xianyu-sheng/Xenon

开源终端 AI 编程 Agent:以在线 Evidence Runtime 验证链(LLM 输出是 Claim、工具结果才是 Evidence)为核心。SWE-bench_Lite 官方评测 40.0% 实例级通过率(同模型 A/B +6.7pp,可复现报告)。7 种推理范式、MCP 工具、落盘补救与验证闭环。Python。

54
Stars
1
Forks
32.2
Radar Score
Stable
Momentum

Scoring Breakdown

Impact14.4
Velocity37.7
Health53.0

Growth Metrics

7-Day Stars
+0
30-Day Stars
+0
Acceleration
x
Language
Python

Why it ranks

Steady growth — consistently collecting stars and contributors.

MCPTop 77% globally
View on GitHub