# ChatLab/ChatLab

Local-first chat history analyzer with AI. | 本地优先的 AI 聊天记录分析工具

Repository: https://github.com/ChatLab/ChatLab
Canonical: https://ross.abutalabs.com/products/chatlab
Homepage: https://chatlab.fun
Language: TypeScript
License: AGPL-3.0
License Family: copyleft
Topics: chat-history, data-visualization, data-analysis, ai-agent, chat-analyzer, harness
Last push: 2026-08-26T16:21:56+00:00

## Health v2 (maintenance only)
Score: 79/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 86, longevity 20
- inputs: {"age_days": 280, "days_push": 7, "days_rel": 13, "gap_med": 2, "n_releases_24m": 76}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 7250, forks 1496 (observed 2026-08-28T04:09:57.833152+00:00)

## What it is
ChatLab is an open-source, local-first desktop application (with an optional CLI) for analyzing chat histories from platforms like WhatsApp, Telegram, QQ, Discord, LINE, Instagram, iMessage, and Google Chat. It combines a SQL engine, rich visualizations, and an AI agent with function calling (plus MCP support) to let users explore and query their conversations privately on their own machine.

## Use cases
- analyze my whatsapp chat history with word clouds and heatmaps
- search and summarize years of telegram messages with AI
- visualize who I talk to most and when across chat apps
- import QQ or iMessage exports and explore them with SQL
- run a local MCP server so AI agents can query my chat records
- find relationship trends and topics in million-message chat logs

## When to choose
- you want private, local analysis of chat exports without uploading raw conversations
- you need cross-platform normalization of chat formats into one queryable model
- you want AI-assisted search and summarization over large chat histories
- you need visual dashboards like rankings, heatmaps, and timelines for chats

## When to avoid
- you need real-time chat monitoring or live message capture rather than analyzing exports
- you require fully offline AI without any data sent to model providers (AI features send processed content to configured providers)
- you need a team/enterprise multi-user analytics service rather than a personal local tool

## Facets
- artifact type: application
- maturity: active
- function: data-visualization, analytics, nlp, agent-framework, mcp, search-engine, cli
- domain: data-visualization, analytics, privacy, self-hosted, messaging-platforms, developer-tools
- platform: cross-platform, cli, self-hosted
- tags: chat-history-analysis, local-first, whatsapp, telegram, discord, imessage, qq, line, word-cloud, sql-engine, function-calling, natural-language-processing, ai-agents, desktop, nodejs, electron, docker

## Member repositories
- ChatLab/ChatLab (main) score 79

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:57.833152+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:39:43.531039+00:00, confidence not recorded.
  - readme: https://github.com/ChatLab/ChatLab (fetched 2026-08-28T04:09:57.833152+00:00, sha 08e1b0df4c3e)
  - homepage: https://chatlab.fun (fetched 2026-08-29T08:34:41.415345+00:00, sha 4ddc2978f898)
  - site_page: https://docs.chatlab.fun/ (fetched 2026-08-29T08:34:41.424631+00:00, sha a6769af158de)
- Data as of 2026-08-30T08:39:29.467469+00:00.