Backed by Y Combinator (S24) and processing traces from thousands of AI agents in production, Laminar is the open-source observability platform that treats agent debugging as a first-class engineering discipline rather than an afterthought. Its OpenTelemetry-native SDK auto-instruments Vercel AI SDK, LangChain, OpenAI, Anthropic, Gemini, Browser Use, Stagehand, Mastra, Pydantic AI, and the OpenAI Agents SDK with a single line of code, capturing every LLM turn, tool call, and sub-agent delegation as nested spans with full input/output data and token costs. The Signals engine lets you describe failures in plain language — "agent is stuck in a loop" or "tool returned empty results" — then reads every trace and alerts via Slack when it detects a match. A built-in debugger records runs and replays them from cache so each iteration takes seconds, designed for Claude Code, Cursor, or Codex to drive the repair loop via the MCP server or CLI. Run code-first evaluations in Python or TypeScript locally or in CI/CD pipelines, build datasets from production traces, and query everything with raw SQL through custom dashboards, the in-app editor, or your coding agent. The Rust backend delivers 20x trace compression, a custom real-time streaming engine, ultra-fast full-text search, and gRPC ingestion, while ClickHouse powers columnar analytics and PostgreSQL stores application state. 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.

Webclaw turns messy web pages into clean content your AI tools can actually use, extracting the meaningful text and leaving the navigation, ads, and boilerplate behind. You point it at a URL and get back Markdown, plain text, structured JSON, raw HTML, or a format trimmed for language model input, with images stripped, links deduplicated, and whitespace cleaned. Crawl a whole site by following same-origin links page after page, map a domain first to discover every URL from its sitemap before deciding what to fetch, or batch many URLs at once and stream the results as they finish. CSS selectors let you include only the part of a page you care about or exclude the parts you never want, and main-content filtering keeps the article while dropping the chrome around it. Compare today's page against an earlier snapshot to see exactly what changed, or pull a site's colors, fonts, and logo into a brand profile. With your own language model connected, extraction follows a JSON schema or a plain prompt, and summaries come back at the length you ask for. Agents reach the same engine through an MCP server, scripts through the command line, and applications through the REST API. 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 16,800 GitHub stars and growing rapidly, Maxun has become the go-to open-source platform for teams who need structured web data without writing scrapers. The TypeScript-based platform provides a no-code visual recorder that captures point-and-click interactions in real-time browser sync, automatically generating reusable extraction robots that handle pagination, infinite scrolling, and dynamic content. LLM-powered extraction accepts natural language prompts like "Extract 10 companies from the Y Combinator website" without requiring a URL — Maxun identifies the source and performs the extraction autonomously. The platform handles authentication-protected pages, adapts automatically to website layout changes through self-healing selectors, and exports directly to Google Sheets, Airtable, or any destination via webhooks. Robots run on configurable schedules with cron-based timing, turning any website into a perpetually fresh RESTful API endpoint. The crawl engine discovers and processes linked pages across entire domains with configurable depth and URL filtering, while the search capability runs automated queries across multiple engines. Official Node.js and Python SDKs provide programmatic control over robot creation, execution, and data retrieval, with MCP integration enabling direct connection to AI tools like Claude. The n8n community node enables workflow automation without custom code. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. AGPLv3 licensed.

