LibreChat screenshot thumbnail

LibreChat

Every major model provider behind one ChatGPT-style interface: LibreChat spans OpenAI, Anthropic, Google, Azure, AWS Bedrock, Vertex AI, Groq, Mistral, OpenRouter, DeepSeek, and any OpenAI-compatible endpoint including local Ollama. You can switch models mid-conversation and compare providers without changing tools. Its Agents framework builds no-code custom assistants with tool access via Model Context Protocol servers, file search over uploaded documents through an optional pgvector-backed RAG service, and a sandboxed Code Interpreter that executes Python, JavaScript, Go, C++, Java, PHP, and Rust. Artifacts render React components, HTML, and Mermaid diagrams directly in chat, and image generation works through DALL-E and other configured providers. Multi-user support is enterprise-grade, with OAuth, SAML, LDAP, and two-factor authentication, per-user conversation history in MongoDB, and Meilisearch-powered search across all messages and files, plus reusable presets, forkable threads, and persistent memory across conversations. The economics favor teams: instead of a ChatGPT Plus seat per person, everyone shares one instance billed per API token, with access to every provider rather than one - and providers see individual API calls, not your accumulated organizational knowledge. Deployment is Docker Compose; API keys and endpoints are configured through .env and librechat.yaml.

Deploy
n8n screenshot thumbnail

n8n

Webhooks, cron schedules, and app events trigger chains of nodes that fetch, transform, and route data: n8n is a workflow automation platform built around a visual, node-based editor. It ships with 400+ built-in integrations covering databases like Postgres, SaaS tools like Slack and HubSpot, and every major AI provider. When a pre-built node does not exist, the HTTP Request node calls any REST API, and the Code node runs JavaScript or Python inline, so you are never blocked by a missing connector. Workflows execute as directed graphs with branching, loops, error handling, and sub-workflows, and every run is logged for inspection and replay during debugging. It also includes LangChain-based nodes for building AI agents with tool calling and memory. Self-hosting on RepoCloud gives you unlimited workflow executions with no per-task pricing, and all data stays on your instance. Runs on Node.js with SQLite by default; add Postgres and Redis queue mode when you need to scale workers horizontally.

Deploy
Bolt.diy screenshot thumbnail

Bolt.diy

Prompt, run, edit, and deploy full-stack Node.js applications from a browser tab: Bolt.diy is the official open-source version of Bolt.new's AI coding agent. Its foundation is StackBlitz's WebContainer technology - a sandboxed in-browser Node.js environment where the AI controls the whole stack: filesystem, npm, dev servers, terminal, and browser console. That means the agent does not just generate code; it installs dependencies, runs Vite or Next.js, reads errors, and fixes them. The defining difference from Bolt.new is model choice per prompt: 19+ providers including OpenAI, Anthropic, Gemini, DeepSeek, Groq, Mistral, Amazon Bedrock, and local models via Ollama or LMStudio, extensible through the Vercel AI SDK. Development ergonomics include live preview, a diff view of AI changes, codebase search, file locking to prevent generation conflicts, 15+ starter templates (React, Vue, Next.js, Astro, Svelte, Expo), and MCP support for external tools. Projects integrate with Git and Supabase, and deploy in one click to Vercel, Netlify, or GitHub Pages.

Deploy
PocketBase screenshot thumbnail

PocketBase

An entire backend in a single Go executable: PocketBase embeds SQLite with realtime subscriptions, authentication and user management, file storage, and an admin dashboard, all behind a REST-ish API. SQLite runs in WAL mode, which outperforms client-server databases for the read-heavy workloads typical of small and mid-sized apps. Authentication supports email/password, one-time passwords, and 15+ OAuth2 providers including Google, Apple, and GitHub, with stateless tokens. Clients subscribe to record changes over server-sent events, and official JavaScript and Dart SDKs cover web, mobile, and Flutter frontends. Collections, rules, and API access permissions are managed visually in the admin UI. When you need custom logic, extend it with JavaScript hooks running in the embedded JS VM of the prebuilt binary, or import PocketBase as a Go library and compile custom business logic into your own single-file backend. File storage attaches uploads to records with thumbnail generation for images and optional S3-compatible external storage. All state lives in one pb_data directory, so backup is a directory copy and upgrade is replacing a binary - one of the lowest-maintenance backends you can run. The contrast with Firebase is the point: where usage-based pricing scales with reads, writes, and bandwidth, PocketBase runs the entire backend at flat hosting cost, and the data is a plain SQLite file you can copy anywhere. MIT-licensed.

