lemony-ai/cascadeflow
Cascading runtime for AI agents. Optimize cost, latency, quality, and policy decisions inside the agent loop.
It acts as an in-process agent harness, enabling per-step model decisions, budget gating for tool calls, and runtime actions like `stop` or `switch_model` with sub-5ms overhead. The library intelligently selects optimal models through speculative execution and integrates with popular frameworks like LangChain, CrewAI, OpenAI Agents, and Vercel AI SDK.
294 stars and 221 monthly downloads. Available on PyPI.
Stars
294
Forks
96
Language
Python
License
MIT
Category
Last pushed
Mar 12, 2026
Monthly downloads
221
Commits (30d)
0
Dependencies
3
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/lemony-ai/cascadeflow"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related agents
Pipelex/pipelex
Declarative language for composable Al workflows. Devtool for agents and mere humans.
lobehub/lobehub
The ultimate space for work and life — to find, build, and collaborate with agent teammates that...
strands-agents/sdk-typescript
A model-driven approach to building AI agents in just a few lines of code.
agents-flex/agents-flex
Agents-flex is A Lightweight Java AI Application Development Framework.
JetBrains/koog
Koog is a JVM framework for building predictable, fault-tolerant and enterprise-ready AI agents...