QM is Y Combinator's internal multiplayer agent infrastructure that shifts AI agents from personal assistants to shared company operating layer. The headless TypeScript core runs on Node.js with Fastify handling HTTP, Slack integration via Bolt, and a web UI built with Vite and Lit. PostgreSQL stores sessions, memory, queue state, and audit logs. Every person and every Slack channel gets an isolated sandbox with its own durable file system, installed tools that persist across runs, private memory, keychain view, permissions, and background crons. The harness-agnostic architecture routes agent tasks through Pi, OpenCode, Codex, or Claude Code without vendor lock-in, with production implementations swapping via a single wiring file. Three org-level security postures gate execution: Strict requires human approval for every tool call, Auto applies automated content screening, and Dangerous removes all pauses. Skills are scope-owned and shareable by grant, with admin-gated promotion to the entire organization and skill packs importable from Git repositories. The web apps feature lets agents spin up custom internal applications published to specific users. The qm CLI bootstraps operator-owned deployment directories with digest-pinned release images, infrastructure rendering, secret management, and live verification checks for Docker, Fly.io, or AWS ECS Fargate targets. On RepoCloud, deploy QM on a dedicated VPS with PostgreSQL persistence, Docker socket access, root SSH access, and complete control over your multiplayer agent infrastructure, all under the MIT license.

With 83,000+ GitHub stars and $18.8M in Series A funding, OpenHands delivers the leading open-source platform for AI coding agents that scored 68.4% on SWE-bench Verified with Claude Opus 4.6, outperforming Devin 2.0's publicly reported 45.8%. The Agent Canvas web UI organizes work into persistent conversations where agents edit files, run shell commands, browse the web, and execute multi-step development tasks inside isolated Docker sandbox containers. The observe-plan-act loop drives agent behavior: the Python controller manages LLM abstraction via LiteLLM routing to 100+ providers including OpenAI, Anthropic, Google, DeepSeek, Qwen, Llama, and local Ollama models. Built-in skills for code review, Docker management, PRD generation, repo-rules enforcement, release notes, and test running attach to conversations automatically via auto-discovery or trigger-based activation. The Automations system schedules recurring agent tasks with configurable templates for CI workflows, dependency updates, and documentation generation. MCP server integration enables agents to access external tools and data sources. The REST API powers an OpenAI-compatible endpoint for connecting agents to chat UIs, IDEs, and voice platforms. GitHub, GitLab, Slack, and Jira integrations enable pull request reviews, issue resolution, and team notifications. The SDK provides Python and REST APIs for embedding agents in custom tools with local or cloud execution, custom agent behaviors, and Kubernetes deployment. On RepoCloud, deploy OpenHands on a dedicated VPS with Docker socket access, persistent project storage, root SSH access, and complete control over your AI development infrastructure, all under the MIT license.

OpenRouter's most-used application by token volume — over 17 trillion tokens processed — Hermes Agent is an open-source autonomous agent built by Nous Research that lives on your server and gets more capable every day. Define a goal in natural language and Hermes plans sub-tasks, executes them through tool integrations, observes results, handles errors, and refines until the job is done or it genuinely needs your input. Persistent memory with full-text search and LLM summarization lets it recall context across sessions, and an agent-created skills system self-improves after complex tasks. A messaging gateway connects Telegram, Discord, Slack, WhatsApp, Signal, and 16 more platforms with cross-channel conversation continuity. A built-in cron scheduler runs daily reports, nightly backups, and weekly audits unattended. Subagent spawning parallelizes workstreams, and six terminal backends — local, Docker, SSH, Singularity, Modal, and Daytona — fit any infrastructure. Works with any LLM provider: Nous Portal, OpenRouter for 400+ models from 70+ providers, OpenAI, Anthropic, or your own endpoint. The API key you supply powers all LLM calls; billing goes through your own account. Running on a dedicated VPS with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

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.

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.

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.

