A personal AI assistant that remembers what it learns and reaches you wherever you are — OpenClaw is an open-source agent gateway built by the OpenClaw Foundation with 247,000+ GitHub stars. It connects to 200+ LLM models through providers like Anthropic, OpenRouter, and OpenAI, and meets you on 21+ messaging channels: Telegram, Slack, Discord, WhatsApp, Signal, iMessage, Matrix, and more. Persistent memory with full-text search lets the agent recall context across sessions, and a self-improving skills system means it gets more capable the longer it runs. Voice wake words and talk mode enable hands-free interaction on macOS, iOS, and Android. A live canvas provides an agent-driven visual workspace. Built-in browser automation, cron scheduling for unattended tasks, and subagent spawning for parallel workstreams round out the toolset. The gateway architecture keeps all sessions, credentials, and conversation history on your own server — nothing transits a third-party cloud unless you choose to connect one. The API key you provide for your chosen LLM provider powers the underlying 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.

Open-source alternative to OpenAI's Canvas — a collaborative writing and coding environment where AI agents help you draft, edit, and refine documents through an agentic architecture built on LangGraph. The dual-mode editor combines a BlockNote rich text editor for live-rendered markdown with a CodeMirror-based code editor supporting syntax highlighting across multiple programming languages, letting you switch between prose and code artifacts within the same session. The built-in reflection agent automatically generates style rules and user insights from your chat history, storing them in a shared LangGraph memory store that persists across sessions for increasingly personalized assistance. Pre-built quick actions provide one-click access to common writing transformations including summarize, expand, simplify, and translate, while coding actions offer explain, refactor, add comments, and convert between languages. The monorepo architecture separates the Next.js 14 frontend from the LangGraph agent backend, connecting via HTTP and WebSocket protocols through the @langchain/langgraph-sdk client. Seven LLM providers are supported out of the box — OpenAI, Anthropic Claude, Google Gemini, Fireworks AI, Groq, Azure OpenAI, and local Ollama models — with Supabase handling authentication and data persistence. Deploy via Docker or build from source. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Relaticle delivers the first CRM built from the ground up for both human operators and AI agents — a self-hosted platform where Claude, GPT, Gemini, or any custom model connects through a production-grade MCP server exposing 30 tools for full CRUD operations across companies, people, opportunities, tasks, and notes without a single line of integration code. The 22 custom field types include text, email, phone, currency, date, select, multiselect, entity relationships, conditional visibility rules, and per-field encryption — all configurable through the UI without database migrations or code changes. Multi-team isolation enforces data boundaries through a 5-layer authorization system with team-scoped workspaces, API tokens, and granular permissions. The JSON:API REST surface provides Spatie QueryBuilder filtering, sorting, and pagination with schema discovery endpoints that let agents introspect your data model at runtime. A built-in AI chat connects directly to CRM data for natural language queries, while the external MCP server gives any compatible agent the same 30-tool access. Docker Compose deployment runs five containers — app (nginx + PHP-FPM), Horizon queue worker, scheduler, PostgreSQL 17, and Redis 7 — with automatic migrations on startup and demo data seeding for new teams. 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.

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

Archestra delivers the enterprise AI infrastructure layer that organizations need when managing multiple LLM providers, MCP servers, and AI agents across teams becomes unmanageable. The LLM gateway routes requests across Anthropic, OpenAI, Azure, Bedrock, and DeepSeek with virtual API keys, per-team cost limits, and dynamic model routing — giving every developer one token for Claude Code, Cursor, or Codex while finance tracks spend per department. The MCP gateway authenticates tool calls with OAuth 2.1 and On-Behalf-Of tokens so each tool executes as the calling user, not a shared service account, eliminating credential sprawl. The private MCP registry lets teams publish custom tool servers with approval flows promoting servers from dev through staging to production, each environment maintaining its own credentials and network egress policies. The Kubernetes operator manages MCP server lifecycle — deploying containers, scaling, health-checking, and routing gateway traffic to local servers automatically. The agent runtime supports scheduled triggers, email and webhook invocations, sub-agent delegation, reusable skills, and sandboxed code execution with a K8s-native filesystem. Deterministic guardrails including Dual-LLM verification and Lethal Trifecta protections prevent dangerous tool calls before execution. Built-in OpenTelemetry traces and Prometheus metrics provide full observability without additional tooling. Docker deployment exposes the Admin UI on port 3000 and API on port 9000 with a single command. 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.