Deploy
Teable screenshot thumbnail

Teable

An Airtable-style spreadsheet interface directly on PostgreSQL: Teable is an open-source no-code database where every table is a real Postgres table. Unlike tools that store records in a metadata abstraction layer, every Teable table is a real Postgres table with standard column types, so filtering, sorting, and grouping run at database speed, million-row tables answer complex filters in roughly 200 milliseconds without index tuning, and any PostgreSQL-compatible tool - psql, BI dashboards, ETL pipelines - can query the same data directly. The interface offers Grid, Kanban, Gallery, Calendar, and Form views as non-destructive overlays with their own filters and hidden fields, plus 20+ field types, formulas, comments, attachments, batch editing, undo/redo, and edit history. Collaboration is real-time with live cursors and instant sync across views, backed by Redis, and a REST API is auto-generated per table, largely compatible with Airtable API clients - alongside native SQL access for BI tools, analytics pipelines, and your own applications to JOIN and query directly, with no exports, API rate limits, or sync jobs. Global search spans all records, chart plugins handle quick visualization, and CSV and Excel import/export cover migrations. Where Airtable caps paid plans at 100K-500K rows and charges roughly $20 per user per month, a self-hosted Teable instance has neither limit: the Postgres database itself is the export if you ever leave. Built in TypeScript with NestJS, deployed via Docker with PostgreSQL and Redis, and licensed AGPL-3.0.

Deploy
AutoGen Studio screenshot thumbnail

AutoGen Studio

Prototype multi-agent AI systems without writing orchestration code: AutoGen Studio is Microsoft's low-code interface over the AutoGen AgentChat framework. You compose teams of LLM-powered agents in a visual Team Builder, either by drag-and-drop from a component library or by editing the declarative JSON specification directly. Each agent gets a model, a prompt, tools (Python functions), and the team gets termination conditions and an orchestration pattern, sequential or LLM-driven. The Playground runs teams interactively with live message streaming between agents, a visual control-transition graph, tool-call and code-execution tracking, and pause/stop controls, which makes it a practical debugger for agent behavior. Finished teams export as JSON for use in any Python application via the TeamManager class, or serve as an API endpoint. Any OpenAI-compatible model endpoint works, including local servers like Ollama or vLLM. Microsoft labels it a research prototype: use it for prototyping and evaluation, and build production systems on the underlying AutoGen framework.

Deploy
Flowise screenshot thumbnail

Flowise

Drag nodes onto a canvas and ship an LLM app: Flowise is an open-source visual builder for AI agents and LLM applications, written in Node.js on LangChain.js and licensed Apache-2.0. You assemble flows by dragging nodes onto a canvas: models, prompts, memory, vector stores, retrievers, and tools, then wire them together and test in the built-in chat panel. Three builder types cover increasing complexity: Assistant for simple RAG chat over uploaded files, Chatflow for single-agent systems with techniques like rerankers and Graph RAG, and Agentflow for multi-agent orchestration with branching, looping, shared flow state, and human-in-the-loop checkpoints. Over 100 integrations connect data sources, vector databases, and both proprietary and open-source models, plus MCP client and server nodes for standard tool interop. Finished flows are exposed as REST APIs, embedded chat widgets, or via JS and Python SDKs - each flow gets an endpoint the moment it is saved, removing the deployment gap between a working prototype and something your application can call. Execution logs, visual step debugging, and external log streaming trace behavior, while input moderation and rate limiting act as guardrails; RBAC, SSO, and workspaces cover team deployments. Self-hosting keeps prompts, encrypted credentials, and conversation data on your own instance, which matters when flows handle internal documents or customer data - and wiring a model, prompt, memory, and vector store on the canvas replaces the boilerplate a hand-coded LangChain project would need.

