Skip to content

CubeLoop — a Pythonic, async-native agent harness core designed for high performance, readability, and production-grade persistence.

3.7 KB
Raw Blame
---
id: intro
title: "CubePi — Pythonic async-native agent framework"
description: "A Pythonic, async-native agent framework. Plain async functions, append-only checkpointing, three dependencies."
slug: /
sidebar_position: 0
---


# 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.

```bash
pip install cubepi
```

Then jump to the [Quick Start](./getting-started/quick-start.md) 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 `StreamEvent`s
  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.
- **Nine-hook middleware.** `transform_context`, `convert_to_llm`,
  `transform_system_prompt`, `resolve_tool_call`, `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](https://modelcontextprotocol.io) server
  (HTTP or stdio) and get back a list of `AgentTool`s.
- **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](./getting-started/installation.md) |
| Understand the building blocks | [Getting Started → Core Concepts](./getting-started/core-concepts.md) |
| Wire a real tool-using agent | [Guides → Building Your First Agent](./guides/agents/first-agent.md) |
| Persist a conversation across restarts | [Guides → SQLite Checkpointing](./guides/checkpointing/sqlite.md) |
| Ship traces to Jaeger / Tempo / Honeycomb | [Guides → Tracing](./guides/tracing/overview.md) |
| Look up a specific symbol | [API Reference](./api/index.mdx) |
| See full working examples | [Recipes](./recipes/weather-agent.md) |
| Port an existing langgraph agent | [Migration → From langgraph](./migration/from-langgraph.md) |

## Status

You are reading the **CubePi 0.13** release docs. This is the latest stable
documentation set for installing CubePi and building against the published
0.13 API.

CubePi 0.13 adds reasoning capability primitives and controls across all
providers, run-scoped compaction with real-token triggering, tool-batch
fault isolation that preserves all checkpoint state, and durable parallel
HITL approval replay.

Source, issues, and discussion live on
[GitHub](https://github.com/cubeplexai/cubepi).