惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

Jina AI
Jina AI
云风的 BLOG
云风的 BLOG
人人都是产品经理
人人都是产品经理
T
The Blog of Author Tim Ferriss
阮一峰的网络日志
阮一峰的网络日志
罗磊的独立博客
J
Java Code Geeks
博客园 - 聂微东
B
Blog
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
WordPress大学
WordPress大学
腾讯CDC
L
LangChain Blog
Apple Machine Learning Research
Apple Machine Learning Research
Microsoft Azure Blog
Microsoft Azure Blog
D
DataBreaches.Net
The GitHub Blog
The GitHub Blog
美团技术团队
博客园 - Franky
Google DeepMind News
Google DeepMind News
V
V2EX
让小产品的独立变现更简单 - ezindie.com
让小产品的独立变现更简单 - ezindie.com
月光博客
月光博客
The Cloudflare Blog

Hacker News: Show HN

PurrrrrFocus: Pomodoro Timer App - App Store Workflow Engine — Multi-Step Orchestration for Bun RapidPhoto: Pro Photo Editor App - App Store GitHub - DheerG/swarms: Achieve extraordinary results with claude code across a variety of tasks SPICE simulation → oscilloscope → verification with Claude Code — Lucas Gerads Show HN: VCoding – A 5 MB native Windows IDE with no dynamic dependencies Show HN: LLMs don't hallucinate because they're bad at math, it's the format GitHub - Agent-FM/agentfm-core: AgentFM is a peer-to-peer network that turns everyday computers into a decentralized AI supercomputer. AgentFM lets you run massive AI workloads directly across a global mesh of idle CPUs and GPUs. Show HN: Tracking Top US Science Olympiad Alumni over Last 25 Years GitHub - Potarix/agent-hub: One place to talk to all your agents Show HN: Runtime security for AI agents(injection,tool abuse, data exfiltration) GitHub - dubeyKartikay/lazyspotify: Terminal Spotify client for macOS and Linux GitHub - the-banana-tool/king-louie: Easy to use GUI Personal AI Assistant. Win/Linux/Mac. Show HN I made my vacation rental bookable by AI agents–no Airbnb, 0% commission GitHub - basteez/jsf-autoreload: maven plugin to enable hot reload on jsf projects uvm32/hosts/host-gdbstub at main · ringtailsoftware/uvm32 GitHub - labsai/EDDI: Config-driven engine that turns JSON into production-grade AI agents. Multi-agent orchestration, 12+ LLM providers, MCP/A2A protocols, RAG, persistent memory, and enterprise compliance (EU AI Act, GDPR, HIPAA). Built on Quarkus. GitHub - glitchnsec/fortyone-oss: AI Executive Assistant Platform Quickstart | Alien GitHub - muxshed/shed: One stream in, or many. Every destination, simultaneously. No cloud middleman, no per-channel fees, no limits. GitHub - ocrbase-hq/ocrbase: 📄 PDF/IMG ->.MD/JSON Document OCR API for PaddleOCR and GLMOCR. Self-hostable. GitHub - impactjo/home-memory: MCP server that lets your AI assistant remember everything about your home. GitHub - Sets88/dbcls: DbCls is a powerful terminal database client that supports various databases GitHub - neptun2000/heor-agent-mcp GitHub - SeanFDZ/macmind: Single-layer transformer in HyperTalk for the classic Macintosh RollQuation: Math Puzzles - Apps on Google Play GitHub - dropbox/witchcraft Show HN: Agent-cache – Multi-tier LLM/tool/session caching for Valkey and Redis GitHub - opentalon/opentalon: OpenTalon is an open-source platform built from the ground up in Go as a robust alternative to OpenClaw LinkedIn™ 职位抓取工具 - Chrome 应用商店
GitHub - multiplayer-app/multiplayer: The open-source deb...
argoeris · 2026-06-18 · via Hacker News: Show HN

Multiplayer

License Visit Multiplayer

Follow on X Follow on LinkedIn Follow on Bluesky

The open-source debugging agent for developers. We connect your favorite coding agent to prod to fix application bugs automatically. Run us locally and eliminate PR slop.

Website · Docs · CLI

Multiplayer CLI agent preview

What is Multiplayer?

The Multiplayer debugging agent connects your favorite coding agent directly to production to fix application bugs automatically.

Multiplayer runs securely and locally alongside tools like Claude Code (GA), Codex (private beta), and Copilot (private beta). Only when it detects an error or exception anywhere in your stack it sends runtime session data to your coding agent, managing the whole process from bug identified to bug fixed: data gathering, intelligent triage and issue deduplication, coding agent prompting, PR creation and user notification.

The session data fed to the coding agents is full-stack, auto-correlated, and unsampled. It also includes data observability tools miss such as request/response content and headers from all components in your system.

This repository contains the self-hostable agent: the web app, backend services, data pipelines, storage integrations, and shared libraries that power Multiplayer.

