# Open Source

Workflow orchestration engine

Netflix-originated workflow orchestration platform with JSON and code-based workflow definitions, human-in-the-loop support, and AI agent orchestration capabilities. With 18k+ GitHub stars, Conductor handles complex distributed workflows at massive scale, offering built-in retry logic, event-driven triggers, and visual workflow monitoring for microservice coordination.

Context engineering patterns for AI coding assistants

Context Engineering Intro is an open-source repository by Cole Medin providing structured context engineering patterns for AI coding assistants. Built around Claude Code, it includes .claude command files, PRP templates, and the WISC framework for managing AI context in coding sessions. The repo shows how to structure project context and rules so AI assistants produce reliable, architecture-aware code. With 13K+ GitHub stars, it is a go-to reference for context-first AI coding.

GitHub Copilot AI assistant native to Xcode

Copilot for Xcode is GitHub's official AI coding assistant for Apple's Xcode IDE. It provides inline code completions, chat-based coding help, and code review directly in Swift and Objective-C workflows. The extension integrates natively with Xcode, supporting iOS, macOS, watchOS, and tvOS development with context-aware suggestions. With 6K GitHub stars, it is the standard way Apple platform developers access Copilot.

Full-stack framework for building AI copilots with generative UI

CopilotKit is an open-source full-stack framework for building AI-native applications with generative user interfaces. It provides React and Angular SDKs that enable agents to dynamically generate and render UI components, synchronize state between frontend and backend in real time, and implement human-in-the-loop workflows. Supports integration with LangChain, LangGraph, CrewAI and protocols including AG-UI, MCP, and A2A for standardized agent interaction.

Open-source deep learning text-to-speech toolkit

Coqui TTS is an open-source deep learning toolkit for text-to-speech synthesis, originally built by former Mozilla TTS engineers. It supports multi-speaker and multilingual synthesis, voice cloning from just six seconds of audio, and ships pre-trained models for 20+ languages. After Coqui shut down in 2023, the Idiap Research Institute forked and actively maintains it. With 45K+ GitHub stars, it remains the most popular open-source TTS framework in Python.

Full-lifecycle AI agent optimization and monitoring

CozeLoop is an open-source AI agent optimization platform from ByteDance's Coze ecosystem providing full-lifecycle management from development to production monitoring. It enables developers to debug agent prompts, evaluate agent performance across test cases, optimize reasoning processes, and monitor deployed agents in real-time. Built on Go and React with SDKs for Go, Python, and Node.js, CozeLoop is designed for enterprise-grade AI agent development and operation.

Production-grade web scraping and browser automation library

Crawlee is an open-source web scraping and browser automation library for Node.js and Python that handles the hard parts of building reliable crawlers. It manages proxy rotation, request queuing, automatic retries, session management, and fingerprint spoofing out of the box. Supports Puppeteer, Playwright, Cheerio, and HTTP-based crawling with a unified API. Built by Apify, it includes persistent storage, autoscaling concurrency, and TypeScript-first design for production deployments.

Kubernetes-native cloud infrastructure control plane

Crossplane is a CNCF Graduated open-source project that extends Kubernetes to manage cloud infrastructure through declarative APIs. Platform teams compose custom infrastructure abstractions as Compositions and publish them as self-service APIs. It provisions resources across AWS, Azure, GCP, and 200+ providers directly from kubectl. Used by 450+ organizations with 11,000+ GitHub stars.

End-to-end encrypted collaboration suite

CryptPad is an open-source end-to-end encrypted collaboration suite that provides real-time document editing, spreadsheets, presentations, kanban boards, whiteboards, and forms without the server ever accessing user content. Built as a privacy-first alternative to Google Workspace, CryptPad encrypts all data client-side so neither administrators nor attackers can read stored documents. It supports team drives, access control, and self-hosting.

Community cursor rules directory

Community-maintained collection of .cursorrules files that customize Cursor IDE's AI behavior for specific frameworks, languages, and project types. Define coding conventions, preferred libraries, architectural patterns, and style guidelines that the AI follows consistently. Popular rules exist for Next.js, React, Python, TypeScript, Tailwind, and more. Hosted on cursor.directory with 1-click installation. Essential for getting consistent, project-aware AI completions in Cursor.

Universal database tool

DBeaver is a free, open-source universal database GUI and SQL client supporting 100+ engines including PostgreSQL, MySQL, Oracle, SQL Server, SQLite, MongoDB, Cassandra, and Redis. Offers a consistent cross-platform interface for schema browsing, visual query building, SQL execution, data editing, ER diagrams, and data migration between heterogeneous databases, all in a single Java-based desktop app.

Programming — not prompting — LLMs

Declarative framework from Stanford University for programming language models rather than prompting them. DSPy treats LLM interactions as programmable modules with input-output signatures and uses optimization algorithms to automatically compile these modules into effective prompts or fine-tuned weights, replacing brittle prompt strings with structured, modular AI software.

