Some questions are really about how things connect, and Neo4j is the graph database that stores your data as nodes and relationships so those connections become the thing you query. Model people, products, accounts, devices, or transactions as labeled nodes with properties, then draw typed, directed relationships between them and traverse multi-hop paths in a single Cypher query instead of stacking SQL joins. The built-in Neo4j Browser renders query results as interactive node diagrams, so you can expand a fraud ring, a dependency chain, or a recommendation neighborhood visually and share the picture with your team. Cypher reads like the picture it queries: MATCH patterns describe shapes in the graph, filters narrow them, and aggregations roll up counts, sums, and shortest paths. Store embeddings as node properties and build vector indexes over them, then combine similarity search with graph traversal so matches can be filtered by owner, connections, or freshness. Full-text indexes search names, descriptions, and documents, while uniqueness constraints keep identifiers honest at write time. Bulk-load millions of nodes from CSV files with the offline import tool, then keep data flowing in through official drivers for Python, JavaScript, Java, Go, and .NET applications. Fraud teams trace shared phones and cards between accounts, platform teams map microservice dependencies before a migration, and security analysts hunt lateral movement through identity graphs. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. GPL-3.0 licensed.

One admin platform can cover the back office of a whole company, from approvals and inventory to customers, projects, and devices. RuoYi-Vue-Pro, also called Yudao, wraps a long list of business modules around a shared system core, so teams switch on only the pieces they need. The core handles tenants, tenant packages, menus, roles, departments, SMS and email channels, audit logs, and OAuth2 single sign-on for connected apps. A workflow module offers a BPMN designer and a simplified DingTalk and Feishu style designer for approval flows. Business modules add ERP, WMS inbound and outbound documents, CRM, MES production dashboards, an HR workbench, finance vouchers, project work items, and an OA workspace with attendance, notices, and notes. More modules cover a shop and member center, payments, WeChat official accounts, AI model chat, IoT product and device management, and instant messaging with groups, shared cards, and voice calls. A code generator turns database tables into CRUD pages and back-end code, and file storage can point to local disk or S3-compatible services. Public demo sites allow a full click-through before installing anything. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Deployment decoupled from release: Unleash, the most popular open-source feature management platform on GitHub, is a Node.js server backed by PostgreSQL. Ship code dark, then control who sees it through activation strategies: gradual percentage rollouts, targeting by user ID, IP, hostname, or application name, custom constraints against your own context fields, and scheduled or time-limited releases. Strategies stack - a flag activates if any strategy matches - and strategy variants layer A/B versions on top of the on/off decision. Each flag carries per-environment configurations, so a feature can run at 100% in staging while canarying at 5% in production. Backend SDKs (Node.js, Java, Go, Python, Ruby, .NET, PHP, Rust, and more) fetch configuration and evaluate flags locally, so a flag check adds zero network latency to request paths; frontend SDKs for React, Vue, Svelte, iOS, Android, and Flutter evaluate through a proxy layer. Flag hygiene is built in: flags are typed (release, experiment, operational, kill-switch, permission) with expected lifetimes, and Unleash marks overdue flags as potentially stale and surfaces unknown flags your SDKs request but that don't exist. Self-hosting via Docker keeps flag data, targeting rules, and evaluation infrastructure entirely on your side.

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.

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.

When an agent breaks production at 3 a.m., "the model did it" is no incident report: Bernstein decides in advance what your AI agents may touch, then keeps receipts proving what they did. You write policy as code: which roles may do what, what needs human approval, and what must be recorded before a task counts as done. A deterministic scheduler with no model in the coordination loop turns each goal into parallel tasks, so replaying yesterday's plan reproduces yesterday's task graph exactly. Every coding task runs in its own git worktree behind merge gates; nothing lands on your main branch until tests, lint, and type checks pass. It drives the CLI agents you already use (Claude Code, Codex, Gemini CLI, Aider, Goose, dozens more), mixing cheap local models with heavy cloud ones in one run. Approvals can demand a hardware key touch, and role fences hold whatever an agent tries inside its task. The journal, lineage record, and optional tamper-evident audit chain capture every step, sealed into an Ed25519-signed receipt verifiable offline from the file alone. Non-code work gets the same treatment: an artifact contract names the deliverable (report, dataset, audit evidence pack), and the task completes on a signed receipt instead of a commit. You supervise from the browser dashboard or terminal UI, watching tasks, agents, approvals, and costs live. 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.

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.

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.

