pop-framework 1.0.0

Fast, lean AI agents. 5 lines to production.

Fast, lean AI agents. 5 lines to production.

---

Coding agents: See SKILLS.md for the complete API guide — tools, agents, multi-agent patterns, streaming, memory, and all imports in one file.

---

pop is a lightweight Python framework for building AI agents. It supports multiple LLM providers, has 5 core concepts, and gets you from install to a working agent in under 2 minutes.

Why pop?

• 5 lines to a working agent -- define a tool, create an agent, call run.
• 7 LLM providers built-in -- OpenAI, Anthropic, Gemini, DeepSeek, Kimi, MiniMax, GLM. Switch by changing one string.
• ~2,500 lines of code -- read the entire framework in an afternoon.
• 2 runtime dependencies -- httpx and pydantic. Import time under 1ms (lazy imports).
• Zero commercial dependencies -- no forced telemetry, no vendor lock-in.

Install

uv add pop-framework
# or
pip install pop-framework

All 7 providers (OpenAI, Anthropic, Gemini, DeepSeek, Kimi, MiniMax, GLM) are included — no extras needed.

Quick Start

from pop import Agent, tool

@tool
def search(query: str) -> str:
    """Search the web for current information."""
    return web_search(query)  # your implementation

agent = Agent(model="openai:gpt-4o", tools=[search])
result = agent.run("What happened in AI today?")
print(result.output)

That's it. No StateGraph, no RunnableSequence, no ChannelWrite.

Docs

Guide	What it covers
Skills	Complete API guide for building agents
Providers	Switching LLMs, failover, model adapters
Streaming	Real-time events, pattern matching
Workflows	Chain, route, parallel, agent, orchestration
Multi-Agent	Handoff, pipeline, debate, fan_out
Memory	In-memory and markdown-based persistence
Benchmarks	Performance numbers, framework comparison

Benchmarks

Metric	pop	LangChain + LangGraph	Delta
Framework overhead	~0.15ms	~45ms	~300x faster
Import time	~0.17ms	~1,200ms	~7,000x faster
Lines of code (avg task)	~12	~42	71% less
Dependencies	2	20+	90% fewer

Details: docs/benchmarks.md

License

MIT