3D reconstruction without camera parameters

DUSt3R is Naver's breakthrough 3D reconstruction method that generates dense 3D scenes from unconstrained image pairs without known camera intrinsics or extrinsics. It casts pairwise reconstruction as pointmap regression, removing hard geometric constraints of projective camera models. Supports multi-view alignment, depth estimation, visual localization, and extends to MASt3R and MUSt3R for large-scale applications.

Git-based version control for ML data and pipelines

DVC (Data Version Control) is a free open-source tool that brings Git-like version control to datasets, ML models, and experiment pipelines. It stores pointer files in Git while keeping large data in remote storage like S3, GCS, or Azure. Features include reproducible ML pipelines with DAG-based dependency tracking, experiment management, metrics comparison, and a VS Code extension for visual experiment tracking.

Programmable CI/CD engine that runs your pipelines in containers

Programmable CI/CD engine that replaces shell scripts and YAML with a typed API across 8 languages (Go, Python, TypeScript, Java, Rust, etc.). Dagger runs every pipeline step in containers for portable, locally-debuggable, cacheable builds that work identically on any CI platform. Includes GraphQL query optimization for parallelization, OpenTelemetry observability, and Dagger Cloud for managed compute.

Containerized sandboxes for AI coding agents

Dagger Container Use provides isolated container environments for AI coding agents, enabling multiple agents to work in separate sandboxed branches simultaneously. Built by the Dagger team, it ensures reproducibility and safety for autonomous code execution by giving each agent its own containerized workspace with full toolchain access.

Single-binary workflow engine with zero dependencies

Dagu is a local-first, self-contained workflow engine that runs as a single binary under 128MB of memory with no database, message broker, or runtime dependencies. Workflows are defined in declarative YAML and can orchestrate shell commands, Docker containers, SSH sessions, HTTP calls, and SQL queries. It includes a built-in Web UI with DAG visualization and Gantt charts, plus an AI agent that creates and debugs workflows from natural language via Slack or Telegram.

Open-source BI tool for data visualization

DataEase is an open-source business intelligence tool that enables anyone to perform data analysis and build visualizations through a drag-and-drop interface without coding. It connects to MySQL, PostgreSQL, Elasticsearch, ClickHouse, and other data sources, providing interactive dashboards that can be shared via links or embedded in applications. DataEase offers chart templates, calculated fields, and role-based access control for team collaboration.

Open-source metadata platform for data discovery

DataHub is an open-source metadata platform for data discovery, governance, and observability, originally developed at LinkedIn. It provides a centralized catalog with 80+ integrations for data warehouses, lakes, dashboards, and ML platforms. DataHub offers real-time metadata ingestion, column-level lineage tracking, automated quality checks, and fine-grained access policies. Used by 3,000+ organizations in production. Apache 2.0 licensed with 11.8K+ GitHub stars.

Visual database designer with Git-integrated schemas

DbSchema is a visual database designer supporting 80+ SQL and NoSQL databases that features Git integration for schema version control, interactive HTML documentation generation, and AI-assisted query building. It provides the best visual approach to designing and maintaining database schemas in a version-controlled environment, bridging the gap between visual design and code-managed infrastructure.

AI data runtime for multimodal datasets and vector search

Deep Lake is an open-source AI data runtime from Activeloop for storing, versioning, and querying multimodal data and embeddings. It fits teams building RAG, training, evaluation, or dataset-heavy agent workflows that need a bridge between vector search, structured metadata, and large image, text, audio, or video collections.

DeepSeek's expert-parallel communication library for MoE model training

DeepEP is DeepSeek's open-source communication library optimized for expert-parallel training of Mixture-of-Experts models. It provides efficient GPU-to-GPU data routing for distributing tokens to expert networks across multiple devices during MoE model training and inference. Enables the distributed expert parallelism that powers DeepSeek's competitive model efficiency. Over 9,100 GitHub stars.

DeepSeek's FP8 general matrix multiplication kernels for efficient inference

DeepGEMM is DeepSeek's open-source library of FP8 matrix multiplication CUDA kernels optimized for LLM inference and training on modern NVIDIA GPUs. It provides efficient GEMM operations using 8-bit floating point precision that reduce memory bandwidth requirements while maintaining model accuracy. Designed for integration into inference engines and training frameworks. Over 6,300 GitHub stars.

State-of-the-art open-source code language models

DeepSeek Coder is a family of open-source code language models trained from scratch on 2 trillion tokens of code and natural language data. Available in sizes from 1B to 33B parameters, these models support 80+ programming languages with 16K context windows and fill-in-the-blank capabilities. DeepSeek Coder outperforms CodeLlama-34B on HumanEval and MBPP benchmarks while being commercially licensable under MIT.