With over 126,000 GitHub stars and adoption across professional studios, research labs, and independent creators, ComfyUI has become the most widely used node-based interface for generative AI workflows — supporting image, video, audio, and 3D content creation through a single visual canvas. The graph editor natively supports Stable Diffusion 1.5, SDXL, SD3.5, Flux.1, Flux.2, HunyuanDiT, Lumina Image 2.0, HiDream, Qwen Image, and Pixart for image generation, plus Wan 2.1 and 2.2, LTX-Video, HunyuanVideo 1.5, CogVideoX, and Mochi for video, ACE-Step and Stable Audio for audio, and Hunyuan3D 2.0 for 3D models. Built-in tools handle inpainting, outpainting, ControlNet conditioning, LoRA and Hypernetwork loading, ESRGAN upscaling, area composition, model merging, and GLIGEN spatial control without writing code. The execution engine implements asynchronous queue processing with partial graph re-execution, running only changed nodes between iterations, and smart VRAM management that offloads models on GPUs with as little as 1 GB of memory. API nodes optionally connect to closed-source models through Comfy API while the core runs fully offline. Reusable subgraphs and App Mode expose complex workflows as simplified interfaces for non-technical users. The V3 custom node schema enables stateless execution with async support and process isolation. The TypeScript and Vue frontend ships as a PyPI package with stable releases every two weeks. Workflows save as JSON and embed in generated PNG, WebP, and FLAC files for reproducibility. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. GPL v3.0 licensed.

Address is a self-hosted generator that returns real, verifiable postal addresses for 27 countries and regions, each labelled with its source, precision, and coordinates, for form testing, validation checks, and logistics demos. Records come from official registers, open map data, or validated geocoding, and any field it cannot confirm stays empty instead of being invented. Pick a country, region, city, district, or postcode filter that follows the real administrative hierarchy, choose one of ten display languages, and generate. Results can be copied, exported, saved to favorites, or opened in Google Maps or AMap. QA teams fill checkout and signup forms with them, developers test address-format validation, and logistics demos finally show streets that are on the map. The OpenAPI-documented JSON API covers single and batch generation, location search, coverage queries, and address translation. A public coverage monitor shows how complete each country is. Behind the login, the admin console tracks sync history, quick locations, provider credentials, translation routing, access control, and API tokens. Incremental imports back off and stop when a source has nothing new. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Backed by 12,400+ GitHub stars and positioned as the self-hosted alternative to FullStory and Hotjar, OpenReplay delivers the open-source session replay platform that keeps every byte of user behavior data on your own infrastructure. The JavaScript tracker captures pixel-perfect recordings of clicks, scrolls, form inputs, and navigation with automatic sensitive data masking, while simultaneously logging network requests, console errors, JavaScript exceptions, and Redux, VueX, MobX, NgRx, Pinia, and Zustand store state changes for complete technical context. DevTools mode reconstructs each session with full stack traces, GraphQL queries from Apollo and Relay, Fetch and Axios request payloads, CPU and memory metrics, and page speed waterfall charts — effectively giving developers a browser inspector tied to any user session. Product analytics surfaces conversion funnels, user journeys, click heatmaps, web vitals trends, and retention cohorts without requiring custom instrumentation. Co-browsing connects support agents to live user sessions with cursor control and WebRTC audio, enabling real-time assistance without third-party screen-sharing software. Integrations push session context into Sentry, Datadog, CloudWatch, Stackdriver, and Elastic for front-to-back debugging. Feature flags enable gradual rollouts with session-level targeting. The platform deploys to any cloud via Docker and Kubernetes with auto-scaling ingestion handling up to 50,000 sessions per month on the open-source edition. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. AGPLv3 licensed.

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).

