Directory
126 products in total: 53 OSI-approved open source, 2 source-available, 5 unresolved-license Projects, and 66 proprietary. Structural source=open URLs remain supported; use the license-policy filter for the canonical distinction.
AI coding agent for terminal, editor, and desktop
OpenCode is a coding agent that runs where you already work rather than in a separate chat window. The same session can be driven from a terminal, an editor extension, or a desktop client, and it keeps context across all three.
Visual workflow automation with room to drop into code
n8n sits between a no-code automation builder and a scripting environment. Workflows are assembled on a canvas from several hundred integrations, and any node in that canvas can be replaced with a JavaScript or Python function when the visual version stops being expressive enough.
Turn any website into clean, model-ready data
Firecrawl handles the unglamorous part of feeding the web to a language model: rendering JavaScript, following pagination, stripping navigation and cookie banners, and returning markdown or structured JSON that a model can actually use.
Run open language models locally with one command
Ollama reduced local model hosting from an afternoon of CUDA troubleshooting to a single pull command. It handles model download, quantisation selection, GPU offloading, and memory management, and exposes an OpenAI-compatible endpoint on localhost.
Documents, databases, and project tracking in one workspace
Notion's insight was that a document and a database can be the same object. A page can be prose, a table, a board, or all three, and the same records can be viewed differently by different teams without duplication.
Web and product analytics tied to Google's ad stack
Google Analytics is free at the point of use because the data feeds an advertising business. For sites that advertise through Google, that integration is the entire value: audiences built here are usable directly in campaigns.
Build and deploy AI agents and RAG pipelines visually
Dify is where a prompt experiment becomes something a team can operate. Workflows are assembled on a canvas, datasets are indexed and versioned, and every deployment gets an API endpoint with logging and cost tracking attached.
Drag-and-drop builder for agents and RAG pipelines
Langflow turns pipeline construction into a graph you can see. Components are Python underneath, so a flow that outgrows the canvas can be exported and run as code rather than rebuilt.
One chat interface for every model you run or connect
Open WebUI is the front end that turns a local inference server into something a household or a team can actually use. It handles accounts, conversation history, document retrieval, and model switching, and speaks to both local runtimes and hosted APIs.
File sync and sharing across devices and teams
Dropbox made file sync boring in the best sense: a folder that is the same everywhere, with conflict handling that mostly does the right thing. Two decades on, the sync engine is still the part competitors struggle to match.
Collaborative whiteboard with a hand-drawn look
Excalidraw's sketchy rendering is not decoration. Diagrams that look provisional invite comment, where a crisp vector diagram signals a decision already made, so it is unusually good at the early part of a design conversation.
Inference engine that runs LLMs on almost any hardware
llama.cpp is the layer most local model tooling is built on. It is a C and C++ inference engine with no Python runtime, aggressive quantisation support, and hand-tuned kernels for a remarkably wide range of hardware.
Password and secret management for people and teams
1Password is the credential manager most often recommended to people who will not tolerate friction. The apps are good on every platform, sharing within a family or team is comprehensible, and the security model has held up under scrutiny.
OpenAI's assistant and the interface that set the pattern
ChatGPT is the product that made conversational assistants ordinary. Beyond the chat box it now covers file analysis, image generation, web browsing, voice, and custom assistants sharing one account.
Remote desktop you can point at your own relay server
RustDesk is remote desktop software where the relay server is a binary you can run yourself. That is the whole argument: the same convenience as the commercial tools, without your screen sessions transiting a vendor's infrastructure.
Catalogue music streaming with algorithmic discovery
Spotify's advantage is not the catalogue, which is broadly the same everywhere, but the recommendation layer on top of it. Discover Weekly and the radio features remain the reason many people stay.
Product analytics built around events and cohorts
Mixpanel answers behavioural questions rather than traffic ones: which sequence of actions precedes retention, where a funnel leaks, and how a cohort from March differs from one from June.
Infrastructure monitoring, logs, and tracing in one platform
Datadog's value is correlation. A latency spike on a dashboard, the traces behind it, and the logs from the affected hosts are one or two clicks apart, which is the difference between a ten minute incident and an hour.
Customer messaging combining chat, help centre, and bots
Intercom put support, onboarding, and product messaging into one thread per customer. The messenger in the corner of a product is close to a genre convention now, and Intercom largely defined it.
Self-hosted photo and video backup for your own server
Immich replaces a cloud photo service with software that runs on hardware you own. Mobile apps for iOS and Android back up new photos and videos in the background, so the library on your server stays current without you thinking about it.
Work management for teams that are not only engineers
Asana is aimed at the coordination work around delivery rather than at engineering tickets: campaigns, launches, onboarding, and the dependencies between them. Timeline and workload views are the parts teams adopt first.
Channel based team messaging with a large integration ecosystem
Slack replaced internal email for a generation of companies by making conversation searchable and public by default. Channels, threads, and a very large app directory are the shape most team chat now copies.
Free 2D and 3D game engine with no royalties
Godot ships a complete engine, editor, and export pipeline under the MIT licence, which means no royalties, no revenue thresholds, and no licensing conversation before a project starts.
Let AI agents drive a real browser
Browser Use gives an agent a real browser rather than an HTTP client. It handles the translation between a model's intent and DOM actions, keeps a structured representation of the page in context, and recovers from the usual navigation failures.
126 results