OpenAI
Frontier models, developer APIs, ChatGPT, and agent-facing tools. The reference point for many modern Open* apps.
A curated directory of open AI apps, agent workflows, infrastructure, security, observability, public data, and developer tools.
Frontier models, developer APIs, ChatGPT, and agent-facing tools. The reference point for many modern Open* apps.
Self-hosted AI interface for local and cloud models, with tools, prompts, documents, RAG, and team workflows.
Model routing and API access across many providers. Useful when comparing behavior, price, and availability.
Memory layer for coding agents and MCP workflows, aimed at keeping useful context available across sessions.
Configurable research agent from LangChain for bringing your own models, search tools, and MCP servers.
Open source computer vision library for image processing, machine perception, deep learning, and edge AI work.
Fine-tuning and agent reinforcement-learning tooling that turns expensive prompts into cheaper task-specific models.
Open platform for cloud coding agents, with CLI, SDK, web workflows, and model-agnostic agent orchestration.
Open-source framework for internal coding agents with cloud sandboxes, workflow triggers, subagents, and PR creation.
Open source coding agent for terminal, IDE, and desktop workflows, with broad model-provider support.
Open-source AI website-to-app builder that turns existing sites into React and Next.js application code.
Vendor-neutral feature flag specification and SDK ecosystem for keeping product rollout logic portable.
Agent workflows, skills, tutorials, recipes, service paths, and community discussion under the xopen umbrella.
Open implementation path for general AI agent experiments inspired by the newer autonomous-agent wave.
Open-source video editor for web and desktop — multi-track timeline, no watermark, and a real alternative to closed editors.
Local-first conversational video editor with a professional multi-track timeline, agent skills, and MCP integration.
Local-first design workspace that turns your coding agent into the design engine — prototypes, decks, and pages exported as real HTML, PDF, or PPTX.
Open project from milind-soni/OpenMausBot. Auto-discovered from GitHub.
Open-source AI coworkers that each get a computer of their own: a browser, files and tools, with every action decided before it happens and recorded after. Bring any AG. Auto-discovered from GitHub.
Open infrastructure for cloud computing. A foundational name for private cloud and infrastructure control.
Open infrastructure-as-code project for provisioning and managing cloud resources with a familiar workflow.
Search, observability, and analytics stack for searchable systems and operational dashboards.
Linux-based embedded operating system for routers and network devices with writable packages and deep control.
CNCF cost monitoring for Kubernetes and cloud spend, with per-workload attribution instead of one opaque invoice.
One data access layer for every storage backend — S3, GCS, HDFS, and dozens more behind a single API.
Open-source secrets manager and Vault fork for secret storage, dynamic credentials, and encryption services.
Fine-grained authorization system inspired by Zanzibar-style relationship-based access control.
Cryptography and TLS infrastructure used across the web. Not glamorous, but very much load-bearing.
Secure networking and VPN tooling for private access, remote operations, and network control.
Operating system project known for security focus, correctness, and a deeply opinionated engineering culture.
CNCF-graduated general-purpose policy engine. Keeps authorization and admission rules out of application code.
Vendor-neutral observability framework for traces, metrics, logs, APIs, SDKs, collectors, and instrumentation.
Open-source observability platform for logs, metrics, traces, dashboards, alerts, pipelines, and frontend monitoring.
Self-hosted session replay and product analytics for seeing user behavior and debugging frontend issues.
Open-source status page and uptime monitoring for teams that need transparent incident communication.
Open-source web and product analytics with event tracking, funnels, retention, and privacy-first reporting.
OpenTelemetry-based observability for LLM and agent apps — traces, prompts, token cost, and quality signals.
Collaborative map data for the world. A public knowledge layer for products, research, and civic tooling.
Open-source map hosting path for displaying custom OpenStreetMap-based maps in websites and apps.
Open catalog of the global research system, with scholarly works, authors, institutions, citations, and APIs.
Open-source database of sanctions, watchlists, and politically exposed persons for screening and research.
An open catalog for books and reading. Open systems are cultural infrastructure too.
Open data platform for investment research — market data, analytics, and an API built for analysts, quants, and agents.
Open* projects the crawler picked up in the last 60 days from GitHub and Hacker News. Raw finds, shown as-is — they only move up into the directory once they earn it.
Official repository for "OpenWAM: An Open, Modular Exploration Towards Systematic World–Action Model Pretraining".
Run any model in Grok Bot — one-command setup, model picker UI, evidence-based provider wire maps, and an update-proof doctor. Not farming you, arming you.
iMessage personal assistant + password vault
A Model Context Protocol server for persistent project-specific AI agent context.
Turn one Claude Code subscription into a crew of AI agents that research, plan, and ship code in parallel — a Slack-style HQ on your laptop where every risky action need.
A free, open-source macOS drag-and-drop shelf and Dynamic Island for files, images, text and links. Built with SwiftUI + AppKit.
Lightweight asynchronous reverse proxy and load balancer with health checks, circuit breaker, and Prometheus metrics. MIT licensed.
Open-source, white-label AI agent platform for agencies to deploy and manage branded WhatsApp agents across client accounts, with human handoff, knowledge bases, custom.
Entries are reviewed for projects that are genuinely useful and actively maintained — spanning research agents, feature flags, computer vision, and embedded networking.
If an open project deserves a place on the map, suggest it — every recommendation makes the directory sharper. Each card links straight to the project.