DeepSeek Harness gained over 60,000 GitHub stars within hours of its August 2026 launch, establishing itself as the first fully modular open-source agent runtime where literally every component is a swappable plugin. Built on the Cordis framework—a programming paradigm for spatiotemporal composability—dsh decomposes the entire agent stack into independently replaceable pieces: model adapters for DeepSeek, Anthropic, OpenAI, AWS Bedrock, Azure, and Google Gemini; tool registries covering bash execution, file system operations, web search, subagent delegation, and todo management; plus session stores, sandboxes, approval policies, orchestration loops, and the user interface itself. Four operating modes serve different workflows: Standard provides the full toolset, Code mode uses model-generated code to compose multi-round tool calls, Minimal strips down to a shell and editor for benchmarking, and Creator mode lets developers inspect the running runtime and test Cordis plugins in memory. The kernel handles plugin mounting, unmounting, and dependency resolution while typed events and services coordinate between components. Profiles and bundles allow the same codebase to produce entirely different products—a terminal coding agent, a browser-based workspace, a headless automation service, or an ACP/JSON-RPC endpoint—by swapping YAML configuration layers. Session history is stored as an append-only event stream for full trajectory replay, and project-level hooks on agent lifecycle events enable fine-grained behavioral customization. MCP client integration connects to external tool servers, while Agent Client Protocol enables programmatic orchestration. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Buzz delivers the first production workspace where humans and AI agents operate as cryptographically equal team members on a self-hosted Nostr relay. The Rust-based backend stores every message, code patch, CI result, review comment, and workflow step as a signed Nostr event in a unified PostgreSQL-backed event log with Redis pub/sub for real-time presence and S3/MinIO for media storage. The integrated Git forge implements NIP-34, turning feature branches into dedicated channels where patches, reviews, and merge decisions live alongside the discussion that produced them — eliminating the split between chat tools and code hosts. Through the open Agent Client Protocol, Buzz natively supports Goose, Anthropic Claude Code, and OpenAI Codex as first-class channel members with scoped permissions, their own audit trails, and the ability to create patches, run workflows, and orchestrate multi-step automations via YAML-defined triggers including message events, reactions, schedules, and webhooks. The Tauri-based desktop client runs on macOS, Windows, and Linux, while buzz-cli provides agent-first JSON I/O for headless automation. Deploy via Docker Compose with the production bundle in deploy/compose/, Railway one-click, or build from source requiring Rust 1.88+, Node 24+, and pnpm. Multi-community mode scopes tenant data by domain with NIP-42 Schnorr authentication, rate limiting, and hash-chain audit logging. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache 2.0 licensed.

Open source GrokBot, built by the team behind the AG-UI protocol. OpenBot is the open-source enterprise agent platform that gives every AI coworker its own sandboxed computer — a real Chromium browser with its own login sessions, a private filesystem, and only the MCP tools you explicitly grant. The centralized gateway evaluates CEL policy rules against tool name, intent, bot identity, page URL, element attributes, and file paths before any action executes, writing an immutable audit row for every call and outcome. Any agent that speaks AG-UI — LangGraph, Mastra, CrewAI, Pydantic AI, Google ADK, or hand-written endpoints — registers as a Bot and receives its own channel with persistent conversation history. The take-the-wheel system lets humans assume control when an agent encounters login walls or two-factor prompts, recording control transfers as structured audit events. Knowledge documents from Google Drive and OneDrive carry source-based permissions where deny principals always win and ambiguous mappings refuse retrieval entirely. The React and Vite frontend provides live screen viewing of each agent's browser, channel-based chat, admin settings, and component galleries. The Hono API server on port 3001 handles authentication, role-based access, tenant packaging, and credential management backed by PostgreSQL with pgvector. Deploy via Docker Compose with the included supervisor that manages per-bot computer containers. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