DeerFlow 2.0 is ByteDance's ground-up rewrite that transforms what began as a Deep Research framework into a batteries-included super agent harness handling tasks lasting minutes to hours autonomously. Built on LangGraph and LangChain, the runtime orchestrates a lead agent that plans, decomposes, and delegates to sub-agents executing in isolated Docker or Kubernetes sandboxes with persistent filesystem access, while an extensible skills system lets developers add capabilities as Python functions or MCP servers with OAuth token flows. The harness ships with long-term memory using persistent event loops with per-agent isolation, scheduled task execution via cron, context engineering with manual compaction, and a web UI at localhost:2026 for interactive sessions. Model support spans OpenAI GPT-4o/GPT-5, Anthropic Claude via OAuth, Google Gemini, DeepSeek, Qwen via vLLM, and OpenRouter-compatible gateways with per-model pricing configuration. IM channel integration connects Telegram, Slack, Feishu/Lark, Discord, WeChat, WeCom, DingTalk, and Buzz without requiring a public IP — all using long-polling or WebSocket transports. Production deployment uses Docker Compose with nginx reverse proxy, PostgreSQL or SQLite persistence, Redis stream bridges for multi-worker scaling, and lease-based run ownership with automatic orphan recovery. The terminal workbench TUI enables headless operation. 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 107,000 GitHub stars and adoption by teams at Mozilla, 1Password, Peerlist, and thousands of startups, Supabase has become the most widely deployed open-source Firebase alternative — built entirely on PostgreSQL rather than a proprietary NoSQL store. Every project provisions a dedicated Postgres database with 40+ preinstalled extensions, auto-generating REST APIs via PostgREST, GraphQL via pg_graphql, and real-time change streams via an Elixir-based WebSocket engine that supports database change listeners, user presence tracking, and arbitrary broadcast messaging. Authentication covers email and password, phone OTP, magic links, and 20+ social providers including Google, GitHub, Apple, Azure, and SAML SSO, all enforced through Postgres Row Level Security policies that run inside the database itself. S3-compatible object storage delivers files through a CDN spanning 285+ cities with on-the-fly image transformations powered by imgproxy. Edge Functions run globally distributed TypeScript on the Deno runtime with Node.js compatibility and access to over two million NPM packages. The pgvector extension stores, indexes, and queries vector embeddings for AI-powered semantic search and retrieval-augmented generation workflows. Supabase Studio provides a browser-based dashboard with a table editor, SQL editor, schema visualizer, and log explorer. Official client SDKs ship for JavaScript, Python, Flutter, Swift, Kotlin, C#, Go, and Ruby. The self-hosted Docker Compose stack runs fourteen coordinated services including Kong API gateway, Supavisor connection pooler, and Logflare analytics. 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.

Your own Heroku or Vercel on a dedicated server — Dokploy is the open-source PaaS that replaces cloud platform subscriptions with a single dashboard you control. Point it at a Git repository or a Docker image, and it builds and deploys the application using Dockerfiles, Nixpacks, or Heroku/Paketo buildpacks. Traefik handles reverse proxying, routing, load balancing, automatic Let's Encrypt SSL, and HTTP/3. Databases — MySQL, PostgreSQL, MongoDB, MariaDB, libsql, and Redis — provision from the UI with automated backups to any S3-compatible destination. Complex multi-service applications deploy through native Docker Compose support, and multi-node scaling uses Docker Swarm. The web dashboard covers environment variables, volumes, resource limits, real-time CPU/memory/network monitoring, and deployment logs, with a CLI and REST API for automation. Deploy notifications go to Slack, Discord, Telegram, or email. One-click templates install common open-source tools, and a single control plane can manage deployments across multiple remote servers. Because everything is standard Docker, there is no lock-in: Dockerfiles, Compose files, and data volumes work anywhere else Docker runs. The push-to-deploy workflow of a $20/seat cloud PaaS, running on a dedicated VPS with guaranteed CPU, RAM, SSD, and full root access — no per-app, per-environment, or per-seat fees regardless of how many applications you deploy. 26,000+ GitHub stars.