Draw it, write it as code, or hand it to your AI agent: OpenFlowKit is an open-source diagram canvas where the picture and the text behind it are always the same diagram. Drag shapes on the canvas or type a few forgiving lines, and each side regenerates the other as a single undo step. Ten diagram types share that one language: architecture with C4 views and cloud icons, sequence, flowchart, entity-relationship, state, class, mind maps, git graphs, charts, and wireframes. Paste Mermaid, Structurizr, or D2 and it converts into editable shapes, and Copy as Mermaid sends a flowchart or sequence back out for your README. Paste a GitHub repository instead and Map mode draws its architecture for you, with every arrow citing the exact file and line behind it, and a CLI that maps a local checkout for private repos. Connect Claude Code, Cursor, or any MCP client and the agent draws on your live canvas, restyles what is there, and screenshots its own work to check it. A built-in assistant works with your own key from Claude, OpenAI, Gemini, Groq, Mistral, OpenRouter, or a local Ollama, and exports cover PNG, SVG, PDF, JSON, and animated SVG, GIF, MP4, or WebM you can drop into documentation. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Twigpine Node is a self-hosted git node that publishes repositories under cryptographic identities and replicates them across a peer-to-peer network. Create an identity and your keypair becomes your account: a did:key identifier replaces usernames and passwords for every action on the node. Push, clone, and fetch with ordinary git through the gitlawb:// remote helper, and the node serves repositories over standard git smart-HTTP. Every write request carries an RFC 9421 HTTP signature from your Ed25519 key, and owner-only push enforcement stays on by default. Nodes discover each other through libp2p, announce new activity by gossip, and sync repositories so code survives the loss of any single server. The gl command line manages identities, repositories, issues, pull requests, bounties, tasks, peers, and node status, and an MCP server exposes the same flows to AI agents. Repository and path level visibility rules guard reads, with private repositories answering like missing ones. Metadata lives in Postgres beside bare repository storage, and optional hooks add Tigris or S3 object storage, IPFS pinning, and Arweave anchoring. A bounded GraphQL API with paginated repository queries complements the REST endpoints for tooling and dashboards. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT and Apache-2.0 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.

Your coding agents work in separate terminals and cannot ask each other anything; Imbo gives Claude Code, Codex, opencode, Cursor CLI, and six other agent tools one shared messaging network, so a session can send a question to another session and get an answer while both keep working. Messages land inside the receiving session mid-task, and a reply wakes an idle session so it can act on the answer. You add people by account ID, and their agents can message yours; group chats let several sessions from several people coordinate on one brief, with every reply reaching every member. Sessions can send files that land in the receiving machine's ~/.imbo/files folder, and an agent asks you first before sending your data out, deleting files, spending money, or touching production. From the web app or the iPhone app you can message your own sessions from anywhere, and a closed Claude Code session reopens in the background to pick the message up. The server is a single binary with a bundled PostgreSQL, HTTPS through Let's Encrypt, email code sign-in, and optional domain restrictions on who may register. 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.

MateClaw delivers a multi-agent AI platform where digital employees run as persistent team members with roles, goals, and accumulated skills rather than stateless chat completions. The Spring Boot backend on Spring AI Alibaba provides ReAct iterative reasoning and Plan-and-Execute decomposition on a StateGraph runtime, with parallel delegation between employees and dynamic context pruning for multi-step tasks. Five career templates ship ready (Product Researcher, Customer Support, Knowledge Curator, Data Analyst, Executive Assistant) while custom employees inherit configurable backstories, pixel-art avatars, and dedicated tool bindings. The MCP integration supports stdio, SSE, and Streamable HTTP transports with per-employee tool isolation preventing capability bleed between agents. ACP bridges bring Claude Code, Codex, and other coding agents in as first-class employees. Workflow orchestration composes multiple employees and system actions into publishable linear DSL processes with seven step modes: sequential, fan_out, collect, conditional, await_approval, dispatch_channel, and write_memory. The trigger system wires cron schedules, webhooks, channel messages, employee lifecycle events, content matches, and workflow completions to automated flows. The Admin Runtime Console provides real-time visibility into running employees with token usage tracking and one-click force-recycle. Spring Boot Actuator monitoring, full audit trail, and per-channel error isolation deliver production-grade reliability. 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.

Running local models usually means choosing between a polished app that hides the engine and a terminal full of flags you half remember. LlamaForge refuses the trade: it installs and drives the official llama.cpp release itself, then puts a browser panel over all of it, every one of the 200-plus llama-server flags your build supports, grouped, searchable and editable per model. Before you load anything, each model is drawn into your GPUs at its real footprint, so the out-of-memory surprise happens on screen instead of in a crashed server; before you download anything, every quant on Hugging Face gets a fit rating for your VRAM, FITS, TIGHT or CPU OFFLOAD. Auto-Forge then measures placements, KV cache types and speculative drafters on your own hardware and keeps the fastest configuration, checking that a drafter still produces identical tokens before applying it with one click, and undoing it with one click. Keep several models loaded at once and a planner places each on the GPUs that fit it; when a game launches, Game Mode unloads your models and brings them back when you quit. Chat in llama.cpp's own interface, join from your phone by QR code, duel two models blind in the Arena under an Elo board, and let Embers, small local agents, keep a wiki and write scheduled briefs counting only facts they can quote verbatim. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.