Open-source alternatives to ChatLab

OpenPanel is a self-hosted product analytics platform designed for tracking user behavior and visualizing product metrics on private infrastructure. It provides a comprehensive system for collecting events across web, mobile, and server environments while ensuring complete ownership of data. The platform distinguishes itself through a privacy-first approach, utilizing cookieless event tracking and regional data residency to simplify regulatory compliance. It integrates large language models via the Model Context Protocol, enabling users to query behavioral data and analyze trends using natura

Echotrace is a chat history decryptor and communication analytics tool designed for privacy-focused data backups. It transforms encrypted local messaging records, including those from Signal and WeChat, into plain text and structured data. The project functions as a decryption utility and an HTML report generator, converting conversation logs into static web pages for offline viewing. It also acts as a stateless analyzer that computes frequency and volume metrics from raw message files to generate statistical reports and visual charts on interaction trends. The system covers capabilities for

G0DM0D3 is a static web client and multi-model chat gateway designed for AI research, prompt optimization, and red teaming. It provides a unified interface to query numerous AI models in parallel, allowing for the simultaneous evaluation of different prompt variations and sampling parameters to identify the most successful outputs. The project features specialized tooling for probing safety filters and bypassing model constraints through an input perturbation engine that applies text obfuscation and character substitution. It includes a composite scoring system to rank model performance and a

Goatcounter is a privacy-focused web analytics platform designed to be self-hosted on your own infrastructure. It collects visitor statistics like page views, browser information, location, screen size, and referring sites without using cookies or storing any personal data, identifying unique visits through a non-identifiable hash derived from browser and network data. The platform distinguishes itself by offering multiple tracking methods that respect user privacy, including a lightweight JavaScript snippet, an image-based tracking pixel for environments without JavaScript, and the ability t

Fathom is a privacy-focused website analytics server written in Go. It monitors website traffic and page views without collecting personal data or using intrusive cookies, providing a self-hosted alternative for traffic monitoring. The system utilizes a Preact-based dashboard interface for visualizing traffic patterns and reports. Data is persisted in a SQL database analytics store, with support for MySQL, PostgreSQL, and SQLite. The project covers the collection of visitor data via lightweight tracking snippets and the management of that data through a pluggable storage layer. It includes m

Redash is a self-hosted analytics platform and SQL data visualization tool. It provides a web-based SQL query editor for writing, executing, and scheduling database queries, and functions as a business intelligence dashboard for monitoring metrics via visual widgets. The platform distinguishes itself through its data source connectors, which integrate with various SQL, NoSQL, and API-based stores to retrieve information for analysis. It enables self-service analytics by allowing users to run queries with dynamic parameters and supports shared data reporting via public links or embedded dashbo

Exportify is a web-based music metadata tool and data archive utility designed to export Spotify playlists and liked songs into portable CSV files. It serves as a multi-language data export utility that allows users to save track, album, and artist details for long-term preservation or data analysis. The tool provides capabilities for bulk playlist archiving, where entire collections of playlists are saved as CSV files and bundled into a single ZIP archive. It also supports targeted extraction through playlist search and filtering based on ownership or collaboration status. The system handle

Chartbrew is a self-hosted business intelligence platform and data visualization engine designed to transform raw data from SQL databases and external API endpoints into interactive charts and dashboards. It serves as a tool for building analytics dashboards that monitor business metrics and KPIs through a privately hosted environment. The platform distinguishes itself with an embedded analytics workflow, allowing users to generate secure, time-limited shared links and iframes to display private charts on external websites. It also provides programmatic chart generation via API and integrates

OpenReplay is a session replay platform and frontend debugging suite designed to record and play back user browser sessions. It functions as a user behavior monitoring system that captures interaction patterns and technical metadata to identify conversion issues and revenue loss. The platform is distinguished by its self-hosted infrastructure model, allowing the recording and analytics pipeline to be deployed on private servers for full control over data residency. It also includes a browser co-browsing tool for real-time screen sharing and direct communication to provide immediate technical

Discord Chat Exporter is a tool for extracting messages and media from Discord channels and direct messages into offline files. It functions as a backup utility and archival tool, using authentication tokens to retrieve chat history and metadata for long-term storage or history recovery. The system converts API data into readable documents and supports multi-format export options, including HTML, TXT, CSV, and JSON. It includes capabilities for automated chat backups by creating recurring tasks through the host operating system's task scheduler. The tool provides data management features suc

Apache DataFusion is an extensible, columnar SQL query engine that runs embedded within a host application without requiring a separate server process. It processes data in columnar batches using Apache Arrow for memory-efficient analytics, and can scale analytic workloads across multiple nodes for parallel execution. The engine supports both SQL and DataFrame queries through a modular, streaming architecture that allows custom operators, data sources, functions, and optimizer rules. The engine distinguishes itself through its modular extension framework, which enables building custom query e

Goatcounter is a self-hosted web analytics platform that collects visitor statistics without cookies, personal data, or persistent identifiers. It uses privacy-preserving techniques like anonymous session hashing to count page views and visits, and can be deployed on your own infrastructure using a binary or Docker container with SQLite or PostgreSQL storage. The platform offers multiple data collection methods, including a lightweight JavaScript snippet, an image-based tracking pixel for environments where scripts are blocked, and server log file parsing from nginx, Apache, Caddy, or CloudFr

Umami is a privacy-focused web analytics platform and open-source visitor tracking tool. It functions as a self-hosted alternative to commercial tracking services, allowing the operation of a private analytics platform on independent infrastructure to maintain ownership and control over visitor data. The platform focuses on monitoring website traffic and analyzing user behavior without using invasive data collection methods. It provides capabilities for mapping user journeys and performing audience segmentation to compare how different visitor cohorts interact with site content.

