Her · हेर - Claude Code 会话分析工具
阅读原文· huggingface.co每次 Claude Code 跑完都留下一堆 JSON,没人看。Her 用一个本地小模型帮你分析会话,钱花在哪、有没有危险操作一目了然,还不把数据传出去,是个务实的小工具。
Her(हेर)是专为 Claude Code 设计的会话分析工具。用户上传 .jsonl 文件后,Her 用自然语言重建每轮交互,标记部署、配置变更、秘密等高风险操作并定位到具体轮次。它展示 token 消耗、所用工具、子智能体、技能和 MCP 服务器,并结合 Anthropic 与社区最佳实践给出改进建议(仅在有明确可修复模式时)。内置“Ask Her”问答功能,支持单会话与跨会话项目分析。工具不调用第三方 AI API,使用 Nemotron-Mini-4B-Instruct 模型在 Hugging Face ZeroGPU 上运行,评估引擎完全确定,模型仅负责文本生成与建议。Her 内置 Homebrew、npm、PyPI 主流 CLI 工具数据库,自动识别会话中使用的工具,并对部署工具、数据库客户端等执行活动进行标记提醒。
Her · हेर — a detective for your Claude Code sessions
Her · हेर — Marathi for “detective.” A detective for your Claude Code sessions.
Try it here: Her on Hugging Face
Every Claude Code session leaves a trace — a .jsonl file with every turn, tool call, and token. But in practice, that trace is write-only. Rarely anyone reads 4,000 lines of JSON to figure out why the agent reached for production, where the context budget actually went, or which subagent quietly burned half the run.
Her reads it for you.
The premise is simple: drop a session file onto the page and let her investigate. She reconstructs what happened in plain English, flags the risky moves — deploys, config and production changes, secrets — and traces each one back to the exact turn where it happened.
She shows where the tokens went, which tools, subagents, skills, and MCP servers were used, and — only when a named, fixable pattern fires — what you could have done better, grounded in Anthropic’s and the community’s best practices. She suggests, never asserts, and stays silent when there’s nothing worth saying.
There’s also a built-in copilot: Ask Her. Ask “why was this tool used?” and she answers from the trace, cites the turns, and opens the exact tool call. Drop one file for a session view; drop several to build a project view and hunt a question across many sessions at once.
No third-party AI API is ever called. The model — Nemotron-Mini-4B-Instruct — runs on the Space’s own GPU via ZeroGPU. Your session is uploaded only to a private, auto-deleted namespace that belongs to your run, and nothing about it leaves the box.
The split that makes this trustworthy: the evaluation engine is purely deterministic. The model is used only to write the English and propose softer suggestions. It never asserts a finding. The numbers don’t move when the model changes.
One nice detail: Her doesn’t just list the CLI tools a session used — she identifies them. A database of top tools from Homebrew, npm, and PyPI ships with the Space, so most tools are named offline with a one-line blurb. When deploy tools, database clients, or dev servers are actually executed, Her flags that activity for the second look it deserves.
It grew over a weekend. It started as an operator’s view — a journey graph where every query is a node sized by cost, the heaviest one glowing — built for a friend.
I showed it to another friend who wanted it simpler, so the graph grew an executive Report that’s now the default. Then the first friend asked why their CLI tool didn’t show up — which is how the tool database was born.
The frontend is a React app served straight off a Gradio server, with the deterministic engine doing the forensics and Nemotron handling the prose.
When Claude loses his mind, call Her. ;)
Try it here: Her on Hugging Face
Spaces mentioned in this article 1
Community
Instead of her use 'wife' as name but great tool man 🌱
Haha thank you!
· or to comment




