tiny-agent-os 1.2.8

Python agent loop

TinyAgent

A small, modular agent framework for building LLM-powered applications in Python.

Inspired by smolagents and Pi — borrowing the minimal-abstraction philosophy from the former and the conversational agent loop from the latter.

Beta — TinyAgent is usable but not production-ready. APIs may change between minor versions.

Note: The optional tinyagent._alchemy binding now lives in https://github.com/tunahorse/tinyagent-alchemy and is not built from this repo.

Overview

TinyAgent provides a lightweight foundation for creating conversational AI agents with tool use capabilities. It features:

• Streaming-first architecture: All LLM interactions support streaming responses
• Tool execution: Define and execute tools with structured outputs
• Event-driven: Subscribe to agent events for real-time UI updates
• Provider agnostic: Works with any OpenAI-compatible /chat/completions endpoint (OpenRouter, OpenAI, Chutes, local servers)
• Prompt caching: Reduce token costs and latency with Anthropic-style cache breakpoints
• Provider paths: Optional external alchemy binding adapter plus proxy integration
• Type-safe: Full type hints throughout

Quick Start

This example uses the optional tinyagent._alchemy binding via tinyagent.alchemy_provider. Install that binding from the external repo first, or use the proxy path instead.

import asyncio
from tinyagent import Agent, AgentOptions
from tinyagent.alchemy_provider import OpenAICompatModel, stream_alchemy_openai_completions

# Create an agent
agent = Agent(
    AgentOptions(
        stream_fn=stream_alchemy_openai_completions,
        session_id="my-session"
    )
)

# Configure
agent.set_system_prompt("You are a helpful assistant.")
agent.set_model(
    OpenAICompatModel(
        provider="openrouter",
        id="anthropic/claude-3.5-sonnet",
        base_url="https://openrouter.ai/api/v1/chat/completions",
    )
)
# Optional: any OpenAI-compatible /chat/completions endpoint
# agent.set_model(OpenAICompatModel(provider="openai", id="gpt-4o-mini", base_url="https://api.openai.com/v1/chat/completions"))

# Simple prompt
async def main():
    response = await agent.prompt_text("What is the capital of France?")
    print(response)

asyncio.run(main())

Installation

pip install tiny-agent-os

Optional binding:

• Install/build tinyagent._alchemy from https://github.com/tunahorse/tinyagent-alchemy if you want stream_alchemy_openai_completions
• Otherwise, use the proxy path in tinyagent.proxy

Core Concepts

Agent

The Agent class is the main entry point. It manages:

• Conversation state (messages, tools, system prompt)
• Streaming responses
• Tool execution
• Event subscription

Messages

Messages are Pydantic models (use attribute access):

• UserMessage: Input from the user
• AssistantMessage: Response from the LLM
• ToolResultMessage: Result from tool execution

Tools

Tools are functions the LLM can call:

from tinyagent import AgentTool, AgentToolResult, TextContent

async def calculate_sum(tool_call_id: str, args: dict, signal, on_update) -> AgentToolResult:
    result = args["a"] + args["b"]
    return AgentToolResult(
        content=[TextContent(text=str(result))]
    )

tool = AgentTool(
    name="sum",
    description="Add two numbers",
    parameters={
        "type": "object",
        "properties": {
            "a": {"type": "number"},
            "b": {"type": "number"}
        },
        "required": ["a", "b"]
    },
    execute=calculate_sum
)

agent.set_tools([tool])

Events

The agent emits events during execution:

• AgentStartEvent / AgentEndEvent: Agent run lifecycle
• TurnStartEvent / TurnEndEvent: Single turn lifecycle
• MessageStartEvent / MessageUpdateEvent / MessageEndEvent: Message streaming
• ToolExecutionStartEvent / ToolExecutionUpdateEvent / ToolExecutionEndEvent: Tool execution

Subscribe to events:

def on_event(event):
    print(f"Event: {event.type}")

unsubscribe = agent.subscribe(on_event)

Prompt Caching

TinyAgent supports Anthropic-style prompt caching to reduce costs on multi-turn conversations. Enable it when creating the agent:

agent = Agent(
    AgentOptions(
        stream_fn=stream_alchemy_openai_completions,
        session_id="my-session",
        enable_prompt_caching=True,
    )
)

Cache breakpoints are automatically placed on user message content blocks so the prompt prefix stays cached across turns. See Prompt Caching for details.

Optional Binding: tinyagent._alchemy

This repo keeps tinyagent/alchemy_provider.py as a compatibility adapter for the optional external tinyagent._alchemy extension. The binding source, build instructions, and low-level binding API now live in:

• https://github.com/tunahorse/tinyagent-alchemy

The compiled path is still useful when you want OpenAI-compatible streaming without routing through a separate proxy, but it is no longer bundled or built from this repository.

Using via TinyAgent

You don't need to call the Rust binding directly. Use the alchemy_provider module:

from tinyagent import Agent, AgentOptions
from tinyagent.alchemy_provider import OpenAICompatModel, stream_alchemy_openai_completions

agent = Agent(
    AgentOptions(
        stream_fn=stream_alchemy_openai_completions,
        session_id="my-session",
    )
)
agent.set_model(
    OpenAICompatModel(
        provider="openrouter",
        id="anthropic/claude-3.5-sonnet",
        base_url="https://openrouter.ai/api/v1/chat/completions",
    )
)

MiniMax global:

agent.set_model(
    OpenAICompatModel(
        provider="minimax",
        id="MiniMax-M2.5",
        base_url="https://api.minimax.io/v1/chat/completions",
        # api is optional here; inferred as "minimax-completions"
    )
)

MiniMax CN:

agent.set_model(
    OpenAICompatModel(
        provider="minimax-cn",
        id="MiniMax-M2.5",
        base_url="https://api.minimax.chat/v1/chat/completions",
        # api is optional here; inferred as "minimax-completions"
    )
)

Smoke validation after installing the external binding:

• uv run python scripts/smoke_rust_tool_calls_three_providers.py

Limitations

• The optional binding currently dispatches only openai-completions and minimax-completions.
• Image blocks are not yet supported (text and thinking blocks work).
• next_event() is blocking and runs in a thread via asyncio.to_thread -- this adds slight overhead compared to a native async generator, but keeps the GIL released during the native work.

Documentation

• Architecture: System design and component interactions
• API Reference: Detailed module documentation
• Prompt Caching: Cache breakpoints, cost savings, and provider requirements
• OpenAI-Compatible Endpoints: Using OpenAICompatModel.base_url with OpenRouter/OpenAI/Chutes-compatible backends
• Usage Semantics: Canonical usage schema across provider flows
• Harness Rules: ast-grep rules for the live tool-call harness
• Changelog: Release history

Project Structure

tinyagent/
├── agent.py              # Agent class
├── agent_loop.py         # Core agent execution loop
├── agent_tool_execution.py  # Tool execution helpers
├── agent_types.py        # Type definitions
├── caching.py            # Prompt caching utilities
├── alchemy_provider.py   # Adapter for the optional external binding
├── proxy.py              # Proxy server integration
└── proxy_event_handlers.py  # Proxy event parsing