Kortix Suna is an AI management system where autonomous agents run on isolated Linux sandbox computers, producing finished deliverables that humans review through a change request workflow before anything merges. With 20,000+ stars, it positions itself against Claude Cowork and ChatGPT Work by storing every agent persona, skill, memory artifact, and connector in a git repository: versioned, diffable, and shared across an organization. Each session launches a dedicated sandbox with full terminal access, Playwright-controlled Chromium, writable filesystem, and internet connectivity. Over 3,000 app connectors are available through MCP, OpenAPI, GraphQL, and raw HTTP, with credentials brokered server-side so tokens never enter the sandbox. Skills (reusable markdown-plus-script packages encoding company workflows) load automatically into every session, compounding institutional knowledge over time. Bring-your-own-key model routing through LiteLLM connects to OpenAI, Anthropic, Google, Mistral, or local models without vendor lock-in. The deployment runs as a single Docker Compose stack bundling the Next.js frontend, FastAPI backend, Supabase, Redis, and Caddy with automatic TLS certificates. Enterprise features include SAML/OIDC SSO, SCIM provisioning, RBAC, and audit logging. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Elastic License 2.0.

Dify turns the notoriously complex process of building production-grade AI applications into a visual drag-and-drop experience that teams can actually ship and maintain. With over 87,000 GitHub stars and backing from prominent investors, the platform has become the go-to open-source LLMOps solution for organizations that refuse to be locked into proprietary AI stacks. The visual workflow canvas lets developers wire together LLM calls, conditional logic, iteration loops, tool invocations, and human-in-the-loop checkpoints without writing boilerplate integration code. Its RAG pipeline engine handles the full document lifecycle from ingestion of PDFs, Word documents, and HTML through configurable chunking strategies, embedding with models from OpenAI or open-source alternatives, vector storage in Weaviate, Qdrant, Pinecone, or pgvector, and hybrid semantic-plus-keyword retrieval with citation tracking. Dify integrates with hundreds of model providers including OpenAI GPT-4o, Anthropic Claude, Google Gemini, Mistral, Llama, and any OpenAI-compatible endpoint like Ollama for fully local inference. The agent framework supports both ReAct and function-calling strategies with 50-plus built-in tools spanning Google Search, DALL-E, Stable Diffusion, WolframAlpha, and custom API definitions. Published apps can be deployed as hosted web interfaces, embedded chat widgets, REST API endpoints, or MCP-compatible tools. Enterprise features include role-based access control, SSO integration, and audit logging. A built-in marketplace enables teams to share and reuse model providers, tools, and workflow templates across projects. 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 an open-source community edition.

Kandev provides a command center for orchestrating AI coding agents across parallel workstreams. The Go backend paired with a Next.js frontend delivers kanban boards with drag-and-drop columns, pipeline workflow definitions with per-step agent handoffs, and an IDE-like review workspace combining file editor, file tree, terminal, browser preview, and unified git diffs. Multi-provider support connects Claude Code, GitHub Copilot, Codex, Qoder, Grok, and custom agents through configurable profiles with per-agent prompts, runtimes, and review gates. Tasks execute in isolated git worktrees with multi-repository support, letting agents work on separate branches simultaneously while changes surface in a consolidated review interface. Native integrations with GitHub, GitLab, Jira, Linear, Sentry, and Slack pull external issues into the kanban and link tasks to pull requests. Kandev exposes streamable HTTP and SSE MCP endpoints, enabling external clients — Cursor, Claude Desktop, Augment — to create tasks and read workspace context programmatically. Workflow definitions export as portable YAML for sharing across installations. Agentic workflows chain multi-step pipelines mixing different models per step — Opus for architecture, Sonnet for implementation, with human review gates between stages. 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 29,000 GitHub stars and deep integrations into LangChain, LlamaIndex, and CrewAI, Chroma has become the default vector database for developers building retrieval-augmented generation pipelines and AI agent memory systems. Its core API consists of just four functions — create, add, query, and delete — making it the fastest path from zero to semantic search, while the underlying Rust engine handles tokenization, embedding, HNSW indexing, and similarity scoring automatically. Chroma supports dense vector search via HNSW with configurable distance metrics including L2, cosine similarity, and inner product, sparse vector search using SPLADE, full-text BM25 keyword search, and regex matching, all combinable in hybrid queries through a single unified interface. Metadata filtering at query time uses MongoDB-style operators including $eq, $ne, $gt, $lt, $in, and logical combinators $and and $or, enabling precise result scoping without post-processing. The multimodal pipeline powered by OpenCLIP embeds text and images into a shared vector space, allowing cross-modal retrieval where text queries return relevant images and vice versa. Deployment options range from embedded mode via PersistentClient for notebooks and prototypes, to client-server mode with Docker for production, to Chroma Cloud for serverless scalability. Official Python and JavaScript SDKs provide identical APIs, and embedding function integrations support OpenAI, Cohere, Hugging Face, Google, Ollama, and custom models. 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.

