







Pi coding agent extension that allows Pi to autonomously control interactive CLIs in an observable overlay. Full PTY emulation, no tmux, token efficient. User can take over anytime.

I Hated Every Coding Agent, So I Built My Own — Mario Zechner (Pi)
can1357/oh-my-pi
⌥ AI Coding agent for the terminal — hash-anchored edits, optimized tool harness, LSP, Python, browser, subagents, and more
nicobailon/pi-model-switch
Pi coding agent extension that gives the agent the ability to switch models on its own
Building pi in a World of Slop — Mario Zechner
Pi: The Minimal Agent Within OpenClaw
A gentle introduction to the Pi coding agent and why I think it’s a glimpse into the future of software.

Rapidly building interactive CLIs in Go with Bubbletea - Inngest Blog
Our product is just different enough to make our CLI require really good interactivity. We bundle an interactive event browser in our CLI. Here's how it's built.

Cline - AI Coding, Open Source and Uncompromised
Open-source AI coding agent with Plan/Act modes, MCP integration, and terminal-first workflows. Trusted by 5M+ developers worldwide.

Supported agents – Every coding agent Paseo runs
Run Claude Code, Codex, Copilot, OpenCode, Cursor CLI, Gemini CLI, and dozens more coding agents from your phone. Self-hosted, your code stays on your machine.

Terminal Apps need a DOM | C1
agent-tui runs terminal programs on a PTY and exposes the rendered screen as text or an outline with stable refs. Agents can drive live TUIs, including other AI agents, by snapshotting, pressing keys, and waiting for screen state.

Working with canvas extensions in the GitHub Copilot app - GitHub Docs
Use canvases in the GitHub Copilot app to build shared, agent-driven artifacts and interfaces for human-agent collaboration.

Prompt Caching In Agents | EARENDIL
How prompt caching shapes the cost, latency, tools, and architecture of coding agents, and what Pi does to keep cache behavior visible.

New capabilities for building agents on the Anthropic API | Claude
Claude now offers code execution, MCP server connections, file storage, and extended prompt caching through the API—giving developers powerful tools to build agents that analyze data, connect to external systems, and maintain context for longer periods of time.

perplexityai/SPACE
Sandboxed Platform for Agentic Code Execution: pluggable-runtime sandboxes for running agent and user code in isolation.
perplexityai/SPACE
Sandboxed Platform for Agentic Code Execution: pluggable-runtime sandboxes for running agent and user code in isolation.