NanoClaw delivers a radically simple alternative to OpenClaw — a single Node.js process and a handful of files that provide the same core functionality with true container-level security isolation. Agents execute inside Docker containers on Linux or Apple Containers on macOS, where even root access inside the sandbox cannot reach the host filesystem. The platform natively runs Claude Code via Anthropic's official Claude Agent SDK, with drop-in alternatives including OpenAI Codex, OpenRouter via OpenCode, Google, DeepSeek, and local open-weight models via Ollama — configurable per agent group. Multi-channel messaging connects WhatsApp, Telegram, Discord, Slack, Microsoft Teams, iMessage, Matrix, Google Chat, Webex, Linear, GitHub, WeChat, and email via Resend, installed on demand through skill commands. Each agent group receives its own CLAUDE.md memory file, isolated filesystem, container sandbox, and session state — a prompt injection in one group cannot exfiltrate data from another. The OneCLI Agent Vault handles credentials so agents never hold raw API keys, while approval-gated self-modification allows agents to request new packages or MCP servers that administrators must authorize. Scheduled tasks run recurring jobs inside containers with message delivery back to users. The setup script handles dependencies, authentication, and container configuration through Claude Code conversation. Deploy on any Docker-capable Linux server. 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 open-source PaaS with 55,000+ GitHub stars and the largest one-click service catalog in its class — Coolify gives you the Vercel push-to-deploy workflow on a dedicated server you control. Connect a GitHub, GitLab, Bitbucket, or Gitea repository and every push builds and deploys automatically via Nixpacks, a Dockerfile, or Docker Compose, with Traefik or Caddy reverse proxying, automatic Let's Encrypt certificates, and per-branch preview deployments with their own URLs. Databases — PostgreSQL, MySQL, MariaDB, MongoDB, Redis — provision in a few clicks, and a catalog of 280+ one-click service templates covers WordPress, n8n, Grafana, MinIO, Plausible, Ollama, and more. One dashboard manages the entire server, with Docker Swarm available for clustering multiple nodes. Backups go to any S3-compatible storage with one-click restore, and a full API supports CI/CD integration. All configuration lives on your own server, so resources keep running even if you stop using Coolify — no vendor lock-in by design. Running on a dedicated VPS with guaranteed CPU, RAM, and SSD, full root access via SSH and browser console. Apache 2.0 licensed.

With over 37,000 GitHub stars and used by teams at Y Combinator, Airbus, and Phantom, PostHog replaces an entire stack of paid analytics tools — Mixpanel, Amplitude, Heap, LaunchDarkly, Hotjar, and Google Analytics — with a single open-source platform where every tool shares a common event layer and user context. Product analytics captures events automatically or via manual instrumentation with HogQL (SQL) access for custom queries, while web analytics provides GA-like dashboards for traffic, conversions, and Core Web Vitals. Session replay records user interactions with DOM snapshots and network waterfall analysis, linking directly to errors and feature flag exposures. Feature flags safely roll out changes to specific cohorts with multivariate support and instant rollback, while experiments run A/B tests with automatic Bayesian significance calculations and revenue attribution. Error tracking captures stack traces linked to session replays and user properties for immediate reproduction context. AI observability monitors LLM generations, traces, token usage, latency, and costs across model versions. The managed data warehouse syncs 120+ external sources including Stripe, Postgres, Salesforce, and HubSpot alongside product events, queryable through a unified SQL editor. An MCP server enables AI agents in Cursor, Claude Code, or VS Code to query analytics and execute SQL directly. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