Open-source, plugin-based agent harness from DeepSeek

DeepSeek Harness (dsh) is an open-source, MIT-licensed agent harness from DeepSeek with a web UI, desktop app, CLI and SDK, in developer preview. It is built on a plugin architecture and works with a DeepSeek API key or other compatible model providers. Session-log upload to the DeepSeek API is on by default in the master branch as of 30 Sep 2026 and can be turned off.

Deep learning optimization for distributed training

DeepSpeed is Microsoft's open-source deep learning optimization library that makes distributed training and inference easy, efficient, and effective. Its ZeRO optimizer eliminates memory redundancies across data-parallel processes, enabling training of models with trillions of parameters. DeepSpeed supports 3D parallelism combining data, pipeline, and tensor parallelism, along with mixed precision training, gradient checkpointing, and CPU/NVMe offloading for memory-constrained environments.

Open-source LLM red-teaming framework with 40+ attack types

DeepTeam is an open-source red-teaming framework for systematically testing LLM applications against 40+ adversarial attack types. It covers OWASP Top 10 for LLMs including jailbreaks, prompt injection, PII leakage, and hallucination attacks. Built as the sister project of DeepEval for security testing alongside evaluation. Apache-2.0 licensed.

ByteDance's open-source agentic workflow platform

DeerFlow is ByteDance's open-source agentic workflow platform that combines LLM-powered agents with deep research capabilities. It features multi-agent orchestration, web research automation, report generation, and podcast creation from research outputs. Built with LangGraph, it supports configurable LLM backends and provides a modern React-based UI for managing complex AI-driven research and content workflows.

Swiss-army MCP server for local system automation

DesktopCommanderMCP is a general-purpose MCP server that gives AI agents the ability to execute local programs, read and write files, search the filesystem, and edit text files. It acts as a comprehensive local system actuator, enabling coding agents to interact with the development environment beyond just code editing.

Instant isolated dev environments powered by Nix

Devbox is an open-source command-line tool that creates instant, reproducible development environments using Nix packages without requiring you to learn Nix. Define your project dependencies in a simple devbox.json file and get isolated shells with access to over 400,000 package versions. It eliminates dependency conflicts between projects and ensures every team member works in an identical environment, with support for devcontainers, Docker, and cloud deployment.

Kubernetes dashboard with 360-degree visibility

Devtron is an open-source Kubernetes management dashboard that provides a 360-degree view of cluster resources with fine-grained RBAC for multi-cluster environments. Its upcoming agentic AI feature automates debugging and cluster optimization, while the current platform offers centralized visibility, GitOps-based deployment workflows, and security policy enforcement across distributed Kubernetes infrastructure.

Open-source IaC orchestration that runs Terraform plans and applies from pull request comments

Digger is an open-source infrastructure-as-code orchestration tool for running Terraform and OpenTofu plan/apply workflows from pull request comments. It uses the team’s existing VCS and CI runners instead of adding a separate runner fleet, supports GitHub, GitLab, and Azure DevOps style workflows, and stores PR-level locks and plan cache in the user’s cloud account.

Get your documents ready for gen AI

Docling is an open-source document processing toolkit by IBM Research that converts complex documents into structured formats optimized for generative AI applications. It parses PDF, DOCX, PPTX, XLSX, HTML, images, audio, and LaTeX with advanced PDF understanding including layout analysis, reading order detection, and table structure recognition. Docling exports to Markdown, HTML, JSON, and DocTags, and integrates natively with LangChain, LlamaIndex, and other AI frameworks for RAG workflows.

Self-hosted collaborative wiki and documentation platform

Docmost is an open-source collaborative wiki offering real-time editing, spaces with granular permissions, page history, and rich diagram support via Draw.io, Excalidraw, and Mermaid. Designed as a self-hosted Confluence and Notion alternative for teams needing data sovereignty, it provides nested pages, comments, and full-text search. Over 19,700 GitHub stars and 52 releases demonstrate strong community adoption.

Open-source voice AI platform with visual builder and MCP integration

Dograh is an open-source voice AI platform and visual workflow builder. It enables teams to build self-hosted conversational agents, plug in BYOK models and speech engines, connect telephony providers, and orchestrate tools via Model Context Protocol.

The smallest PaaS implementation

Dokku is a Docker-powered, open-source mini-Heroku that gives you the smallest PaaS implementation for deploying applications on your own server. Push with Git, build via Heroku buildpacks or Dockerfiles, and get automatic subdomains, SSL, zero-downtime deploys, and add-on plugins for databases and services. Ideal for self-hosted developers who want Heroku ergonomics without the cloud vendor bill.