Backed by the Linux Foundation with contributions from AWS, Cisco, IBM, Microsoft, Red Hat, and Shell, Agentgateway is the first data plane built from the ground up for AI agent workloads — providing a unified Rust-based proxy that handles conventional HTTP and gRPC traffic alongside MCP tool servers, A2A agent communication, and LLM inference endpoints through a single deployment. The LLM gateway routes requests to OpenAI, Anthropic, Gemini, AWS Bedrock, and other providers through an OpenAI-compatible unified API with per-tenant budget controls, spend tracking, prompt enrichment, load balancing across multiple model endpoints, and automatic failover when providers experience outages. The MCP gateway federates multiple tool servers behind one endpoint, supporting stdio, HTTP/SSE, and Streamable HTTP transports with built-in OAuth authentication compliant with the MCP auth specification, integrating Auth0 and Keycloak out of the box. OpenAPI integration exposes existing REST APIs as MCP-native tools without code changes, enabling legacy services to participate in agent workflows. Policy-based RBAC controls which agents access which tools, while OpenTelemetry integration provides distributed tracing across agent communication chains. Deploy as a standalone binary with flat YAML configuration or on Kubernetes using the built-in controller with Gateway API support for declarative infrastructure-as-code management. 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.

Reaching #1 on GitHub Trending with over 48,000 stars, OpenMontage is the first open-source agentic video production system — transforming AI coding assistants like Claude Code, Cursor, Copilot, Windsurf, and Codex into complete video studios that handle research, scripting, scene planning, asset generation, editing, and final rendering through natural language prompts. Twelve production pipelines cover animated explainers, cinematic trailers, documentary montages, talking heads, screen demos, podcast repurposing, character animation, localization and dubbing, avatar spokesperson videos, hybrid productions, clip factory batch processing, and animation workflows. Over 100 registered Python tools connect to 60+ providers including Kling, Runway Gen-4, Google Veo 3.1, FLUX, Google Imagen 4, ElevenLabs, and Suno AI for cloud generation, plus Piper TTS, WAN 2.1, Hunyuan, and CogVideo for fully local GPU rendering — while free footage from Archive.org, NASA, Wikimedia Commons, Pexels, and Unsplash powers the documentary montage pipeline's CLIP-indexed retrieval system for real-motion video without paid generation APIs. Two composition engines — Remotion for React-based programmatic video and HyperFrames for HTML/GSAP motion graphics — render final output with spring animations, word-level captions, kinetic typography, and SVG character rigs. A seven-dimension scored provider selector, pre-compose validation gates, post-render ffprobe self-review, slideshow risk scoring, configurable budget caps with per-action approval thresholds, and the Backlot live web dashboard for visual production monitoring enforce production-grade quality at every stage. 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.

Designed as a unified personal AI workstation, QwenPaw operates as an autonomous digital copilot that coordinates scheduled automations, interactive coding sessions, and multi-channel team communication across everyday messaging apps. Users can dispatch long-running research tasks, process office documents including PDF, Excel, and Word files, and execute browser-based data collection without manual intervention. The built-in web console and terminal interface provide full visibility into agent reasoning, allowing operators to inspect intermediate thinking steps, review proposed file edits, and approve sensitive tool calls. Through direct connectors for Discord, Telegram, DingTalk, Lark, and WeChat, teams can trigger specialized skills or query shared workspaces directly from their existing group channels. A self-evolving personal memory system continuously indexes chat interactions and local resources into editable Markdown files, ensuring knowledge persists across restarts and task delegations. Built-in guardrails including a sandboxed execution runtime, tool access policies, and automated skill scanners protect underlying host files from unauthorized modifications during autonomous scripting runs. 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.