With over 14,000 GitHub stars and 41 releases since its May 2026 launch, Prime Agent delivers a fundamentally different approach to AI coding agents by treating the agent's own operating environment as programmable state that improves through use. The Recursive Language Model architecture provides the model exactly one tool — a persistent IPython kernel — where file operations, shell commands, subagent delegation via rlm() function calls, and context management all happen through code rather than rigid tool-calling schemas. Subagents launch as independent sessions with their own model, kernel, and history, communicating results through agent_message.send() without blocking the parent. The Continual Harness stores supplemental prompts, memories, skill descriptions, and reusable subagent specifications as durable state that the /refine command updates through small, evidence-backed edits with full rollback by ID. Daemon-backed sessions keep running when the terminal disconnects, with automatic context compaction summarizing older messages while preserving recent state. The TUI provides an Agent View for monitoring, switching between, and steering multiple live sessions simultaneously. Autonomous mode operates within configurable turn, token, and time budgets with user-defined quality gates. Persistent goals, heartbeats, and scheduled prompts maintain continuity across terminal sessions. Compatible with Anthropic Claude, OpenAI, Google Gemini, local models via Ollama or vLLM, and Prime Inference endpoints. Install via a single curl command on Linux or macOS. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Open Lovable from the Firecrawl team delivers the first truly open-source alternative to Lovable.dev — a chat-driven AI copilot that takes any website URL and regenerates it as a complete, editable React application with TypeScript and Tailwind CSS in seconds. The pipeline combines Firecrawl's intelligent web scraping for JavaScript-rendered pages and single-page applications with your choice of AI provider — Claude, GPT-4, Google Gemini, or Groq — to analyze HTML structure, extract layouts and styling, decompose pages into proper React components, and generate production-ready code following modern best practices. Live preview runs in a secure sandbox environment using Vercel Sandbox with OIDC authentication or E2B Cloud, letting you see results immediately and iterate through natural language chat to request changes like Tailwind migration, componentization, SEO improvements, accessibility fixes, or custom form implementations. The optional Morph LLM fast-apply path accelerates small edits by applying diffs directly without full regeneration. The provider-agnostic architecture means you control costs by routing to different models — use Groq for fast iterations and Claude for complex layouts. Project structure follows Next.js conventions with organized app, components, atoms, styles, utils, and hooks directories. Deploy via pnpm with Node.js 18+ requiring only a Firecrawl API key, one AI provider key, and a sandbox provider configuration. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

The most widely deployed open-source BI tool, Metabase is a visualization and query layer that sits on top of your existing databases without ingesting or copying data. Non-technical users ask questions through a visual query builder with drill-through menus that answer follow-ups like "broken down by month" without writing a new query, while analysts use the native SQL editor with variables and templates for complex work. Questions assemble into interactive dashboards with filters, auto-refresh, fullscreen mode, and custom click behavior, and dashboard subscriptions email or Slack scheduled reports to stakeholders. It connects to 20+ data sources including PostgreSQL, MySQL, MongoDB, SQL Server, BigQuery, Snowflake, Redshift, and ClickHouse - always querying in place, so there is no second data store to secure, sync, or pay for, and results are always current. Models and metrics let a data team define official, reusable starting points so self-service stays consistent, collections with permissions organize content, and alerts fire when a metric crosses a threshold. The practical effect is cutting the ad-hoc query queue that lands on the data team, since non-technical staff can answer their own questions. Written in Clojure, licensed AGPL, and shipped as a single JAR or Docker image with an embedded application database - a working BI instance runs before most tools finish their installer - the open-source edition has no limits on users, dashboards, or connected databases, where commercial BI platforms price per viewer as well as per creator.

Formerly known as Danswer and now backed by over 31,000 GitHub stars with 253 releases, Onyx delivers a production-ready AI platform that turns any LLM into a context-aware enterprise assistant connected to your organization's actual knowledge. The agentic RAG pipeline combines BM-25 keyword search with prefix-aware embedding models in a hybrid index, then deploys AI agents to retrieve, verify, and synthesize answers with source citations from over 40 connected workplace tools including Google Drive, Confluence, Slack, Notion, Jira, SharePoint, GitHub, and Linear. Custom AI assistants with configurable prompts, backing knowledge sets, and document-level access control enable specialized agents for engineering, sales, support, and research workflows. The platform supports every major LLM provider — Anthropic Claude, OpenAI, Google Gemini, plus self-hosted options via Ollama, LiteLLM, and vLLM for fully air-gapped deployments. Beyond chat, Onyx provides web search with Serper, Google PSE, Brave, and SearXNG integration, an in-house web crawler, code execution, file creation, and multi-step deep research with report generation. Enterprise features include SSO via Google OAuth, OIDC, or SAML with SCIM provisioning, role-based access control, usage analytics by team and agent, query history auditing, PII removal through custom code hooks, and full whitelabeling. Deploy via Docker Compose on any infrastructure. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed (Community Edition).

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.

The most comprehensive open-source control plane for Hermes Agent — a full workspace combining AI chat, visual workflows, multi-agent orchestration, coding agent management, and platform channel integration in one self-hosted dashboard. Real-time chat streaming over Socket.IO connects to any OpenAI-compatible backend including Ollama, OpenAI, Anthropic, and custom endpoints with multi-session management, tool call expansion, inline file previews for HTML, PDF, DOCX, images, and source code, plus profile-scoped uploads and workspace attachments. The visual workflow builder provides a Vue Flow canvas for constructing DAG-structured pipelines with directed edges, conditional routes, approval gates, loops, and live execution with per-node status updates. Platform channel integration configures Telegram, Discord, Slack, WhatsApp, Matrix, Feishu, DingTalk, QQBot, WeChat, and WeCom bots from one page with credential management and per-platform behavior settings. Multi-agent group chat rooms enable real-time messaging with @mention routing, automatic context compression, and SQLite message persistence. The coding agent panel installs, launches, and monitors Claude Code and Codex with built-in terminal, session history, and file diffs. Usage analytics track token consumption, estimated costs, cache hit rates, and 30-day daily trends with model distribution charts. Kanban boards plan and track agent work alongside cron job scheduling for recurring tasks. Deploy via Docker, npm CLI, or desktop installer for Windows, macOS, and Linux. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