OpenPencil is the open-source design editor that reads and writes native Figma .fig files using the same Kiwi binary format — enabling bidirectional copy-paste between Figma and OpenPencil without data loss. The built-in AI assistant provides 90+ design tools through a chat interface, creating and modifying shapes, fills, strokes, auto-layout, components, variables, and boolean operations from natural language prompts, with BYOK support for Anthropic, OpenAI, Google AI, OpenRouter, Z.ai, MiniMax, and compatible endpoints. A Skia CanvasKit WASM renderer paired with Yoga WASM layout engine delivers Figma-parity rendering with flex and CSS Grid support including gap, padding, and alignment. The headless CLI inspects node trees via XPath queries, lints naming and accessibility, converts between document formats, analyzes color and typography patterns, extracts design tokens, and exports to PNG, SVG, JSX/Tailwind, and HTML. An MCP server exposes all design operations over stdio and HTTP, connecting Claude Code, Cursor, Windsurf, and Gemini CLI for AI-assisted design automation. Real-time P2P collaboration via WebRTC with Yjs CRDT synchronization requires no server and no account. The Vue SDK provides headless components for embedding the editor into custom applications. Ships as a 7 MB Tauri v2 desktop app for macOS, Windows, and Linux, or runs in any browser as a PWA. 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 27,000 GitHub stars and an ecosystem of 1,900+ plugins covering every major cloud provider, database, and SaaS platform, Kestra is the orchestration engine that brings Infrastructure as Code principles to workflow automation — defining complex multi-step pipelines in readable YAML that execute across any language, runtime, or infrastructure boundary. The built-in VS Code-style editor provides syntax highlighting, auto-completion, real-time validation, and an AI Copilot that generates workflow YAML from natural language descriptions. Tasks execute in Python, Node.js, Go, R, Shell, SQL, or any Docker container, with event-driven triggers listening for file arrivals on SFTP and cloud storage, messages from Kafka, Redis, Pulsar, AMQP, MQTT, NATS, AWS SQS, Google Pub/Sub, and Azure Event Hubs in real time. The topology view visualizes workflow DAGs with execution state, duration, and output artifacts for each task node. Namespaces organize workflows into isolated environments with configurable secrets, while subflows enable modular composition with inputs, outputs, and conditional branching. Retry policies, timeouts, error handlers, and automatic backfills for missed schedules ensure reliability across production workloads. Git integration pushes workflows directly to branches from the UI with CI/CD pipeline support for automated deployment. The REST API enables programmatic workflow management, execution triggering, and resource provisioning. 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.

Forge intercepts failing LLM tool calls and fixes them before they derail your agent workflow, applying rescue parsing, retry nudges, response validation, and step enforcement between your AI clients and local model backends. The proxy server mode drops in as a transparent intermediary speaking both the OpenAI chat-completions API and the Anthropic Messages API, so tools like Aider, Claude Code, Continue, and opencode connect through it without configuration changes. Under the hood, the WorkflowRunner provides a complete agentic loop manager with system prompt injection, tool execution, context compaction with configurable thresholds, and VRAM budgeting for consumer GPUs with 12-32 GB. SlotWorker enables priority-queued access to shared inference slots with automatic preemption for multi-agent architectures. The guardrails middleware exposes a two-method check-and-record API that wraps into any existing orchestration loop, providing malformed tool-call rescue parsing, retry nudge generation, required step enforcement, and prerequisite ordering without taking over execution control. Backend adapters support generic OpenAI-compatible endpoints, Ollama, llama-server, Llamafile, vLLM, and Anthropic with automatic model discovery and health checking. Architecture Decision Records document every design choice. Launched February 2026, already at 2,200+ GitHub stars. MIT licensed.

DocsMint is a self-hosted knowledge workspace where your team writes documentation once and both people and AI agents retrieve it through hybrid search and a built-in MCP server. Documents live in a rich visual editor with Markdown import and export, organized by folders, categories, and tags, with sharing and version history. Search blends exact title matches, multilingual keyword search, typo-tolerant fuzzy matching, and semantic vectors, then widens results through graph relationships between documents, so a query in one language or phrasing still finds the right page. Every edit quietly refreshes the index in the background; nothing needs manual re-embedding. Agents connect through 22 MCP tools covering search, reading, creation, updates, folders, snapshots, and export, over a local stdio bridge or the HTTP endpoint on your own installation. Category-scoped API keys hand each integration only the slice of the library it may read, edit, or write, while a global key serves trusted automation. The same operations are available through the REST API, a typed TypeScript SDK, and a terminal CLI for scripts. The web application installs as a PWA with offline reading, and AI features run on your choice of an OpenRouter key or a fully local Ollama setup. 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.