Speakr transforms audio recordings into organized, searchable, AI-enhanced notes with speaker recognition that identifies who said what across your entire recording library. The Python/Flask backend with Vue.js 3 and Tailwind CSS frontend deploys via Docker on port 8899, offering multiple transcription engines through auto-detected connectors: WhisperX for local processing with speaker diarization and voice embeddings, OpenAI Whisper and GPT-4o-transcribe, Mistral Voxtral for cloud diarization, AssemblyAI for multi-hour files, and any custom ASR webservice. Speaker voice profiles use embedding comparison to recognize individuals across different recordings automatically, while custom vocabulary biases the transcriber toward domain-specific jargon. The AI layer goes well beyond transcription: customizable summaries with per-recording, per-tag, and per-folder prompt templates; event extraction surfacing action items and calendar events; per-recording chat with streaming responses; and Inquire Mode for semantic search and natural-language queries across your entire library simultaneously. Smart tags execute custom AI prompts on transcripts for automatic categorization. The REST API with Swagger documentation supports signed webhooks integrating with n8n, Zapier, and Make. Auto-export pushes to Obsidian and Logseq, auto-processing watches directories, and the installable PWA provides mobile-first, offline-capable access with share-target support. 3,600+ stars since May 2025. 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.

Live web search plus an LLM of your choice: Farfalle is an open-source, self-hosted answer engine in the Perplexity mold. Queries route through one of several search providers - self-hosted SearXNG for a fully independent stack, or Tavily, Serper, and Bing APIs - and the model composes a cited answer from the retrieved results. Model flexibility is the core design: run llama3, mistral, gemma, or phi3 locally through Ollama for zero per-query cost and full privacy, use cloud models like GPT-4o or Groq-hosted Llama 3 for speed, or route to any provider via LiteLLM. An Expert Search mode uses an agent that plans a multi-step search strategy and executes it for harder questions, and chat history keeps prior research sessions available. The stack is a Next.js and shadcn/ui frontend over a FastAPI backend with Redis rate limiting, shipped as a pre-built Docker image. A browser search-engine entry pointing at your instance makes it the default search from the address bar. Paired with SearXNG and Ollama, the whole pipeline runs with no external API at all.

Transforming fragmented research notes, daily technical logs, and project documentation into an interconnected knowledge base is what NoteDiscovery delivers for privacy-conscious teams and researchers. Writers compose rich documents using a dual-pane editor that renders MathJax equations, interactive task lists, and dynamic Mermaid sequence diagrams side by side with raw text. The interactive knowledge graph maps semantic relationships across notebooks, allowing researchers to explore backlinks, uncover hidden topical connections, and navigate complex idea webs visually. Team members sketch architecture diagrams and wireframes directly inside note canvases using the integrated drawing tool, saving revisions as embedded image layers without external editors. The platform organizes thoughts through flexible tag hierarchies, nested folder trees, and reusable document templates equipped with automatic date and variable substitutions. Autonomous coding assistants and language models query documentation, create structured meeting summaries, and update project indexes directly through the native Model Context Protocol server. Built-in export tools convert notebook collections into standalone HTML packages, printable documents, or portable Markdown archives for offline archiving. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Machine translation with no Google, no Azure, no per-character billing, and no text leaving your infrastructure: LibreTranslate is a free, open-source translation API that runs entirely on your own server. The engine underneath is Argos Translate, which runs OpenNMT neural models with SentencePiece tokenization and Stanza sentence-boundary detection, all offline. Models install as portable .argosmodel packages covering dozens of languages - English, Spanish, French, German, Chinese, Japanese, Russian, Arabic, Hindi, Portuguese, and many more - and Argos handles automatic pivoting: with es-to-en and en-to-fr installed, it chains them to translate es-to-fr without a direct model. The API is a straightforward HTTP POST to /translate with source and target language codes, returning JSON - simple enough that the ecosystem has clients in every major language and integrations across tools like Weblate and Mastodon. Beyond plain text it translates HTML while preserving markup and handles whole file uploads (documents in, translated documents out), plus automatic language detection when the source is unknown. A clean bundled web UI serves interactive translation for end users, and optional API keys with rate limits control access. AGPL-licensed and trainable with custom models, it is the standard answer when translation must be private, unmetered, and self-contained - GDPR-sensitive text never touches a third party.