Highlights

  • Plug and play with your own agent: we run locally right next to your favorite coding agent so you can fix application bugs in production.
  • Better data for coding agents and humans: APMs heavily sample and miss critical content. We capture and correlate deep, unsampled data across your entire system (frontend to backend), giving your agent the complete runtime picture.
  • Intelligent issue triage and deduplication: we filter for high-priority bugs and group identical errors locally. You get one high-quality, merge-ready fix for critical issues, instead of an avalanche of duplicate PRs for the same bug.
  • Multiplayer CLI: Use the terminal UI to work through sessions, inspect context, ask an agent to debug, and turn fixes into branches or pull requests.
  • Open SDK ecosystem: Capture sessions from JavaScript, React Native, Go, .NET, Python, Ruby, and Java applications.
  • Self-hostable stack: Run the platform locally with Docker Compose, PM2, Turborepo, MongoDB, RabbitMQ, Redis, Kafka, ClickHouse, MinIO, OpenSearch, and OpenTelemetry.

Multiplayer CLI

The Multiplayer CLI brings the debugging workflow into the terminal. It is designed for agent-assisted investigation: connect a session, inspect the collected evidence, reason over code and runtime context, and produce a concrete fix.

Multiplayer debugging agent demo

Use the CLI when you want to:

  • hand an AI agent the exact session and code context for a bug;
  • investigate issues without switching between the dashboard, terminal, and browser tools;
  • create a branch or pull request from the debugging flow;
  • keep the full debugging trace attached to the fix.

See the multiplayer-cli repository for installation and usage instructions.

Multiplayer web dashboard

The Multiplayer web dashboard gives teams a shared debugging workspace for debugging sessions. Engineers can review the conversation between the Multiplayer debugging agent and their coding agent and dive into the specific session data (full-stack session recordings) and how the issues were identified and grouped (issues).

Multiplayer session dashboard

Use the web dashboard when you want to:

  • review the debugging sessions across all Multiplayer debugging agents in your team;
  • resume or edit a debugging session to update a bug fix and generate a new PR;
  • review the issues identified in your platform;
  • review the data gathered per bug identified and replay the user journey, inspect events and requests;
  • annotate session recordings and keep notes tied to the exact runtime evidence that produced the issue.

What's in this repo?

  • clients/multiplayer-web-app - the Multiplayer web application.
  • services/* - backend services for API, auth, git integrations, collaboration, notifications, assets, versioning, and radar/debugging workflows.
  • libs/* - shared platform libraries for auth, models, storage, messaging, telemetry, logging, MCP, and service utilities.
  • scripts/* - local development, infrastructure, migrations, seed data, and PM2 orchestration.
  • docs/img/* - README and product preview assets.

Requirements

For Docker Compose deployment (recommended): only Docker and Docker Compose are required.

For local development with PM2: Node.js, pnpm, PM2, and bunyan are also required.

Running with Docker Compose (Recommended)

docker/docker-compose.prod.yml starts the full platform using prebuilt images from Docker Hub — all infrastructure (MongoDB, RabbitMQ, Redis, Kafka, ClickHouse, MinIO, OpenSearch, OpenTelemetry collector) plus all application services (API, auth, radar, git, collaboration, assets, notifications, version, nginx).

1. Configure environment

Copy the example env file into the docker/ directory, where the compose file expects it:

cp .env.example docker/.env

Edit docker/.env and fill in any required credentials. Email integrations can be left blank unless you need them.

2. Start the platform

docker compose -f docker/docker-compose.prod.yml up -d

All services use health checks and will come up in dependency order.

Stopping

# Stop containers
docker compose -f docker/docker-compose.prod.yml down

Local Development

1. Install dependencies

2. Configure environment

Review .env before starting the platform. Most local defaults are defined in pm2.config.yml; external provider credentials such as email providers are only needed when testing those integrations.

3. Start infrastructure

Start just the infrastructure dependencies with the dev compose file:

docker compose -f docker/docker-compose.dev.yml up -d

4. Start the platform

This starts Docker Compose, builds the platform libraries and services, runs migrations, seeds required roles, and launches the web app and backend services with PM2.

Open http://localhost when startup completes.

PM2 commands

  • pm2 stop all - stop all services.
  • pm2 restart {{SERVICE_NAME}} - restart one service, for example pm2 restart auth.
  • pm2 restart all - restart all services.
  • pm2 delete all - remove all services from PM2.
  • pm2 logs {{SERVICE_NAME}} - view logs for one service.
  • pm2 logs {{SERVICE_NAME}} --raw | bunyan - view formatted logs for one service.

Useful Commands

pnpm build
pnpm lint
pnpm stop:pm2
pnpm migrate:up
pnpm migrate:down
pnpm seed-roles

Related Projects

Documentation

Start with the Multiplayer docs for product concepts, SDK setup, and hosted-platform usage. Service-specific setup notes live in the README files under services/* and library-specific notes live under libs/*.

Contributing

Please read CONTRIBUTING.md for the branching strategy and commit conventions.

License

Multiplayer Platform is released under the MIT License.