Tag
48 catalogue entries use this topic; each Project's license policy is labeled separately.
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.
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.
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.
Local-first smart home automation with no cloud dependency
Home Assistant runs on a box in your house and talks to devices directly rather than through their manufacturers' servers. That single design decision is why automations keep working when the internet is down, and why a discontinued cloud service does not brick your lights.
Autonomous agents that complete real engineering tasks
OpenHands runs agents that plan and execute multi-step engineering work: reading a repository, editing files, running tests, and iterating until a task is done. Each agent works inside a sandboxed runtime rather than on the host machine.
Open-source web crawler that turns pages into LLM-ready markdown
Crawl4AI is a Python crawler that turns websites into clean markdown and typed JSON for RAG pipelines, AI agents, and data pipelines.
Open-source investment research terminal with Python-first market data
OpenBB Terminal is an open-source financial terminal for market data, investment research, and analytics, now developed as the Open Data Platform.
Open-source memory layer for AI agents and apps
Mem0 is an open-source memory layer that gives AI agents and apps persistent memory across sessions, with self-hosted and managed platform options.
Open-source AI gateway unifying 100+ LLMs behind one API
LiteLLM is an open-source AI gateway that calls more than 100 large language model providers through one OpenAI-compatible interface.
Terminal pair-programming assistant that edits codebases with LLMs
Aider is a terminal-based pair-programming tool that applies LLM-suggested edits directly to files in new or existing codebases.
Open-source Python framework and runtime for building AI agent platforms
Agno is a Python framework and runtime for building agent platforms with memory, knowledge, and tool integrations.
React SDK and infrastructure for in-app AI copilots and agents
CopilotKit is an open-source framework for adding AI copilots, chatbots, and in-app agents to products.
Open-source LLM observability, evals, and prompt management
Langfuse is an open-source platform for tracing, evaluating, and improving LLM applications and AI agents, with prompt management and experiments built in.
Open-source vector database for AI search and retrieval
Chroma is an open-source vector database for AI retrieval, storing embeddings with metadata and serving vector, full-text, and regex search in one query.
Full-stack Python platform for building and deploying web apps
Reflex is a full-stack Python platform for building internal tools and customer-facing web apps, with an AI builder, open-source framework, and cloud or on-premises deploy.
Infrastructure as code in TypeScript, Python, Go, and .NET
Pulumi is an open source infrastructure-as-code platform for defining and managing cloud infrastructure with general-purpose programming languages.
Open-source platform for stateful AI agents with memory
Letta is an open-source platform for building stateful AI agents with persistent memory, background jobs, and multi-agent orchestration.
Open-source Python workflow orchestration for resilient data pipelines
Prefect is an open-source workflow orchestration framework that turns Python functions into resilient data pipelines with scheduling, retries, and event triggers.
Open-source headless commerce backend with a GraphQL API
Saleor is an open-source headless commerce backend with a GraphQL-only API and multi-channel catalog control, deployable with Docker or run as managed Cloud.
Open-source AI agents that complete workflows in a real browser
Skyvern is a self-hosted AI platform that completes browser workflows with vision models, with a Playwright-compatible SDK and a managed cloud option.
Open source coding agent that fixes GitHub issues with LLMs
SWE-agent is an open source coding agent that turns a GitHub issue into a tested fix by letting a language model use shell, editor, and search tools in a sandbox.
Open-source framework for building and running crypto trading bots
Hummingbot is a free open-source framework for building and running crypto trading bots, with a no-code dashboard and Python scripting for custom strategies.
A control layer for customer-facing AI agents
Parlant addresses the problem that stops most support agents from shipping: a model that is helpful ninety-five percent of the time is not safe to put in front of customers. It manages behaviour through explicit, context-matched guidelines rather than one long prompt.
Free and open-source machine translation API you can self-host.
LibreTranslate is a free, open-source machine translation API powered by Argos Translate that runs on your own server instead of a third-party cloud.
