# a16z-infra/companion-app

AI companions with memory: a lightweight stack to create and host your own AI companions

Repository: https://github.com/a16z-infra/companion-app
Canonical: https://ross.abutalabs.com/products/companion-app
Homepage: https://ai-companion-stack.com/
Language: TypeScript
License: MIT
License Family: permissive
Last push: 2024-04-23T06:48:57+00:00

## Health v2 (maintenance only)
Score: 29/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 83
- inputs: {"age_days": 1168, "days_push": 862, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 5977, forks 949 (observed 2026-08-28T04:09:33.947555+00:00)

## What it is
A tutorial starter stack for building and hosting AI companions with personality, backstory, and conversational memory. It combines Next.js, LangChain.js, a vector database (Pinecone/pgvector), and LLMs from OpenAI or Replicate into a deployable chat application.

## Use cases
- build an ai companion chatbot with memory
- create an ai girlfriend or boyfriend chat app
- learn how to build chatbots with langchain and nextjs
- host a custom ai character with a backstory
- chat with an ai companion via sms
- starter template for llm chatbot apps with vector search

## When to choose
- you want a learning-oriented starter stack showing how companion chatbots are assembled
- you need conversational memory plus vector-based retrieval in one template
- you want to deploy a chatbot quickly to Fly.io with auth and SMS support included

## When to avoid
- you need a production-grade, maintained chatbot platform rather than a tutorial
- you want a framework or library to embed in an existing app instead of a full-stack template
- you require active development and recent updates

## Facets
- artifact type: framework
- maturity: maintenance
- function: chatbot, rag, llm-inference, vector-database, web-framework, agent-framework
- domain: artificial-intelligence, large-language-models, chatbots, web-development, developer-tools
- platform: self-hosted
- tags: ai-companions, starter-template, langchain, nextjs, conversational-memory, tutorial-stack, sms-chat, retrieval-augmented-generation, nodejs, typescript, web-server, docker

## Member repositories
- a16z-infra/companion-app (main) score 29

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:33.947555+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:50:03.022302+00:00, confidence not recorded.
  - readme: https://github.com/a16z-infra/companion-app (fetched 2026-08-28T04:09:33.947555+00:00, sha 77be29c6c8ea)
  - homepage: https://ai-companion-stack.com/ (fetched 2026-08-29T08:46:09.428442+00:00, sha 99735426f018)
- Data as of 2026-08-30T08:39:29.467469+00:00.