Deploy
GPT Researcher screenshot thumbnail

GPT Researcher

A question goes in; a cited, long-form report comes out - GPT Researcher is an open-source autonomous research agent. A planner agent decomposes the query into sub-questions, execution agents crawl 20+ web sources in parallel with JavaScript-enabled scraping, and a publisher aggregates findings into a 2,000+ word report with inline citations, exportable to PDF, Word, and Markdown. The Deep Research mode extends this recursively: each result yields follow-up questions that are explored to configurable breadth and depth in a tree pattern, while accumulated learnings, citations, and visited URLs are shared across branches. It also researches local documents (PDF, CSV, Word) alongside the web. LLM and search providers are pluggable, including OpenAI, Anthropic, Google, DeepSeek, and Ollama for models, and Tavily, Google, Bing, DuckDuckGo, and SearXNG for retrieval. It ships as a Python package, a FastAPI server with web frontend, a Docker image, and an MCP server for use inside Claude or Cursor. MIT-licensed.

Deploy
Dokploy screenshot thumbnail

Dokploy

Your own Heroku or Vercel on a single server - Dokploy is the open-source, self-hosted Platform-as-a-Service that makes the swap. You point it at a Git repository or a Docker image, and it builds and deploys the application using Dockerfiles, Nixpacks, or Heroku/Paketo buildpacks. Traefik is integrated as the reverse proxy, handling routing, load balancing, automatic Let's Encrypt SSL certificates, and HTTP/3. It also provisions and manages databases (MySQL, PostgreSQL, MongoDB, MariaDB, Redis) with automated backups to external storage. Complex multi-service applications deploy through native Docker Compose support, and multi-node scaling uses Docker Swarm. The web UI covers environment variables, volumes, resource limits, real-time CPU/memory/network monitoring, and deployment logs, with a CLI and API for automation. Deployment notifications go to Slack, Discord, Telegram, or email. One-click templates install common open-source tools, and a single Dokploy control plane can manage deployments across multiple remote servers. Because everything is standard Docker under the hood, there is no lock-in: your Dockerfiles, Compose files, and data volumes work anywhere else Docker runs. You get the Heroku-style push-to-deploy workflow without operating a Kubernetes cluster, and the total cost is the server it runs on - no per-app, per-environment, or per-seat platform fees regardless of how many applications you deploy.

Deploy
Coolify screenshot thumbnail

Coolify

Any SSH-accessible Linux box - VPS, bare metal, Raspberry Pi, EC2 - becomes a Heroku-like deployment environment under Coolify, an open-source, self-hostable platform-as-a-service. Connect a GitHub, GitLab, Bitbucket, or Gitea repository and every push builds and deploys automatically via Nixpacks, a Dockerfile, or Docker Compose, with Traefik reverse proxying, automatic Let's Encrypt certificates, and per-branch preview deployments with their own URLs. Databases - PostgreSQL, MySQL, MariaDB, MongoDB, Redis - provision in a few clicks, and a catalog of 280+ one-click service templates covers WordPress, n8n, Grafana, MinIO, Plausible, and more, replacing an afternoon of Compose YAML with a two-minute operation. One dashboard manages multiple servers, with Docker Swarm available for clustering. Backups go to any S3-compatible storage with one-click restore, a browser terminal gives real-time server access, and a full API supports CI/CD integration. All configuration lives on your own servers, so resources keep running even without Coolify. Apache 2.0 licensed.

Deploy
Authorizer screenshot thumbnail

Authorizer

Your users belong in your own database - Authorizer, an open-source authentication and authorization server shipping as a single Go binary, keeps them there. It connects to 13+ backends - PostgreSQL, MySQL, SQLite, SQL Server, MariaDB, MongoDB, Cassandra, ScyllaDB, ArangoDB, DynamoDB, Couchbase, YugabyteDB, PlanetScale, and CockroachDB - so identity data lives beside the application it protects instead of in an auth vendor's cloud. The server is fully OAuth 2.0 and OpenID Connect compliant, including authorization code flow with PKCE, a JWKS endpoint, token revocation, and nine JWT signing algorithms. Login options cover email/password, magic links, TOTP multi-factor, SMS OTP via Twilio, and social providers including Google, GitHub, Apple, Microsoft, and Discord. Authorization goes beyond roles: an embedded OpenFGA engine provides Zanzibar-style relationship-based permission checks in process. APIs are exposed over GraphQL, REST, and gRPC, with SDKs for JavaScript, React, Go, and Python, plus themeable built-in login pages and an admin dashboard. Apache 2.0 licensed.

