Loop your agents like a dandy little b*tch
Single-file Python CLI that names and backgrounds loops so you can stop writing while-true.
The tool-calling loop for LLM agents; iterator-first, protocol-hooked, one dependency.
Iterator-first design beats black-box frameworks like LangChain for debugging.
Python developers building custom LLM agents
LangChain · LlamaIndex · Haystack
Single-file Python CLI that names and backgrounds loops so you can stop writing while-true.
One decorator caps agent costs, detects loops, logs telemetry—real guardrails for runaway LLMs.
Runs agent loop in browser instead of server—questions the default orchestration assumption.
Eighteen-step tutorial refactoring a chat script into event-driven multi-agent architecture.
Builds a real agent loop with MCP support from scratch, skipping all frameworks.
It makes a smart, practical bet: let existing Python functions become agent-ready tools by turning type hints into structured tool schemas with validation and HTTP endpoints, so you don't rewrite logic to expose it to agents. The included PolyClaw agent and discovery/orchestration features sound useful for multi-service workflows, but the space is crowded (LangChain/AutoGPT/etc.), so what matters next is demos showing robust orchestration, failure handling, and provider integrations.