Back to directory

ZipAgent

A lightweight Python framework for building an AI agent in a few lines of code, with a tool decorator, streaming output, context management and native Model Context Protocol integration.

ZipAgent

ZipAgent is a Python framework for building AI agents with a small, simple API. Its core agent engine, tool system and conversation management are implemented in about 700 lines of code.

A function decorated as a tool becomes callable by the agent, and an Agent is created with a name, instructions and a list of tools, then run through a Runner. Streaming responses expose events for answer text and tool calls as they happen, and a Context object tracks multi-turn conversation history and token usage across a session. ZipAgent also integrates natively with the Model Context Protocol to reach external tools, supports custom model configuration such as pointing at any OpenAI-compatible endpoint, and raises typed errors for cases such as tool execution failures and reaching a maximum number of turns.

It installs from PyPI and is covered by more than 120 test cases.

More in Agent frameworks

See all 902
  • Recurse

    recurse.run

    A serverless harness that lets a coding agent design, test, and deploy its own specialist sub-agents as tools, MCP servers, or bots, defined by a schema-validated manifest.

  • ProofForge

    shulgin.is-a.dev

    An AI-agent pipeline that decomposes a mathematics problem, proves each piece, and formalizes the result in Lean 4 and Mathlib until the Lean kernel accepts it, with six of its proofs already merged into Google DeepMind's formal-conjectures repository.

  • local-coder

    github.com

    Builds a local coding-agent team on top of Ollama and OpenCode by detecting the machine's hardware, recommending models for seven specialist roles, and testing whether each assigned model can actually use tools, edit a repository and pass verification.