Open-source data quality tests and docs for pipelines
Great Expectations is an Apache-2.0 licensed Python framework for testing data quality with Expectations, Checkpoints, and auto-generated Data Docs.
Open-source tracing, evals, and prompt tools for LLM apps
Arize Phoenix is a self-hosted observability platform for LLM apps with tracing, evaluations, datasets, and a prompt playground.
Incremental data pipelines that keep AI indexes and RAG context fresh
CocoIndex is a Python framework for building incremental data pipelines that keep search indexes and RAG context in sync with changing sources.
Open-source billing platform and merchant of record for SaaS
Polar is an open-source billing platform and merchant of record for digital products and SaaS, combining usage billing, subscriptions, and global tax handling.
Disk cleaner that frees space and shreds leftover traces
BleachBit clears unneeded files from a Windows or Linux machine and wipes the traces left behind by browsers, installers, and everyday applications. One run covers cache, logs, temporary files, and cookies across thousands of supported programs.
No-code database and application builder you can host
Baserow is a spreadsheet-shaped database with the API and permission model of a real backend underneath. Non-technical colleagues get grid, gallery, kanban, and calendar views; engineers get a REST API and webhooks over the same data.
Open-source agent observability, evals, and AI governance
LangWatch is an open-source observability and evaluation platform for AI platform teams, covering LLM operations, coding-assistant usage, AI gateway routing, and AI governance in one place.
In-memory graph database for real-time analytics and AI
Memgraph is an in-memory graph database that runs Cypher queries and streaming analytics over live connected data for fraud detection, recommendations, and agent memory.
Free self-hosted digital signage for Raspberry Pi and PCs
Anthias is a free, self-hosted digital signage platform that turns a Raspberry Pi or PC into a display player for images, videos, and web pages.
Open-source helpdesk with ticketing, SLAs, and unlimited agents
Frappe Helpdesk is an open-source ticketing system that pulls email, form, and portal requests into one shared queue with SLA tracking and assignment rules.
Open-source tracing, evals, and observability for AI agents
Laminar is an open-source observability platform purpose-built for AI agents, with OpenTelemetry-native tracing, evaluations, and behavior monitoring built in.
Collaborative data notebook mixing Python, SQL, AI help, and live sharing
Deepnote is a collaborative data notebook that mixes Python, SQL, and chart blocks with live connections to warehouses and databases in one cloud workspace.
Federated book tracking and social reading without the ad platform
BookWyrm is a federated social reading platform: readers track what they are reading, write reviews, and follow friends across independently run instances.
Error tracking that speaks the Sentry protocol
GlitchTip accepts events from the official Sentry SDKs, which means adopting it is a DSN change rather than an instrumentation project. Stack traces, breadcrumbs, releases, and issue grouping all work as expected.
Self-hosted error tracking that works with Sentry SDKs
Bugsink is a self-hosted error tracker that collects exceptions from running apps and shows them in one place with stack traces and context.
Serverless GPUs with fast cold starts for AI workloads
Beam is a serverless GPU platform for running AI inference, sandboxes, and background jobs without managing infrastructure. Functions deploy from a Python decorator, and the platform keeps idle containers warm so repeat calls skip the cold start.
Self-hosted experiment tracking and observability for ML teams
mlop is a self-hosted platform for tracking, visualizing, and comparing machine learning experiments, with live training metrics, dataset versioning, and a web dashboard.
Ask questions across document sets and get cited answers
Corpus turns piles of PDFs and web pages into something a team can interrogate.
Run batch tasks on shared provider machines, or earn by sharing yours
Golem is a peer-to-peer network where requestors run batch tasks on machines shared by providers, paying per use in the GLM token. Tasks execute inside provider-hosted environments such as VM images, as a single task or as many parallel tasks spread across providers.
Open-source, OpenAI-compatible LLM gateway with cost and latency tracking
LLM Gateway is an open-source gateway that puts OpenAI, Anthropic, and Gemini calls behind one OpenAI-compatible API. An application keeps its existing OpenAI client and points it at the gateway, so switching providers or spreading load across them is a configuration change rather than a rewrite.