GoRaven transforms AI chat from a question-answer window into a full engineering workstation where agents read files, write code, run shell commands, query databases via MCP tools, and deliver structured results — orchestrating across OpenAI, Claude, DeepSeek, Gemini, Qwen, GLM, and Ollama with task-based routing that allocates the right model for each job based on cost and capability. Built on a Go backend using the Freedom framework with Iris HTTP and a React/TypeScript frontend powered by Vite and Tailwind CSS, each user operates in an isolated workspace with team-shared project areas and centrally managed model quotas. The skill marketplace packages prompts, scripts, and workflows as reusable installable units with automatic dependency resolution and centralized versioning. MCP toolchain integration connects agents to internal APIs, databases, private services, and CLI tools so they query data, invoke services, and trigger actions directly. RAG-powered knowledge bases ingest policies, documentation, and business data for real-time retrieval during planning, coding, and Q&A with source attribution. Long-running task support decomposes complex work through a main agent coordinating sub-agents that execute in parallel across sessions. Plugin hooks inject custom logic at conversation start and end, tool calls, and SSE event streams without forking core code. The operations dashboard tracks usage metrics, model consumption, and team activity. Supports SQLite, MySQL, or PostgreSQL with Redis or local memory caching. Deploy with a single Docker command. 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 70,000 GitHub stars and billions of documents indexed across enterprises like Uber, Netflix, and Wikipedia, Elasticsearch is the world's most deployed search engine, powering everything from application search to security analytics and AI-driven retrieval. Built on Apache Lucene, its inverted index architecture delivers sub-second full-text search across terabytes of data with BM25 relevance scoring, configurable analyzers for 30+ languages, and fuzzy matching for typo tolerance. The kNN vector search API uses the HNSW algorithm for approximate nearest neighbor queries on dense and sparse embeddings up to 4,096 dimensions, while reciprocal rank fusion enables hybrid search that combines lexical and semantic signals in a single query. Elasticsearch's aggregation framework supports metric, bucket, and pipeline aggregations for real-time analytics directly on indexed data without separate OLAP infrastructure. The cluster distributes data across shards with automatic rebalancing, replica allocation, and cross-cluster search for multi-datacenter deployments. Kibana provides the visualization layer with dashboards, Lens visual editor, Canvas for pixel-perfect reports, and Discover for ad-hoc log exploration. Ingest pipelines with processors like grok, dissect, GeoIP enrichment, and inference handle data transformation at index time, and ES|QL brings pipe-based query syntax with joins and columnar processing. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. AGPL v3 licensed.

Thirteen-plus LLM providers, one unified client: NextChat (formerly ChatGPT-Next-Web) is an open-source AI chat interface built on Next.js that spans OpenAI GPT-4, Anthropic Claude, Google Gemini, DeepSeek, Groq, Azure endpoints, and self-hosted backends like Ollama, LocalAI, and RWKV-Runner. Its defining trait is minimalism - the first screen loads in about 100 KB, the desktop client is roughly 5 MB, and there is no database or user system to operate; chat history lives locally in the browser with optional WebDAV or UpStash Redis sync. The Mask system saves reusable prompt-template personas you can share and debug, long conversations auto-compress to fit context windows, and Markdown rendering covers LaTeX, Mermaid diagrams, and code highlighting with streaming responses. Plugins add web search and calculators, MCP support enables external tool calling, and Artifacts previews generated content in a separate pane. Ships as a web app, Docker image, and Tauri desktop builds for Windows, macOS, and Linux, translated into 20+ languages. MIT-licensed.