Deploy
Nocobase screenshot thumbnail

Nocobase

CRMs, project trackers, inventory tools - NocoBase is an open-source no-code/low-code platform for building business systems like these. Its architecture is data-model driven: you define collections and relationships first, then compose any number of interface blocks (tables, forms, kanban, charts) on top of the same model, so data structure is never coupled to a particular view. The core is a microkernel where every feature is a plugin, WordPress-style; you enable official plugins, install marketplace ones, or write your own as npm packages with server and client parts. Data sources include the main PostgreSQL or MySQL database, external databases, and third-party APIs - so you can build admin panels over existing production data instead of migrating it. Built-in infrastructure covers role-based permissions down to collection, record, and field level, workflow automation with approval steps and scheduled triggers, and audit logs; a one-click switch flips between usage and configuration modes. Because custom features live in isolated plugins with a documented lifecycle, core upgrades do not overwrite your customizations, and swapping UIs never requires data migrations since interfaces sit on independent models. Written in TypeScript on Node.js, Koa, and React under the AGPL license, it is light enough for one person to run and extend - and where no-code SaaS platforms charge per seat and per app, a self-hosted instance runs unlimited applications for unlimited users at hosting cost alone.

Deploy
OpenUI screenshot thumbnail

OpenUI

Describe a component in natural language and watch it render: OpenUI, from Weights & Biases, is an open alternative to Vercel's v0. Type a prompt like "a dark-themed dashboard with a sidebar and charts" and the LLM renders working HTML with Tailwind styling live in the browser. You then iterate conversationally, asking for changes until the design is right, and convert the result to React, Svelte, or Web Components for use in a real project. The backend is Python with LiteLLM routing, so it works with OpenAI, Anthropic, Gemini, Groq, and Mistral API keys, or fully offline against local Ollama models, including vision models like LLaVA that can generate UI from screenshot input - feed a screenshot and the model reproduces or riffs on an existing interface. Generated markup is inspectable at any point, with light and dark mode toggles, theme selection, and responsive previews across device sizes. The practical effect is compressing the mockup-review-revise loop from hours to minutes: a described layout renders in seconds and iterates through follow-up prompts, and because output converts to real framework code, prototypes feed directly into production codebases instead of staying trapped in a design tool. Self-hosting keeps unreleased product interfaces and prompts on your own server, and LiteLLM routing lets you pick the model per task - a cheap fast model for rough drafts, a stronger one for final passes, or free local models for unlimited experimentation.

Deploy
Kestra screenshot thumbnail

Kestra

Data, AI, and infrastructure workflows, orchestrated from declarative YAML: Kestra is an open-source, event-driven orchestration platform. Flows are declared in YAML - no DSL rewrites or Python decorators - and the definition stays the single source of truth even when edited through the UI, API, CI/CD, or Terraform, which makes pull-request review, versioning, and rollback natural. Tasks run in any language: Python, Node.js, Go, Rust, R, SQL, or Bash scripts executed in containers, and a plugin ecosystem of 1,000+ integrations covers ingestion, dbt, Airbyte, Spark, cloud storage, databases, and messaging systems. Scheduling supports cron triggers, event triggers, backfills, and conditional branching, with retries, timeouts, error handling, and typed inputs and outputs that surface artifacts in the UI. Namespaces, labels, and subflows organize workflows at scale, and the embedded code editor includes Git integration. Common uses span ETL/ELT pipelines, dbt runs, microservice coordination, infrastructure provisioning, and human-in-the-loop approvals. Java-based, Apache 2.0 licensed, deployed via Docker or Kubernetes.

