{"repo":"lemony-ai/cascadeflow","free":true,"listed":false,"github":"https://github.com/lemony-ai/cascadeflow","clone":"git clone https://github.com/lemony-ai/cascadeflow.git","description":"Cascading runtime for AI agents. Optimize cost, latency, quality, and policy decisions inside the agent loop.","language":"Python","stars":3999,"topics":["agent","ai","anthropic","api","budgets","claude","cost-optimization","gpt","huggingface","llm"],"license":"MIT","category":"ai-agents","readme_excerpt":"Agent Runtime Intelligence Layer Cost Savings: 69% (MT-Bench), 93% (GSM8K), 52% (MMLU), 80% (TruthfulQA) savings, retaining 96% GPT-5 quality. Python • TypeScript • LangChain • OpenAI Agents • CrewAI • PydanticAI • Google ADK • n8n • Vercel AI • OpenClaw • Hermes Agent • 📖&nbsp;Docs • 💡&nbsp;Examples --- The in-process intelligence layer for AI agents. Optimize cost, latency, quality, budget, compliance, and energy — inside the execution loop, not at the HTTP boundary. cascadeflow works where external proxies can't: per-step model decisions based on agent state, per-tool-call budget gating, runtime stop/continue/escalate actions, and business KPI injection during agent loops. It accumulates insight from every model call, tool result, and quality score — the agent gets smarter the more it runs. Sub-5ms overhead. Works with LangChain, OpenAI Agents SDK, CrewAI, PydanticAI, Google ADK, n8n, Vercel AI SDK, and Hermes Agent. Update ### Hermes Agent delegation cascading CascadeFlow now provides a Hermes Agent integration for per-skill model cascading, task-complexity cascading, topic-aware subagent cascading, observe-mode rollout, and auditable decisions without taking over provider credentials, base URLs, fallback chains, or API modes. --- Why cascadeflow? Proxy vs In-Process Harness Dimension External Proxy cascadeflow Harness --- --- --- Scope HTTP request boundary Inside agent execution loop Dimensions Cost only Cost + quality + latency + budget + compliance + energy Latency ","default_branch":null,"files":null,"tree":[],"storefront":"/r/lemony-ai","claimed":false,"request_supported":{"post":"https://gitbuyer.com/r/lemony-ai/cascadeflow/request-supported","requests":0},"note":"indexed from public GitHub; nothing is for sale on this page. Clone it from GitHub. Paid listings live at /search."}