Connecting autonomous AI assistants to internal enterprise databases and legacy systems is streamlined by AnythingMCP, a visual Model Context Protocol gateway with automated knowledge graph generation and granular access controls. Engineers can import OpenAPI specifications, Postman collections, SOAP WSDL files, or raw database credentials to generate standardized Model Context Protocol tools in minutes without writing custom code. The built-in knowledge graph automatically maps entity relationships across disparate databases and software platforms, teaching agents how to correlate customer records in CRM tools with live order histories in enterprise resource planning software. System administrators can enforce fine-grained access policies by restricting tool execution permissions to specific roles and scoping database operations to read-only queries with strict row limits. An interactive web console provides real-time tool inspection, payload testing, request tracing, and comprehensive audit logs that capture every upstream invocation with full parameter visibility. Enterprise teams can integrate identity providers through OAuth2, SAML single sign-on, and SCIM automated user provisioning while protecting sensitive credentials using AES-256-GCM encryption at rest. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. GNU AGPLv3 licensed.

ThoughtDAG turns a long AI conversation from a scroll you cannot rearrange into a map you can edit, branch, and reconnect. Every question and answer becomes a node on an infinite canvas, and the wires between nodes are not decoration: they decide exactly what context the model sees next. Follow a promising thread, park a side question on its own branch, or cut a wire when an early assumption starts poisoning later answers, all without deleting the work that led there. Zoom out to read the shape of an investigation, then zoom back in to full answers, attachments, and highlighted passages. Drop in documents and files as material nodes, ask questions from them, and preview precisely what will be sent before a model runs. Past coding agent sessions can be opened as read-only graph mirrors, so a discussion that started in a terminal can be inspected, cited, and continued on the canvas. Memory lives in readable dossiers that collect decisions and open questions per topic, with sources attached, and relevant dossiers join new questions when you ask. Export a backup, a Markdown context chain, or a thought map that shares the structure of your thinking without dumping the whole transcript. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Originally built at Netflix to orchestrate microservices powering 230 million subscribers and now trusted in production at Tesla, LinkedIn, and J.P. Morgan, Conductor is the most battle-tested open-source workflow engine available — with 32,000 GitHub stars and horizontal scalability to billions of executions. The architecture cleanly separates orchestration from business logic: workflows are defined in declarative JSON while workers execute tasks in any of seven supported languages (Java, Python, Go, JavaScript, C#, Ruby, Rust) with zero framework constraints. Durable execution persists every state transition, enabling automatic retries, configurable timeouts, crash recovery, and instant replay from any failure point without re-executing completed tasks. Native AI agent orchestration supports 14+ LLM providers (Anthropic, OpenAI, Google Gemini, AWS Bedrock, Mistral, Cohere, HuggingFace, Ollama), MCP tool calling, function calling, human-in-the-loop approval gates, and vector database integration (Pinecone, pgvector, MongoDB Atlas) for RAG pipelines. Deploy with your choice of five persistence backends (PostgreSQL, Redis, MySQL, Cassandra, SQLite), six message brokers, and Elasticsearch or OpenSearch for workflow indexing — all configurable via Docker Compose files included in the repository. The built-in web UI provides workflow visualization, execution monitoring, task queue inspection, and manual intervention controls. 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.

OverClick is the task board where your AI agents clock in: you write the assignments, they claim the work, and you stamp what actually got done. A card here is a contract, not a ticket: what should happen, why it matters, and a plain-language test script that says how to confirm it, all written before anyone starts. You tell your agent to grab the next task, and it claims the card over MCP, declares the CLI and model it really runs on, receives a self-contained briefing with the mission context and branch convention, and the card slides into progress. When it finishes, the handoff lands with a summary, evidence, branch and pull request links, and measured telemetry, the tokens per model and minutes the run actually took, read from the session transcript rather than guessed. Every card keeps three roles straight, who asked, who executed, and who reviews, and only a human can mark it validated; reopening with a comment puts your note in front of the agent's next claim. Big decisions can start as RFC cards whose approval spawns the execution cards, and insights roll up what each project, mission, and model consumed. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

