
Why:
CURRENT# AI Companion App (based on AI Getting Started template)
COPY-PASTE FIX# AI Companion Tutorial Stack: Build Your Own Personalized AI Chatbots with Memory
- mediumreadme#3Emphasize 'tutorial' and 'starter stack' in the README's introductory paragraph
Why:
CURRENTThis is a tutorial stack to create and host AI companions that you can chat with on a browser or text via SMS. It allows you to determine the personality and backstory of your companion, and uses a vector database with similarity search to retrieve and prompt so the conversations have more depth. It also provides some conversational memory by keeping the conversation in a queue and including it in the prompt.
COPY-PASTE FIXThis project serves as a developer tutorial and starter stack to create and host AI companions that you can chat with on a browser or text via SMS. It allows you to determine the personality and backstory of your companion, and uses a vector database with similarity search to retrieve and prompt so the conversations have more depth. It also provides some conversational memory by keeping the conversation in a queue and including it in the prompt.
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.
- OpenAI API · recommended 1×
- LangChain · recommended 1×
- Google Cloud Dialogflow CX · recommended 1×
- Hugging Face Transformers · recommended 1×
- Rasa · recommended 1×
- CATEGORY QUERYHow can I build a custom AI chatbot with a defined personality and conversational memory?you: not recommendedAI recommended (in order):
- OpenAI API
- LangChain
- Google Cloud Dialogflow CX
- Hugging Face Transformers
- Rasa
AI recommended 5 alternatives but never named a16z-infra/companion-app. This is the gap to close.
Show full AI answer
- CATEGORY QUERYSeeking a lightweight stack to host my own AI companion for personalized interactions.you: not recommendedAI recommended (in order):
- Mycroft AI (MycroftAI/mycroft-core)
- Rhasspy (rhasspy/rhasspy)
- OpenAssistant (LAION-AI/Open-Assistant)
- Home Assistant (home-assistant/core)
- GPT4All (nomic-ai/gpt4all)
- Ollama (ollama/ollama)
AI recommended 6 alternatives but never named a16z-infra/companion-app. This is the gap to close.
Show full AI answer
Objective checks
Rule-based audits of metadata signals AI engines weight most.
- Metadata completenesswarn
Suggestion:
- README presencepass
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 a16z-infra/companion-app?passAI did not name a16z-infra/companion-app — 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 a16z-infra/companion-app in production, what risks or prerequisites should they evaluate first?passAI named a16z-infra/companion-app 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 a16z-infra/companion-app solve, and who is the primary audience?passAI named a16z-infra/companion-app 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 a16z-infra/companion-app. It auto-updates whenever the report is rescanned and links back to the latest report — easy public proof that you care about AI discoverability.
[](https://repogeo.com/en/r/a16z-infra/companion-app)<a href="https://repogeo.com/en/r/a16z-infra/companion-app"><img src="https://repogeo.com/badge/a16z-infra/companion-app.svg" alt="RepoGEO" /></a>Subscribe to Pro for deep diagnoses
a16z-infra/companion-app — 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