ZhangShenao

Text roleplay with stable personas, memory, and a visible context pipeline.

Local-First · 轻量级 · 功能完备 · 生产可用的通用 Agent 框架

Open sourced predictions, execution logs, trajectories, and results from model inference + evaluation runs on the SWE-bench task.

No project description available.

Open-source, end-to-end platform for evaluating, observing, and improving LLM and AI agent applications. Tracing · Evals · Simulations · Datasets · Gateway · Guardrails. Self-hostable. Apache 2.0.

星夜兼程赶往AGI