PyCaret is a Python AutoML platform and MLOps lifecycle manager designed to automate machine learning workflows. It functions as a low-code environment that leverages a scikit-learn native engine to execute preprocessing, training, and evaluation for tabular data. The platform distinguishes itself as an LLM-powered ML copilot, using large language model agents to analyze datasets, design experiment configurations, and explain model results. It also serves as a Kubernetes ML orchestrator and model registry, enabling the versioning of trained pipelines and their promotion to production API endp

Gemini Voyager is a browser-based toolkit designed to enhance the interface and workflow of large language model web applications. It serves as a conversation manager, an output renderer, and a prompt library manager, allowing users to customize the layout and functionality of AI chat interfaces. The project distinguishes itself through advanced content handling, such as removing image watermarks by reversing alpha blending to restore original pixels. It also provides specialized rendering for LaTeX mathematical formulas and Mermaid diagrams, alongside tools to fix broken Markdown formatting

esProc is a distributed ETL framework and embedded data computation engine. It provides a structured data language for the Java Virtual Machine designed for relational queries, complex data computation, and structured data analysis. The system features a natural language data query interface that leverages large language models to translate requests into executable queries against structured datasets. It employs a domain-specific query language with a concise syntax to establish table relationships and retrieve information. The platform covers data integration across disparate relational and

Pinot is a distributed, columnar analytical database designed for high-concurrency, low-latency query processing. It functions as a real-time OLAP datastore, enabling interactive, user-facing analytics by ingesting and querying massive datasets from both streaming and batch sources. The system architecture relies on a centralized controller for cluster coordination and a distributed segment-based storage model to ensure horizontal scalability. The platform distinguishes itself through a hybrid ingestion pipeline that unifies real-time event streams and historical batch data into a single quer

Materialize is a streaming SQL database that continuously ingests live data from sources such as Kafka, Redpanda, PostgreSQL, and MySQL, and incrementally maintains materialized views. It provides a PostgreSQL-compatible query engine that accepts standard SQL over the PostgreSQL wire protocol, enabling any existing SQL client or BI tool to query real-time data. The system also includes a Model Context Protocol (MCP) server that exposes live materialized view data to AI agents, providing fresh context without polling. Materialize distinguishes itself through its ability to offer configurable c

This project is an extension for JupyterLab that integrates large language model providers and AI agents directly into computational notebooks. It functions as an integration layer and orchestrator, bridging generative AI backends with a data science workspace to enable the execution of AI prompts within notebook cells and the insertion of generated code blocks into documents. The system features a collaborative chat interface where multiple users can engage with AI personas in real time, sharing conversation threads and utilizing drag-and-drop file attachments for context. It allows for the

CodexPlusPlus is a suite of specialized tools designed for API redirection, runtime application enhancement, binary updates, history exportation, and remote editor bridging. It functions as an enhancement framework that modifies the runtime behavior of a specific desktop application. The project provides a proxy mechanism to reroute model requests to custom endpoints while maintaining the original application authentication state. It also includes a bridge to connect local application contexts to remote SSH environments for file editing and a system to automatically download and install the l

Perfetto is a platform for system-level performance tracing and analysis on Linux and Android. It combines a high-throughput trace recorder, a SQL-based query engine, and a browser-based visualizer into a single toolchain. The platform covers CPU scheduling and call-stack profiling, native and Java heap memory allocation tracking, GPU and graphics events, and system-wide counters such as CPU frequency and power consumption. The architecture decouples trace recording from offline analysis, using a compact protobuf format for event encoding and columnar storage for efficient SQL queries. The we

Feast is an open-source feature store for machine learning that provides a central platform for defining, storing, and serving features across both training and inference workflows. It operates as a declarative system where feature definitions are written as code in Python files, synchronized to a central registry, and made available for low-latency online retrieval or point-in-time correct historical joins for training datasets. The project abstracts storage behind a pluggable architecture, allowing offline and online backends to be swapped without changing retrieval logic, and coordinates ma

Apache Hudi is an open-source table format that brings ACID transactions, incremental processing, and multi-modal indexing to data lakes. It provides atomic commits with snapshot isolation, rollback, and optimistic concurrency control for reliable data lake operations, while supporting upserts, record-level updates, and deletions in large analytical datasets. The project distinguishes itself through a timeline-based architecture that coordinates all write operations, enabling features like time-travel querying, incremental change streaming, and multi-modal query views that include snapshot, i

Lightdash is an open-source business intelligence platform that treats analytics logic as code. It centralizes metric and dimension definitions in a semantic layer, allowing data teams to define business metrics in YAML files version-controlled alongside data models. This approach ensures consistent, governed data access without requiring users to write SQL. Lightdash introduces CI/CD workflows for BI content, enabling teams to validate, test, and deploy analytics changes through automated pipelines and isolated preview environments. Its natural language query interface allows users to ask qu

DB-GPT is an agentic data analysis platform and business intelligence AI that functions as a large language model data assistant. It provides a text-to-SQL interface and a sandboxed code execution environment to translate natural language into executable database queries and Python scripts. The platform utilizes iterative agentic reasoning to plan and execute multi-step data analysis workflows through tool calls. It features a modular skill-based extension system that allows domain knowledge and analysis workflows to be packaged into reusable functional components. The system integrates data