OpenSEO provides an alternative to the $100+/month SEO suite monopoly by connecting directly to DataForSEO APIs on a pay-as-you-go basis — you bring your own API key and pay only for the queries you actually make. The platform delivers focused workflows for keyword research with volume, difficulty, CPC, intent, and live SERP inspection; rank tracking with historical position monitoring; backlink analysis with referring domain quality scoring; technical site audits that crawl pages and surface issues; competitor insights comparing SERP positions across keyword sets; and AI visibility monitoring that tracks brand mentions, citations, and prompts across AI models. The integrated MCP server exposes all tools to AI coding agents including Claude Code, OpenClaw, Hermes, and Cursor, while Agent Skills provide reusable SKILL.md workflows that guide agents through complex SEO research tasks. Google Search Console integration reads first-party performance data including clicks, impressions, CTR, and position metrics with URL-level index status inspection. The Prompt Explorer compares how different AI models respond to SEO-relevant queries. Self-host via Docker for personal use or deploy to Cloudflare for team access with automatic database backups. The hosted version at openseo.so adds a 28% markup on DataForSEO requests. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Paste in a job posting and Dossier, a self-hosted job search app, shows how your profile matches it, then drafts a tailored resume and cover letter that use only facts you have given it. Requirements your profile cannot back up appear as gaps instead of invented experience, and a chat lets you refine any part, undo AI changes, or return to an earlier version. Twelve resume themes and a theme builder print to PDF on the server. Find jobs through JSearch, Adzuna, or Germany's Bundesagentur für Arbeit, score a posting against your profile, and start an application in one click. An optional job agent runs one search a day and can prepare drafts that wait for your approval; it never sends or applies. A board and a table track each application from draft to offer, and the dashboard charts your funnel week by week. Connect Gmail and Google Calendar to send applications from your own address, have the AI read employers' replies and draft answers, and keep interviews in step both ways, with nothing sent until you confirm. Choose a local model through Ollama or LM Studio, or a hosted OpenAI-compatible, Anthropic, or Mistral provider. Everything exports as one file, with nightly backups. 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.

Toonflow, an open-source AI studio for short dramas, animated comics, and short videos, lets you plan, generate, and direct every shot as nodes on a canvas that runs on your own server. Text nodes hold the story, characters, and shot descriptions. Image generation nodes create character sheets with close-up, front, side, and back views. Video generation nodes take numbered reference images. Aspect ratio, resolution, and duration options depend on the selected model. Connectors link the nodes, so a character sheet made once is reusable in every shot. The 3D director's studio blocks a scene with camera framing, lighting, and keyframes. Export the scene as a video node. An assistant panel reads the project and reports which assets and videos have been generated. It offers next steps: generate a shot, revise a prompt, or start a new canvas. Finished images and clips preview on the canvas and download for further production work. Models come from third-party APIs, local ComfyUI workflows, or local language models. Plugins for nodes, skills, tools, and agents install from the marketplace. MCP links external tools and services. Projects, settings, and plugins live in one data directory. The interface offers 21 languages. There is no built-in login, so a firewall or an authenticating reverse proxy decides who can reach it. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