Deploy
ToolJet screenshot thumbnail

ToolJet

Retool's job, self-hosted: ToolJet is an open-source low-code platform for building internal tools, dashboards, and admin panels. Apps are assembled in a drag-and-drop visual builder with 60+ responsive components, including tables, charts, forms, and lists, and connected to 80+ data sources: PostgreSQL, MySQL, MongoDB, REST and GraphQL APIs, cloud storage, and common SaaS tools. When visual configuration is not enough, you can run JavaScript or Python inline for queries and transformations. A built-in no-code database (ToolJet Database) covers apps that need their own tables without provisioning an external database, Workflows add node-based automation for background jobs with dedicated worker containers and a Redis-backed queue, and multi-page apps with multiplayer editing, inline comments, and mentions support team development. Security is designed for internal data: credentials are AES-256-GCM encrypted, data flows proxy-only through your server so database contents never reach a third-party cloud, and granular per-app access control plus SSO gate each tool. Where Retool-style platforms bill per builder and sometimes per end user, the self-hosted Community Edition serves unlimited builders and users at hosting cost, and full source availability means the platform itself can be forked, audited, and extended. The stack is Node.js and React on PostgreSQL, deployed via Docker.

Deploy
Morphic screenshot thumbnail

Morphic

Perplexity's answer-engine experience, self-hostable and open-source: Morphic searches the web and writes cited answers. Instead of returning a list of links, it searches the web, reads the sources, and generates a complete answer with inline numbered citations. The generative UI streams rich components, source cards with thumbnails, image grids, syntax-highlighted code, and LaTeX math, rather than plain markdown. Quick mode answers fast; Adaptive mode runs deeper multi-step research. Search backends are pluggable: the Docker Compose bundle ships with a private SearXNG instance so no search API key is required, and Tavily, Brave, and Exa are supported alternatives. LLM providers include OpenAI, Anthropic, Google, Ollama, and any OpenAI-compatible endpoint, with per-mode model mapping - fast, cheap models for quick searches, stronger models for adaptive research, tuning the cost-quality trade-off per query type. An inspector panel exposes tool execution during multi-step research, and AI-suggested follow-up questions keep an investigation moving. Chat history persists in PostgreSQL, results are shareable by URL, file uploads feed context into queries, and optional Supabase authentication adds multi-user or guest access. Because the default search path is your private SearXNG instance, research topics never hit a commercial search API - and with local Ollama models the marginal cost of a query approaches zero. Built with Next.js, TypeScript, and the Vercel AI SDK under Apache 2.0.

Deploy
Activepieces screenshot thumbnail

Activepieces

Zapier's job, on your own server: Activepieces is an open-source workflow automation platform built to be exactly that replacement. Flows are built in a visual no-code editor with triggers, actions, loops, conditional branches, auto-retries, raw HTTP steps, and code steps that run JavaScript or TypeScript with full npm package support. Integrations are "pieces" - type-safe TypeScript npm packages with hot reloading for local development - and the catalog spans 600+ services, with the large majority contributed by the community. The platform is AI-first in two directions: native AI pieces call OpenAI, Anthropic, Google, and Azure models inside flows, and every piece automatically doubles as an MCP server, so assistants like Claude Desktop and Cursor can invoke your integrations and workflows through natural language. A built-in MCP server also exposes 30 tools for building flows, managing tables, and running tests agentically. Flows are fully versioned with draft and locked states. The core is MIT-licensed and runs on TypeScript with PostgreSQL and Redis.

Deploy
Tianji screenshot thumbnail

Tianji

Website analytics, uptime monitoring, and server status - three tools most teams run separately - combined in Tianji, an open-source observability platform. The analytics layer tracks page views, unique visitors, referrers, and UTM parameters with a lightweight cookie-less script, which keeps collection GDPR and CCPA friendly. The uptime monitor checks availability and latency on configurable intervals, accepts passively reported results, and publishes public status pages for incident communication. Server status agents report CPU, memory, disk, and network metrics with threshold-based alerts, and notifications route through webhooks, Slack, Telegram, and other channels with noise control. It also includes anonymous telemetry for tracking deployments of your own open-source projects, surveys, waitlists, team collaboration, and an OpenAPI interface for integrations and exports. The consolidation is the point: traffic analytics, uptime checks, and server metrics share one interface and one alerting layer, so diagnosing an incident does not mean hopping between Google Analytics, Uptime Kuma, and Prometheus - and the built-in public status pages replace a separate paid Statuspage-style subscription. Because collection uses no cookies with IP truncation and aggregation by default, basic traffic measurement requires no consent banner. Built in TypeScript under the Apache 2.0 license and inspired by Umami and Uptime Kuma, it is deliberately right-sized for independent developers and small SaaS teams whose monitoring needs are real but lightweight.

Deploy