neuron-explorer
Steering-first neuron explorer for Qwen3.5-4B: push every MLP neuron, keep every rollout, browse the results
翻译准备中
开源 AI 代理监控平台。全面可观测生产中的故障。发现根本问题,出现异常时收到警报,并验证修复是否生效。
AI 翻译
Open-source AI agent monitoring platform. Full observability into what's failing in production. Discover underlying issues, get alerts when something breaks and verify your fix worked.
开发工具TypeScript · PythonGitHub @latitude-dev在线运营者未确认
试用过了吗? 点一下就好,无需登录。
开源 AI 代理可观测性。找出代理出错的位置,调度您的编码代理进行修复,并使用真实追踪验证修复。
AI 翻译
Open-source observability for AI agents. Find where your agents fail, dispatch your coding agent to fix it, and verify the fix against real traces.
取自仓库 README
正在加载完整 README。 以下为已保存的摘录。
Agents that fix themselves, at scale.
Latitude finds where your agent fails and gets it fixed.
• Observe: one line of telemetry captures every trace: multi-turn sessions, tool calls, and full execution paths. (traces, sessions, tool-call observability, OpenTelemetry ingest)
• Understand: failing traces are auto-grouped into tracked signals with status, size, and trend, so you see what's breaking and how often. (signals, flaggers, behaviours, semantic search, annotations)
• Fix: Latitude dispatches your coding agents (Claude Code, Cursor) with the full context, sample traces, and a deep link.查看完整 README ↗目前无法加载完整 README。请通过原文链接阅读。 以下为已保存的摘录。
Agents that fix themselves, at scale.
Latitude finds where your agent fails and gets it fixed.
• Observe: one line of telemetry captures every trace: multi-turn sessions, tool calls, and full execution paths. (traces, sessions, tool-call observability, OpenTelemetry ingest)
• Understand: failing traces are auto-grouped into tracked signals with status, size, and trend, so you see what's breaking and how often. (signals, flaggers, behaviours, semantic search, annotations)
• Fix: Latitude dispatches your coding agents (Claude Code, Cursor) with the full context, sample traces, and a deep link.查看完整 README ↗