When a query crosses its threshold, Nightingale, a self-hosted alerting engine, decides who hears about it and how, without moving data out of the stores you already run. Rules use PromQL, log queries, or SQL against Prometheus, VictoriaMetrics, Elasticsearch, Loki, ClickHouse, MySQL, or PostgreSQL, graded S1, S2, or S3 with a for-duration that absorbs brief spikes. Existing Prometheus alert rules import from YAML. Business groups give each team its own rules and dashboards, and sign-in works through OIDC, OAuth2, LDAP, or CAS. Once a rule fires, mute rules silence the noise, subscriptions add recipients, and event pipelines rewrite labels or route conditionally. Delivery reaches Slack, PagerDuty, Discord, Telegram, Jira, email, DingTalk, Feishu, WeCom, SMS, and voice calls, plus HTTP webhooks and scripts for anything else. Evaluation records, active and historical events, and notification results show what happened at each step. If an alert misbehaves, the built-in AI agent explains why it fired or never arrived, and it drafts rules, dashboards, and mutes from plain-language requests. Claude Code, Cursor, and other MCP clients can query alerts and manage alerting through /mcp, read-only by default and bound by the caller's own permissions. At remote sites, n9e-edge keeps evaluating and notifying when the link to the center drops. 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.

SuperPlane is an open-source engineering automation platform that turns routine backlog tickets into verified, review-ready pull requests while orchestrating complex multi-system workflows across your developer tools. Engineers use the visual infinite canvas to assemble event-driven pipelines with trigger nodes, conditional routing, loops, and human-in-the-loop approval gates. You can delegate pull request code reviews, automated QA testing, documentation generation, and release management to coding agents operating within strictly defined policy boundaries. Custom operational consoles let teams build live monitoring dashboards displaying key delivery metrics, active incident states, and execution histories from connected tools. Integrations connect natively with GitHub, GitLab, Datadog, PagerDuty, Slack, AWS, and leading AI models through webhook events and bi-directional actions. Every automation run maintains durable state persistence across process restarts, ensuring failed steps resume with full input payloads and debugging context intact. Developers can define reusable work orders, configure canvas memory for long-term state retention, and execute fleet commands over SSH or containerized runners. 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.

Hoarder (now Karakeep) is a bookmark manager that actually fights link rot: every page you save gets archived at capture time using Monolith, so the content survives even when the original URL dies. Beyond archival, an AI layer powered by OpenAI or local Ollama models auto-tags everything by analyzing page content. Prefer full privacy? Ollama keeps all inference on your server with zero external API calls. Full-text search through Meilisearch indexes the actual scraped content of every bookmark, not just titles and tags, so you find articles by what they say rather than labels you half-remember. Save links with automatic metadata extraction, plain text notes, uploaded images, and PDF documents, all organized into shareable lists with collaborative access. Browser extensions for Chrome and Firefox make saving a one-click operation from any page. Migrating is painless with importers for Chrome, Pocket, Linkwarden, Omnivore, and Tab Session Manager. LLM summarization condenses saved pages into brief overviews for quick scanning. The AI layer is entirely optional: Hoarder works perfectly as a manual bookmark manager, with intelligence adding convenience rather than imposing a requirement. SSO integration and responsive dark mode round out the package.

Design posters, social posts, presentations, invitations, resumes, thumbnails, and business cards in your browser with Doory, a self-hosted design editor that keeps your files, fonts, and brand assets on your own server. Start from one of ten starter templates or a blank canvas, then place text, shapes, lines, arrows, emoji, stickers, QR codes, and roughly 27,500 built-in icons anywhere on the page. Photo tools cover cropping, masks, filters, in-browser background removal, and 2x to 4x image upscaling, with stock photo search through Unsplash or Pexels. Layers can be renamed, locked, hidden, grouped, and reordered, while guides, snapping, rulers, per-page sizes, and format resizing keep multi-page designs tidy. Animations add 27 enter and exit effects, 12 emphasis motions, and 16 page transitions, plus Creative Commons music loops and sound effects, so decks can be presented live with speaker notes or exported as MP4, WebM, or GIF. Share links grant view, comment, or edit access with an optional password, and collaborators can pin comments, co-edit in real time, and roll back through version history. Brand kits store your colors, fonts, and logos so recurring posts stay on-brand, and exports cover PNG, JPG, SVG, and print-ready PDF with bleed and crop marks. An optional MCP server lets AI assistants create and fill designs from prompts, including bulk template filling from spreadsheet-style rows. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Attribution Assurance License licensed.