OmniRoute is an AI gateway, aggregating 338 LLM providers including OpenAI, Anthropic Claude, Google Gemini, DeepSeek, Kimi, MiniMax, and GLM into a single OpenAI-compatible endpoint at localhost:20128. The gateway catalogs over 1,200 models across 90 free-tier providers and 40 free-forever providers, automatically rotating through tier-1, tier-2, and tier-3 fallback chains when any provider exhausts its quota or returns errors. RTK plus Caveman stacked token compression reduces eligible context by 15 to 95 percent before forwarding requests, cutting API costs dramatically without degrading output quality. OmniRoute exposes its full routing engine through a built-in MCP server with 104 tools across 31 scopes over stdio, HTTP, and SSE transports, plus an A2A protocol server with six autonomous agent skills and JSON-RPC 2.0 streaming. The gateway integrates directly with Claude Code, Cursor, GitHub Copilot, Codex CLI, OpenCode, and Cline through standard base-URL configuration. Seventeen routing strategies include latency-optimized, cost-minimized, and auto-scoring modes that evaluate candidates on success rate, context fit, model fitness, quota state, and circuit-breaker health. The Next.js dashboard provides real-time provider status, usage analytics, combo chain configuration, and model catalog browsing via a responsive 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 37,400+ GitHub stars and active daily development by the Harness engineering team, Gitness is the open-source developer platform that ships Git hosting, container-native CI/CD pipelines, a Docker-compatible artifact registry, and cloud developer environments in a single Go binary consuming approximately 100 MB of RAM — compared to GitLab's 4+ GB minimum footprint. Born as the next generation of Drone CI, Gitness inherits Drone's battle-tested pipeline engine while adding complete source code management with pull requests featuring threaded code review comments, suggested changes, required reviewer approvals, and merge strategies including squash and rebase. Branch protection rules enforce mandatory pull requests, minimum peer reviews, passing status checks, and force-push blocking. Pipelines use Drone-compatible YAML syntax with stages, steps, and service containers, triggered automatically on code changes with results displayed directly in pull request checks. The built-in container registry eliminates the need for separate Harbor or Docker Registry deployments, supporting Docker image push and pull plus Helm chart storage. Gitspaces provide on-demand remote development environments configured via industry-standard devcontainer.json files. Encrypted secrets management with Gitleaks-powered secret scanning blocks commits containing hardcoded credentials. One-click migration imports existing GitHub Organizations and GitLab Groups, automatically converting GitHub Actions and GitLab CI pipelines to Gitness YAML. The REST API with OpenAPI specification enables programmatic management of all resources. 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.

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

Claiming 60-80% token cost reduction compared to flat single-model deployments and backed by 6,500+ GitHub stars, OpenSquilla delivers an intelligent AI agent runtime where a local ML classifier evaluates every turn on message length, code blocks, keyword patterns, and semantic embeddings before routing it to the optimal model tier from C0 through C3. The pluggable provider layer connects natively to TokenRhythm, OpenRouter, OpenAI, Anthropic, Ollama, DeepSeek, Gemini, DashScope, Moonshot, Mistral, Groq, Zhipu, SiliconFlow, vLLM, LM Studio, and additional compatible backends with primary-plus-fallback selection. The four-tier cognitive memory architecture spans working, episodic, semantic, and raw layers with vector-semantic and BM25 retrieval powered by on-device ONNX embeddings that never leave your infrastructure. Security isolation operates at the syscall level via Bubblewrap on Linux and Seatbelt on macOS, complemented by policy-based execution controls and prompt injection protections. The unified TurnRunner executes identically across the Vue-based control console Web UI, terminal CLI, and chat channel integrations including Slack and Discord, ensuring consistent tool dispatch, retry logic, and decision logging regardless of entry point. Built-in skills cover deep research, multi-search-engine queries, document generation for DOCX, PPTX, XLSX, and PDF formats, GitHub integration, cron scheduling, and bounded subagent delegation. Per-agent workspaces with durable session storage provide transcript replay, context state management, and per-call cost tracking with automatic quota enforcement. 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.