Open-source PaaS alternative to Vercel, Heroku, and Netlify

Dokploy is a free open-source platform-as-a-service for self-hosting applications without cloud vendor lock-in. It provides automated deployments from Git repositories, built-in SSL certificates, database provisioning, Docker and Docker Compose support, and a clean web dashboard for managing multiple applications on your own servers. With 18,000+ GitHub stars, it fills the gap for teams wanting Vercel-like deployment simplicity on their own infrastructure.

ByteDance multimodal document image parser

Dolphin is ByteDance's multimodal document parsing model that handles intertwined text, tables, formulas, and figures in complex documents. Using a two-stage analyze-then-parse approach with a Swin Transformer vision encoder and MBart decoder, it performs layout analysis and parallel element parsing with heterogeneous anchor prompts. Dolphin-v2 adds document-type awareness for invoices, papers, and forms.

Open-source control plane for AI workloads across multi-cloud GPU infrastructure

dstack is an open-source platform that orchestrates AI training and inference workloads across heterogeneous GPU infrastructure spanning multiple clouds, Kubernetes clusters, and bare-metal servers. It abstracts away cloud-specific APIs so teams define GPU requirements declaratively and dstack automatically provisions the cheapest available resources from AWS, GCP, Azure, Lambda, or on-premises hardware.

In-process analytical SQL database

DuckDB is a high-performance analytical database that runs as an in-process SQL OLAP engine. Unlike traditional client-server databases, DuckDB embeds directly within your application, similar to SQLite but optimized for analytical queries. It supports complex SQL including window functions, CTEs, and nested types while processing columnar data with vectorized execution. DuckDB reads Parquet, CSV, JSON, and Arrow formats natively and integrates with Python and R data science workflows.

Pluggable JavaScript and TypeScript linter

ESLint is the standard open-source linter for JavaScript and TypeScript with 26K+ GitHub stars. Statically analyzes code to find problems, enforce coding conventions, and automatically fix issues. Features a pluggable rule architecture with 300+ built-in rules and thousands of community plugins for React, Vue, Angular, Node.js, and more. Flat config system in ESLint v9 simplifies configuration. Integrates with every major editor, CI/CD pipeline, and build tool in the JavaScript ecosystem.

Your CI/CD scripts as code. Consistent, reproducible builds.

Build automation framework that combines Dockerfile and Makefile syntax for repeatable, containerized builds. Earthly runs every step in a container so builds produce identical results on dev laptops and CI, augmenting Make/Gradle/npm/cargo with cross-language reproducibility. Features parallel target execution, layer caching, multi-platform builds, and references across Earthfiles or repositories.

Postgres sync engine for local-first and real-time applications

ElectricSQL is a sync engine that keeps local application state synchronized with PostgreSQL in real-time. It enables local-first architectures where apps work offline with instant responsiveness, syncing data bidirectionally when connectivity is available. Supports partial replication with shape-based subscriptions to sync only relevant data subsets to each client.

Ultra-fast desktop apps with TypeScript, Bun, and Zig

Electrobun is an open-source cross-platform desktop app framework that combines TypeScript with Bun runtime and Zig for native performance. It produces 12MB base installs versus hundreds of MB for Electron, while maintaining full web technology compatibility. Electrobun uses the system's native webview instead of bundling Chromium, delivers sub-second cold starts, and provides native OS integrations through a Zig bridge layer.

Kernel-space host intrusion detection system

Elkeid is ByteDance's open-source HIDS for hosts, containers, Kubernetes, and serverless workloads. Its kernel-level data collection via Kprobe hooks captures process lineage, privilege escalation attempts, file access patterns, and network connections with minimal overhead. Includes an Agent for telemetry, Detector for rule evaluation, Controller for policy management, and a Dashboard for alerts and investigation.

Prompt engineering framework treating prompts as versioned Python functions

Ell is a prompt engineering library that treats LLM prompts as versioned, testable Python functions rather than opaque strings. Built by ex-OpenAI researcher William Guss, it provides automatic prompt versioning with content-addressable hashing, a local TensorBoard-like studio for visualizing prompt evolution, and structured output support via Pydantic. 5,800+ GitHub stars, MIT licensed. Designed for teams who want to version-control and systematically improve their prompts over time.

Code management platform for AI coding agents

Entire is an AI-native code management platform designed for teams managing fleets of AI coding agents. Founded by former GitHub CEO Thomas Dohmke, it records the reasoning and instructions behind AI-generated code alongside the code itself, making agent-written software easier to review, audit, and maintain. Launches with Checkpoints, an open-source CLI tool that logs prompts and token usage for Claude Code and Google Gemini CLI, with more agent integrations planned.

Console for mobile browsers

Open-source mobile web console that embeds a full developer toolkit into any mobile browser. Provides console, element inspection, network monitor, resource viewer, performance timing, and JavaScript execution on devices that lack native DevTools. The de facto standard for debugging responsive layouts, mobile-specific JavaScript errors, and production issues on phones — loaded with a single script tag or a browser extension.