Model switching extension for pi coding agent
Intelligent model recommendation and switching for Pi coding agent
View docs [here](https://radix-ui.com/primitives/docs/components/switch).
General-purpose agent with transport abstraction, state management, and attachment support
Pi extension. A structured questionnaire the model can put to you when it would otherwise guess, with typed options instead of free-form replies.
Pi extension. The /btw slash command, for putting a one-off side question to the same primary model without polluting the main conversation.
Coding agent CLI with read, bash, edit, write tools and session management
Pi extension for llama.cpp integration. Supports both router and single modes.
Prompt template model selector extension for pi coding agent
A collection of pi extensions for context management, workflow audits, review-comment triage, notifications, brrr push alerts, safety guards, GitHub research, repo-local knowledge, todos, tool rendering, and model/provider helpers.
Use Pi providers in Codex Desktop with seamless history switching, image input, and a local OpenAI-compatible proxy.
Pi extension. A todo list for the model, rendered as a live overlay that survives /reload and conversation compaction.
π.
The complete Alibaba provider for pi — Plan subscription + Cloud pay-per-token, International + China endpoints, Anthropic + OpenAI shapes, native thinking levels. Qwen 3.6 Max, Qwen 3.6 Plus, DeepSeek V4 Pro, Kimi K2.6, GLM-5, MiniMax M2.5.
AI model providers for Pi with free model filtering and dynamic model fetching
Coding agent CLI with read, bash, edit, write tools and session management
Pi extension for delegating tasks to subagents with chains, parallel execution, and TUI clarification
Codebase CLI — a TypeScript coding agent on the pi-mono runtime. OAuth-aware, any LLM provider, single install.
pi provider extension backed by @cursor/sdk local agents
switch ui component for react
Codex-oriented tool and prompt adapter for pi coding agent
A pi extension for parallel side conversations with /btw
Pi footer/statusline showing active model, thinking level, context pressure, live progress updates, and extension statuses.
Harness-backed AI testing on top of Vitest.