peerd
peerd is the first AI agent harness native to the browser, allowing AI agents to drive tabs, run sandboxed compute, and share peer-to-peer with no backend.
peerd
What is peerd?
peerd vs Similar AI Tools
| Pricing Model | Free | Free, Freemium | Free | Free |
| Free Credits | ||||
| Key Features |
|
|
|
|
| Pros |
|
|
|
|
| Cons |
|
|
|
|
| Best For |
|
|
|
|
How to use peerd?
- 1Clone the repository from GitHub.
- 2Load the extension/ folder unpacked in Chrome (or Firefox) with Developer mode enabled.
- 3Click the peerd icon in the toolbar to open the side panel.
- 4On first run, create a local vault unlocked by Touch ID, passkey, or passphrase.
- 5Add your API key(s) for Anthropic, OpenRouter, or Ollama in Settings.
- 6Start chatting – peerd can read and drive open tabs, run commands in a sandboxed VM, build apps, and more.
peerd Key Features
- In-browser AI agent loop with full tool integration
- Sandboxed compute: WebVM (Linux), JS Notebooks, and App tabs
- Peer-to-peer sharing via WebRTC (preview channel)
- BYOK – bring your own API keys (Anthropic, OpenRouter, Ollama)
- No backend, no telemetry, no cloud storage
- Local encrypted vault for keys, chat history, and audit log
- Voice input with local STT (Moonshine)
- Open source under Apache 2.0
peerd Use Cases
- Automating browser tasks and web scraping
- Building and testing code in a sandboxed environment
- Creating and running AI-powered apps
- Collaborating with AI agents over a P2P network
- Privacy-preserving AI agent experimentation
peerd Pricing & Free Credits
peerd currently operates on a Free model.
This tool is completely free to use
peerd Pros & Cons
Pros
- Fully client-side – no backend dependency or data leaks
- Supports multiple model providers (Anthropic, OpenRouter, Ollama)
- Sandboxes code execution (WebVM, Notebook) for safety
- P2P sharing enables decentralized agent collaboration
- Strong security boundaries: vault, egress chokepoint, disposable runner
Cons
- Experimental (0.x) – breaking changes likely
- Requires manual setup and API keys
- Limited to browser environment (Chrome/Firefox)
- CheerpX VM depends on proprietary runtime (licensing restrictions for commercial use)
What is peerd best for?
- Developers exploring AI agents
- Privacy-conscious users wanting local control
- Researchers testing agent workflows in the browser
- Hobbyists building personal AI assistants
peerd FAQ
Top free alternatives to peerd
Multi-agent workflow platform that builds and runs workflows from plain English prompts, integrating 1000+ apps and 50+ AI models.
Automate repetitive browser tasks by recording screen actions or describing with chat, turning them into reusable workflows, smart tables, and custom apps.
SureWire is a specialized QA platform that stress-tests AI agents for safety, reliability, and compliance using purpose-built testing agents.
Browser infrastructure platform for AI agents to run on the internet at speed with cloud browser sessions, agents, and serverless functions.
Manifest converts any URL into a structured JSON map of what AI agents can interact with on a page—buttons, forms, inputs, and required fields.
Agentcard provides agent-friendly card issuing and payment infrastructure for AI agents, enabling 5-minute setup and autonomous purchases.
Manage AI agent teams like human teams with responsibilities, numbers, commitments, and approvals across your business tools.
Oodle AI provides agent observability with fast trace search, S3-based storage, and out-of-the-box insights to detect silent failures in AI agents.
Best alternatives AI Tools to peerd
Multi-agent workflow platform that builds and runs workflows from plain English prompts, integrating 1000+ apps and 50+ AI models.
A collection of deliberately vulnerable MCP servers for training in agentic security, mapped to the OWASP Top 10 for Agentic Applications.
Open-source AI tool for deep infrastructure research, running frontier models across code, cloud, and runtime to deliver verified answers.
Terminal UI to manage AI coding-agent sessions (Claude Code, OpenCode, Codex, Grok Build) in tmux with live status, group tree, and diff review.
Self-hostable sandbox SDK for AI agents that provides isolated environments with key management and egress control on your own hardware.
Open-source desktop app to manage multiple project workspaces simultaneously, keeping terminals and AI coding agents running across projects with instant switching.
A macOS menu-bar app that gives AI agents the ability to draw directly on your screen via MCP.
A desktop app that transforms AI coding agents into a visual Kanban build loop for feature development with human review.