WeFlow is a local WeChat chat viewer, exporter, and annual-report app. The product site is weflow.top. The repo hicccc77/WeFlow was created 2026-01-07. On 2026-09-15 GitHub listed 14,293 stars and 445 forks. GitHub reports no SPDX license. The README on that day is a DMCA-era rewrite, not a feature list. Treat weflow.top and doc.weflow.top as first-party product facts.
X For You on 2026-09-12 showed @HalfuTeamo pairing WeFlow with WechatOnCloud and a ZFS copy-on-write sync. That is a community pipeline, not a WeFlow cloud product.
Compare Obsidian if you wanted a notes vault rather than chat export, Khoj if you wanted a local RAG assistant, or NotebookLM Skill if you wanted an agent skill over documents.
Key Features
- Local only: weflow.top says parse and export stay on the device. It claims offline use. It is not a WeChat web client.
- Export formats: JSON, HTML, TXT, Excel, CSV, PGSQL, and a ChatLab format. HTML aims to keep bubbles, stickers, voice, and images.
- Reports: yearly or multi-year annual reports, plus a two-person report for one friend. Private-chat and group stats cover volume, type mix, and time-of-day.
- HTTP API mapping: local messages become an HTTP API for scripts and AI assistants.
- Other modules on the site: anti-recall, desktop notifications with allow/deny lists, Moments decrypt/export, contact export.
Limitation: 14,293 stars is heat, not an audit. License is unverified. After the DMCA rewrite, do not assume GitHub still ships decrypt code. WeChat ToS and local law still apply. HTTP mapping is a local door; it is not a hosted WeChat API.
Use Cases
- People who keep WeChat on a desktop and need a searchable archive or yearly recap without uploading chats.
- Local AI pipelines that want chat text on an HTTP port, as in the X For You WechatOnCloud + WeFlow note.
- People who should stay inside WeChat if they only needed search in the official client.
Pricing
| Piece | Price | Notes from first-party pages 2026-09-15 |
|---|---|---|
| App | $0 listed | Site is free download. License SPDX is missing. |
| Cloud WeChat | Separate | WechatOnCloud is another project, not WeFlow. |
| Hosted WeChat API | Not this product | Mapping is local HTTP. |
Getting Started
- Open weflow.top and pick the build for your OS.
- Read doc.weflow.top before pointing it at a live WeChat data directory.
- Export a small HTML or JSON sample first. Confirm media paths before a full dump.
- If you need an HTTP door for an agent, enable mapping only on localhost.
First-party resource: weflow.top and doc.weflow.top. Contact listed on GitHub: yccccccy@proton.me.
Frequently Asked Questions
Does WeFlow upload chats?
The site says no. Verify the binary you actually run. GitHub README is not the current feature contract.
Is this official Tencent software?
No. It reads local WeChat data. Expect ToS and legal risk.
Can I skip WechatOnCloud?
Yes. WeFlow is a local app. The X post used WechatOnCloud only as a server-side WeChat host.
Alternatives
- Obsidian: notes vault if you already exported Markdown.
- Khoj: local RAG if the goal is Q&A, not WeChat decrypt.
- File Organizer: agent skill for files, not chat databases.
Tips
- Keep exports on the same machine as WeChat. Do not sync decrypted HTML to a public drive.
- Treat anti-recall and Moments intercept as extra legal risk, not as default settings.
- If GitHub looks empty of releases, use the site download and record the checksum yourself.
Comments
No comments yet. Be the first to comment!
Related Tools
Related Insights
Complete Guide to Claude Skills - 10 Essential Skills Explained
Deep dive into Claude Skills extension mechanism, detailed introduction to ten core skills and Obsidian integration to help you build an efficient AI workflow
Claudesidian: Transform Obsidian into an AI-Powered Second Brain
Discover Claudesidian, an open-source project that perfectly integrates Obsidian with Claude Code. Built-in PARA method, custom commands, and automated workflows for a complete idea-to-implementation solution.
Stop Cramming AI Assistants into Chat Boxes: Clawdbot Picked the Wrong Battlefield
Clawdbot is convenient, but putting it inside Slack or Discord was the wrong design choice from day one. Chat tools are not for operating tasks, and AI isn't for chatting.