jevloop
parkavenue9639/jevloop
A Jev-driven general-purpose agent harness for faster, lower-cost execution, with built-in side-by-side experiments against LLM-only agents.
Python
- 星标
- 10
- 派生
- 0
收录依据
将有界工具决策交给 Jev、语言撰写交给 LLM、执行及状态交给确定性代码的独立代理运行时。
parkavenue9639/jevloop
A Jev-driven general-purpose agent harness for faster, lower-cost execution, with built-in side-by-side experiments against LLM-only agents.
将有界工具决策交给 Jev、语言撰写交给 LLM、执行及状态交给确定性代码的独立代理运行时。
Bulk decisions for AI agents. Jev classifies files and logs; your agent reviews exceptions. Reproducible cost and quality benchmarks.
共同主题: ai-agents, llm-evaluation
Sorts customer support tickets automatically and sends the uncertain ones to a person.
共同主题: docker, llm-evaluation
Build and regression-test conversational state machines powered by Jev. Inspect decisions, capture failing conversations as tests, and export runnable TypeScript for your app.
共同主题: ai-agents, llm-evaluation