What is ai-companion-runtime CLAUDE.md?

Project-specific instructions for building an AI companion and general assistant system that communicates in real time. The project uses WebSockets, a way for the browser and server to keep an ongoing connection, along with several AI, database, and monitoring tools.

Use it when developing the project’s Next.js web app, Python API, real-time messaging, emotion and risk analysis, memory, model integrations, background jobs, or monitoring.

It gives an agent the project’s architecture, technology choices, file layout, and development rules so its changes fit the existing codebase.

How yf0522/ai-companion-runtime configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to yf0522/ai-companion-runtime. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/yf0522/ai-companion-runtime/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/yf0522/ai-companion-runtime

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/yf0522/ai-companion-runtime/claude-md/github.svg)](https://agentmods.dev/instructions/yf0522/ai-companion-runtime/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/yf0522/ai-companion-runtime/claude-md"><img src="https://agentmods.dev/badge/instructions/yf0522/ai-companion-runtime/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/yf0522/ai-companion-runtime/claude-md"><img src="https://agentmods.dev/badge/instructions/yf0522/ai-companion-runtime/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,897 This file is loaded in full into every session.

When invoked 1,897 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.01897	$0.01897
Opus 5	$0.00949	$0.00949
Sonnet 5	$0.00379	$0.00379
Haiku 4.5	$0.00190	$0.00190

Measured 9d ago against content hash 5fc2145c33ac, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

ai-companion-runtime CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 147 lines

How it starts

The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI Companion Runtime

项目简介

基于 WebSocket 的实时 AI 情绪陪伴 + 通用助手系统。支持情绪识别、风险分级、工具调用、长期记忆、模型热插拔、Agent Harness 编排、全链路 TraceID 观测。

技术栈

层	技术
前端	Next.js 14 + TypeScript + TailwindCSS + Zustand
后端	Python 3.11 + FastAPI + WebSocket
数据库	PostgreSQL 16 + pgvector + Alembic (migration)
缓存	Redis 7
对象存储	MinIO (archive / attachments / traces 三个 bucket)
异步任务	Celery + Redis (broker)
观测	OpenTelemetry + Jaeger, Prometheus + Grafana
模型	Adapter 模式，支持 Qwen / DeepSeek / OpenAI / Gemini / 本地模型
部署	Docker Compose（后续可上 K8s）

项目结构

ai-companion-runtime/
├── apps/
│   ├── web/              # Next.js 前端
│   │   ├── app/          # 页面 (chat / traces / login)
│   │   ├── components/   # React 组件
│   │   ├── stores/       # Zustand 状态管理
│   │   └── lib/          # WebSocket 客户端 / API 客户端
│   └── api/              # FastAPI 后端
│       └── app/
│           ├── config/       # 配置文件 (models.yaml / harness.yaml / personality.yaml / risk_rules.yaml)
│           ├── api/          # HTTP/WS 端点
│           ├── runtime/      # 核心运行时 (gateway / harness / stream)
│           ├── engines/      # 分析引擎 (intent / emotion / risk / memory / personality / reflection)
│           ├── models/       # 模型层 (router / registry / adapters)
│           ├── tools/        # 工具系统 (weather / search / calculator / reminder)
│           ├── observability/ # 追踪与指标 (trace / metrics / logger / cost)
│           ├── workers/      # Celery 异步任务
│           ├── storage/      # MinIO 客户端
│           └── db/           # SQLAlchemy 模型 + Alembic migrations
├── infra/                # Docker Compose + Prometheus + Grafana
├── data/                 # 本地数据目录
└── docs/                 # 设计文档

开发规范

Python 后端

Python 版本: 3.11+
异步: 全链路 async/await，使用 asyncpg + SQLAlchemy 2.0 async
类型标注: 所有函数必须有类型标注，使用 from __future__ import annotations
数据模型: 使用 Pydantic v2 的 BaseModel 定义所有接口数据结构
接口定义: 模块间通过 ABC 或 Protocol 定义接口，不依赖具体实现
配置管理: 运行时配置放 YAML 文件（config/ 目录），密钥放 .env
导入顺序: stdlib → 第三方 → 本项目，各组之间空一行
错误处理: 不静默吞异常；超时用 asyncio.wait_for；降级走 harness fallback 策略
Migration: 使用 Alembic，修改 db/models.py 后运行 alembic revision --autogenerate

Read the full file on GitHub · 147 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

9d ago First seen · 147 lines · 1,897 tokens per session scan A 5fc2145c33ac

Subscribe to this mod's changes

ai-companion-runtime CLAUDE.md is an instructions file published in the GitHub repository yf0522/ai-companion-runtime (43 stars, last pushed 1mo ago), licensed MIT. It adds 1,897 tokens to every session, about $0.0095 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Building agents ai-agent companion-ai eldercare esp32-s3 family-care fraud-detection

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

ai-companion-runtime: Instructions file for Claude Code