Skip to content
panevibe
FeaturesArchitectureDocs
GitHub
Overview
Start hereGetting started
ConceptsTerminal-first architecture
AgentsAgents and modelsBrowser and MCP
OperateSecurity and privacyConfiguration
ProjectContributing
Agent accessllms.txtFull contextMarkdown index

Understand the harness.
Keep the terminal true.

Start with one command, then go as deep as the PTY boundary, browser engine, provider model, and security posture.

Get runningClone, setup, and open your first pane.Read the architectureWhy the PTY is the source of truth.Bring an agentNative CLIs and compatible API providers.

Everything in one index.

01
Getting started

Clone PaneVibe, run one setup command, and open your first real agent CLI in a PTY.

02
Terminal-first architecture

The PTY is the source of truth. Chat is a readable projection with the raw terminal always available.

03
Agents and models

Use native agent CLIs when they exist, or connect any OpenAI-compatible endpoint for direct model access.

04
Browser and MCP

Six built-in MCP servers and two deliberately different browser surfaces ship inside the binary.

05
Security and privacy

Localhost transport, no telemetry, OS-encrypted credentials, and explicit workspace permissions.

06
Configuration

Everything has a working default; environment variables are escape hatches rather than a required setup surface.

07
Contributing

Keep changes inside one concern, preserve the PTY execution model, and run the focused release gates.

Prefer raw context?

Every page has a Markdown twin, with a compact llms.txt map and a single-file full context bundle.

index.mdllms.txtllms-full.txt
PaneVibe

A terminal first IDE for coding agents.

GitHub

Explore

  • Features
  • Architecture
  • Docs

For agents

  • llms.txt
  • Full context
  • AGENTS.md

© 2026 PaneVibe. MIT licensed.