Scoring 64.4 on the WebBench benchmark — state-of-the-art among browser automation platforms — Skyvern replaces brittle XPath-based scripts with Vision LLM reasoning that adapts when websites change their layouts. The platform extends Playwright with AI-powered page methods including page.act(), page.extract(), and page.validate() that accept natural language prompts while still supporting traditional CSS selectors as fallback. The drag-and-drop Workflow Studio offers 17+ block types including navigation, extraction, login, loops, conditionals, code blocks, file download, and file upload — enabling non-technical users to build complex multi-step automations without writing code. Self-hosted deployments support bring-your-own-LLM with OpenAI, Anthropic, Gemini, and Ollama, while the multi-engine architecture allows swapping between Skyvern 2.0, OpenAI CUA, Anthropic CUA, or UI-TARS per task with a single parameter. Built-in infrastructure handles persistent browser sessions preserving cookies and localStorage across runs, automatic CAPTCHA solving for reCAPTCHA and hCaptcha, anti-bot bypass for Cloudflare and DataDome, residential proxy rotation across 20+ countries, and a credential vault integrating with Bitwarden and 1Password for secure 2FA management. Real-time session livestreaming via WebRTC enables visual debugging, while step-by-step action logs with screenshots and full LLM diagnostic traces provide production observability. The MCP server integration exposes Skyvern as a tool for Claude, Cursor, Windsurf, and any MCP-compatible AI agent. Connect to 6,000+ apps through Zapier, Make.com, or self-hosted N8N workflows. Deploy via Docker Compose or pip install with a two-command setup. 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.

Between your databases and everything that consumes data - BI tools, embedded analytics, AI agents - sits Cube (formerly Cube.js), an open-source semantic layer. Metrics, dimensions, joins, and access rules are defined once as code in YAML, JavaScript, or Python, forming a governed data model that every downstream consumer shares, so "revenue" means the same thing in every dashboard. Caching is two-level: an in-memory cache absorbs bursts of identical queries, and declared pre-aggregations - rollup tables built in the warehouse or in Cube Store, Cube's distributed columnar engine, and refreshed in the background - deliver sub-second latency while cutting warehouse compute costs. The query planner routes each request to cache, rollup, or source automatically. Consumers connect through a Postgres-compatible SQL API (any tool that speaks Postgres works), plus REST, GraphQL, and a Meta API for model introspection. Row-level security and multi-tenancy are enforced in the layer itself, upstream of every client. Sources include Snowflake, BigQuery, Databricks, Postgres, MySQL, Presto, and Athena. Headless by design - bring your own UI.

Pi Web is a browser interface for the Pi coding agent ecosystem, providing a visual workspace that reads the same local configuration and session files as the CLI. The session workspace groups conversations by project with running state indicators, context usage percentages, cost tracking, and compaction details, while two branching modes let users create independent session files from earlier messages or fork branches within existing sessions to explore alternative coding directions. Real-time streaming via Server-Sent Events delivers agent responses with structured Markdown rendering, thinking steps, tool call visualization, and image drag-and-drop input. The project file explorer browses working directories with syntax-highlighted source preview, Git diff inspection, and rendering for Markdown, images, audio, PDFs, and DOCX files with automatic refresh. Git worktree support switches checkouts from the sidebar while keeping sessions from the same repository grouped together. The Models panel manages provider authentication via OAuth and API keys, model selection, model smoke tests, and models.json configuration shared bidirectionally with the CLI agent. The Skills panel lists, searches, installs, and toggles agent skills without terminal access. The interface ships with English and Simplified Chinese translations, light and dark themes, a chat minimap, keyboard shortcuts, and completion sounds. Basic Auth protects remote access when binding to non-loopback addresses. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.