Sim Studio lets teams build, deploy, and monitor AI agent workflows by dragging blocks onto a visual canvas and wiring them into executable pipelines, backed by over 1,000 integrations. The React Flow editor represents each step as a node: LLM calls, tool invocations, conditional branches, and data transformations form directed acyclic graphs that run as complete agent pipelines. Every major LLM provider works natively, including OpenAI, Anthropic, Google Gemini, Groq, and Cerebras, plus local models through Ollama and vLLM. Integrations span Gmail, Slack, Microsoft Teams, Telegram, WhatsApp, Notion, Google Workspace, Airtable, GitHub, Jira, Linear, Perplexity, Firecrawl, PostgreSQL, Supabase, Pinecone, and Qdrant. Built-in tables provide a database layer, a file store offers shared team storage, and knowledge bases powered by PostgreSQL with pgvector enable retrieval-augmented generation. Finished workflows deploy as REST API endpoints, scheduled jobs, or Slack bots, with block-by-block execution traces for full observability. Real-time collaborative editing via Socket.io supports simultaneous multi-user construction. Alternatively, describe agent behavior in natural language and Sim assembles the workflow automatically. Built on Next.js App Router, Bun runtime, Drizzle ORM, and Tailwind CSS. 29,400+ GitHub stars and 100,000+ builders. Apache-2.0 licensed.

With over 7,400 GitHub stars and benchmarked at 0.89 seconds average session lifecycle — 1.7x to 9x faster than competing browser automation platforms — Steel Browser delivers production-grade headless Chrome infrastructure purpose-built for AI agents that need to interact with the modern web. The TypeScript-based server exposes a REST API providing on-demand browser sessions with full CDP (Chrome DevTools Protocol) access, allowing connections from Puppeteer, Playwright, or Selenium through standard WebSocket endpoints without framework lock-in. Each session maintains persistent state including cookies, localStorage, IndexedDB, and authentication credentials across requests, enabling stateful multi-step agent workflows that survive session restarts. Built-in anti-detection includes stealth plugins, browser fingerprint randomization, and configurable user-agent rotation, while the proxy chain manager handles IP rotation through residential, datacenter, or custom proxy pools. CAPTCHA solving integrates natively so agents encounter fewer blocking interrupts during autonomous navigation. The Session Viewer provides real-time WebRTC-streamed visual debugging of live sessions and playback of recorded sessions with full network request logging. Browser Tools APIs convert any page to clean Markdown, readability-optimized text, PDF documents, or high-resolution screenshots with a single API call. The MCP Server integration exposes Steel sessions as tools accessible to Claude, Cursor, and other Model Context Protocol-compatible AI agents. Deploy via Docker with a single container or use Docker Compose for production configurations with automatic resource cleanup and session lifecycle management. 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.

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.

With over 75,000 GitHub stars and native apps across macOS, Windows, Linux, iOS, and Android, AppFlowy is the most widely adopted open-source alternative to Notion — delivering the same block-based workspace model with full data sovereignty. The Flutter frontend renders natively on every platform while a Rust backend powered by Actix-web and Tokio handles CRDT-based real-time collaboration, ensuring sub-second sync across devices with conflict-free concurrent editing. Relational databases support grid, board, kanban, calendar, and gallery views over the same dataset, with two-way relations, rollups, advanced filters, sorts, and formula calculations that cover the majority of Notion's database workflows. The block editor supports 40+ content types including nested pages, toggles, callouts, code blocks with syntax highlighting, embeds, and slash-command insertion. AI integration connects to OpenAI, Anthropic, or local models via Ollama for writing assistance, summarization, and translation — all without sending data off-premises when using on-prem LLMs. Team spaces with workspace-level and per-page permissions, OAuth and SSO authentication through GoTrue, and S3-compatible object storage via MinIO provide enterprise-grade access control and file management. The self-hosted stack deploys through Docker Compose with PostgreSQL for metadata, Redis for caching and pub/sub, and a dedicated background worker for imports and email notifications. Offline-first architecture ensures the desktop app functions without connectivity, syncing changes when the connection resumes. 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.