Cayu
Cayu is a Python framework that runs long-running AI agents durably, with restart recovery, approvals and spend caps, for developers building domain-specific agents.
What it is good for
- Keeping a long-running agent alive across restarts and redeploys
- Requiring human approval before an agent takes side effects
- Capping model spend per request and per app
- Running Claude Code or Codex as a step in an app
At a glance
- Who it is for
- Setup
- Requires programming
Level 5 of 5. You need to write code to use it.
- Cost
- Free and open source
- Type
- Framework or SDK
- Tasks
- Works with
- Claude Agent SDK, Codex, OpenAI, Anthropic, PostgreSQL, SQLite
Momentum
- Rank this week
- Not ranked (last #32, week 42, 2026)
- Best rank
- #3 week 41, 2026
- GitHub stars
- 962
GitHub numbers as of Nov 2, 2026. Updated weekly.
Ranking history
Official links
Setup steps are on the official pages. We do not repeat them here, since they change.
Questions
- Is Cayu free?
- Yes. It is free and open source (Apache-2.0 license).
- Do I need to know how to code to use Cayu?
- Yes. You need to write code to use it.
- What does Cayu work with?
- According to its own documentation, it works with Claude Agent SDK, Codex, OpenAI, Anthropic, PostgreSQL, and SQLite.
- What is Cayu good for?
- Keeping a long-running agent alive across restarts and redeploys, requiring human approval before an agent takes side effects, capping model spend per request and per app, and running Claude Code or Codex as a step in an app.
Similar agents
- LangChain
LangChain is a framework that helps developers build AI agents and LLM-powered applications that connect to models and data sources.
- crewAI
CrewAI is a Python framework that lets developers build teams of AI agents that split up and complete multi-step work.
- LangGraph
LangGraph is a framework that helps developers build long-running agents that keep their state and resume after failures.
- Agno
Agno is a framework and service platform that builds, runs, and improves AI agents for developers and teams who need them available as an API or MCP server.
- Conductor
Conductor is a workflow engine that runs multi-step jobs and AI agents reliably, so steps survive crashes and retries, for developers.
- Agent Development Kit (ADK)
Agent Development Kit is a Python code library that helps developers build, test, and deploy AI agents.