The leading open-source headless CMS with over 72,800 GitHub stars and more than 20 million npm downloads, Strapi has powered content APIs for thousands of organizations since its creation in 2015, providing a complete backend for websites, mobile applications, IoT devices, and any frontend framework through auto-generated REST and GraphQL endpoints. The visual Content-Type Builder lets editors define collections, single types, components, dynamic zones, and relations without code, while Strapi AI introduced in 2026 generates complete content schemas from natural language descriptions, Figma file uploads, or existing JavaScript application code analysis. Version 5 rewrote the platform with a TypeScript-first architecture, replacing the Entity Service with the Document Service API, switching admin panel builds from Webpack to Vite, and integrating internationalization directly into core with unlimited locale support. Database flexibility spans PostgreSQL, MySQL, MariaDB, and SQLite with automatic migration handling. The media library manages uploads to local storage, Amazon S3, or Cloudinary with image optimization and responsive formats. Granular role-based access control defines permissions per content type, field, and locale. The plugin marketplace extends functionality with GraphQL, SEO, email, custom fields, and community contributions, while lifecycle hooks, custom controllers, and middleware enable arbitrary backend logic. Draft and publish workflows, webhooks for external system integration, API token authentication, data import and export, and CRON job scheduling round out a platform that handles content operations from prototype to production. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Puter delivers a complete cloud operating system that runs entirely in the browser — turning any device with internet access into a full-featured personal computer with desktop environment, file management, application hosting, and developer platform. The familiar desktop interface presents windows, taskbar, right-click menus, drag-and-drop, and multi-window management indistinguishable from native operating systems. The hierarchical filesystem supports file creation, uploads, sharing, permissions, and trash recovery with storage backends ranging from local SQLite for self-hosting to S3 and DynamoDB for production scale. Built-in AI integration provides access to GPT-4, Claude, and other models directly from the desktop for text generation, code assistance, and image creation. The developer platform offers a JavaScript SDK, REST APIs, cloud storage, key-value database, and serverless workers for building and hosting web applications without managing infrastructure. Sandboxed applications run in iframes with IPC communication and permission-based access to filesystem, AI, and system services. The app store enables publishing, discovering, and monetizing applications built on the Puter platform. Website hosting publishes static sites with custom domains directly from the file manager. Multi-user support provides individual accounts with authentication, resource isolation, and sharing capabilities. Deploy via Docker with a single command, Docker Compose for production, or npm for development — the one-line install script handles everything automatically on Linux, macOS, and Windows. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. AGPL-3.0 licensed.

With over 2,100 GitHub stars in its first month and benchmarked at 30-75% lower cost than Claude Managed Agents on enterprise task suites, TrueForge is the open-source agent harness that provides the complete runtime layer for turning any LLM into a working production agent on your own infrastructure. The TypeScript server runs the full execution loop — streaming every step, routing tool calls through MCP servers with centralized header-auth and in-chat OAuth, delegating parallelizable work to isolated subagents, and pausing for human approval on sensitive actions. Context engineering keeps token costs low: deferred tool-schema loading delays MCP schemas until invoked, large-result offloading moves oversized outputs to files, Code Mode processes structured data through sandboxed execution, and automatic compaction summarizes older history at a configurable 50,000-token threshold while preserving the full transcript. The sandbox-as-a-tool architecture provisions isolated Daytona environments only when code execution is required, allowing one server to run many concurrent agents without idle overhead. Agents are configured from shipped YAML catalogs of models, MCP servers, git-backed SKILL.md instruction packs, and sandbox providers, then saved to an Agents Library accessible via the chat UI, TypeScript SDK, or embeddable React UI SDK. Run locally with SQLite via a single npx command, or deploy for teams with Docker Compose or Helm using Postgres and Redis with OIDC authentication. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.