Folders and files
| Name | Name | Last commit date | ||
|---|---|---|---|---|
Rediscover your social memories with private, AI-powered analysis.
Official Website · Download · Documentation · Roadmap · Issue Submission
ChatLab is an open-source desktop app for understanding your social conversations. It combines a flexible SQL engine with AI agents so you can explore patterns, ask better questions, and extract insights from chat data, all on your own machine.
Currently supported: WhatsApp, LINE, WeChat, QQ, Discord, Instagram, and Telegram. Coming next: iMessage, Messenger, and KakaoTalk.
- 🚀 Built for large histories: Stream parsing and multi-worker processing keep imports and analysis responsive, even at million-message scale.
- 🔒 Private by default: Your chat data and settings stay local. No mandatory cloud upload of raw conversations.
- 🤖 AI that can actually operate on data: Agent + Function Calling workflows can search, summarize, and analyze chat records with context.
- 📊 Insight-rich visual views: See trends, time patterns, interaction frequency, rankings, and more in one place.
- 🧩 Cross-platform normalization: Different export formats are mapped into a unified model so you can analyze them consistently.
For more previews, please visit the official website: chatlab.fun
- Local-first by default: Raw chat data, indexes, and settings remain on-device unless you explicitly choose otherwise.
- Streaming over buffering: Stream-first parsing and incremental processing keep large imports stable and memory-efficient.
- Composable intelligence: AI features are assembled through Agent + Tool Calling, not hard-coded into one model path.
- Schema-first evolution: Import, query, analysis, and visualization share a consistent data model that scales with new features.
- Main Process (control plane): electron/main/index.ts handles lifecycle and windows. electron/main/ipc/ defines domain-scoped IPC, while electron/main/ai/ and electron/main/i18n/ provide shared AI and localization services.
- Worker Layer (compute plane): electron/main/worker/ runs import, indexing, and query tasks via workerManager, keeping CPU-heavy work off the UI thread.
- Renderer Layer (interaction plane): Vue 3 + Nuxt UI + Tailwind CSS drive management, private chat, group chat, and analysis interfaces. electron/preload/index.ts exposes tightly scoped APIs for secure process boundaries.
- Ingestion: parser/ detects file format and dispatches to the matching parser module.
- Persistence: Stream-based writes populate core local entities: sessions, members, and messages.
- Indexing: Session- and time-oriented indexes are built for timeline navigation and retrieval.
- Query & Analysis: worker/query/* powers activity metrics, interaction analysis, SQL Lab, and AI-assisted exploration.
- Presentation: The renderer turns query output into charts, rankings, timelines, and conversational analysis flows.
- Pluggable parser architecture: Adding a new import source is mostly an extension in parser/formats/*, without reworking downstream query logic.
- Full + incremental import paths: streamImport.ts and incrementalImport.ts support both first-time onboarding and ongoing updates.
- Modular IPC boundaries: Domain-based IPC segmentation reduces cross-layer coupling and limits permission spread.
- Unified i18n evolution: Main and renderer processes share an i18n system that can evolve with product scope.
- Node.js >= 20
- pnpm
# install dependencies
pnpm install
# run electron app in dev mode
pnpm devIf Electron encounters exceptions during startup, you can try using electron-fix:
npm install electron-fix -g
electron-fix start
Please follow these principles before submitting a Pull Request:
- Obvious bug fixes can be submitted directly.
- For new features, please submit an Issue for discussion first; PRs submitted without prior discussion will be closed.
- Keep one PR focused on one task; if changes are extensive, consider splitting them into multiple independent PRs.
Before using this software, please read the Privacy Policy & User Agreement.
AGPL-3.0 License