Back to directory

Coze Loop

An open-source edition of a developer platform for the full lifecycle of AI agents, covering prompt development, evaluation and observability.

Coze Loop

Coze Loop is a platform-level solution for developing and operating AI agents, offering lifecycle management from development and debugging through evaluation to monitoring. Its open-source edition shares core technology modules from a commercial version so developers can customize and extend them.

A prompt-development module gives end-to-end support for writing, debugging, optimizing and versioning prompts through a visual Playground that compares output across different LLMs in real time. An evaluation module runs automated multi-dimensional tests of prompt and agent output, such as accuracy, conciseness and compliance, while an observability module records every stage from user input to AI output, including prompt parsing, model invocation and tool execution, and captures intermediate results and exceptions automatically.

It is written in Go and licensed under Apache-2.0.

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.