CubePi

CubePi is a Pythonic, async-native agent framework designed for high performance, readability, and production-grade persistence. It provides a leaner alternative to graph-based agent runtimes by modeling agent logic as a linear while loop that developers can easily trace and debug.

pip install cubepi

Then jump to the Quick Start to ship a working tool-using agent in under five minutes.

What you get

• Plain async functions, not graph nodes. The agent loop is a while loop over message turns. You build tools as async def functions; the framework routes calls and executes them in parallel.
• One streaming pattern. Every provider yields StreamEvents through a MessageStream. You iterate it with async for. No callback registries, no separate handler types for text vs. tools.
• Append-only checkpointing. Persistence writes the new messages on each turn, not the full transcript. O(1) DB I/O regardless of conversation length — SQLite for laptops, Postgres for production.
• Native multi-provider. Anthropic and OpenAI ship in the box, through a Provider Protocol. Add a new provider in one class.
• Eight-hook middleware. transform_context, convert_to_llm, transform_system_prompt, before_tool_call, after_tool_call, should_stop_after_turn, after_model_response, on_run_end — each with explicit composition rules. No mystery node ordering.
• MCP loaders. Point at any Model Context Protocol server (HTTP or stdio) and get back a list of AgentTools.
• OpenTelemetry built in. Attach a Tracer and every prompt produces a tree of OTel spans aligned with the GenAI Semantic Conventions — works with Jaeger, Tempo, Honeycomb, Datadog, or any OTLP-compatible backend. No payloads recorded by default; opt in with record_content=True and a redact callback.
• Human-in-the-Loop. Suspend an agent mid-run, route a decision to a human (approve/reject/answer), then resume — with full checkpoint persistence so the agent survives a process restart while waiting.

Where to go next

If you want to…	Start here
Install and run your first agent	Getting Started → Installation
Understand the building blocks	Getting Started → Core Concepts
Wire a real tool-using agent	Guides → Building Your First Agent
Persist a conversation across restarts	Guides → SQLite Checkpointing
Ship traces to Jaeger / Tempo / Honeycomb	Guides → Tracing
Look up a specific symbol	API Reference
See full working examples	Recipes
Port an existing langgraph agent	Migration → From langgraph

Status

You are reading the CubePi 0.8 release docs. This is the latest stable documentation set for installing CubePi and building against the published 0.8 API.

CubePi 0.8 adds conversation forking (Agent.fork() / Agent.fork_once()), run-based checkpointing (schema v3→v4 across all backends), the @tool decorator for ergonomic tool definition, and Agent.prompt() now returns the run_id. For unreleased changes on main, switch to the Next docs from the version picker.

Source, issues, and discussion live on GitHub.