OpenCode Manager is a mobile-first command center for AI coding agents. Install the PWA on your phone or tablet and you get real-time streaming chat, multi-repository Git operations, and scheduled automation right in your pocket. Git integration handles SSH-authenticated repo cloning, worktree management, unified diffs, and branch operations across all your projects in one dashboard. Chat with coding agents through Server-Sent Events streaming that supports slash commands, @-mentions for files, Plan and Build modes, and Mermaid diagram rendering for architecture discussions. Schedule reusable prompts to run against any repository on intervals or cron expressions, with each run tracking history and linking to sessions so you can pick up exactly where automation left off. MCP server configuration adds local and remote HTTP servers with OAuth support, plugging into the broader Model Context Protocol ecosystem. A dedicated assistant workspace provides an isolated AI environment with auto-provisioned skills for managing schedules, notifications, and settings. Multiple AI providers are supported including Anthropic, GitHub Copilot, and OpenAI-compatible services, each configurable with custom system prompts and granular tool permissions. Push notifications alert you to session events, agent questions, errors, and task completions across all managed repositories.

ClipForge turns one product photo into a short selling video, extracting the selling points, writing the pitch, and keeping your product looking like itself instead of letting a generator redraw it. Paste a product link and it pulls the title, price, and images into a review form before anything enters your library, or start from a single sentence when the video is not about a product at all. Choose the free path and it composes with openly licensed stock footage, free voiceover, and local rendering, so your first video costs nothing and needs no API key. Choose AI generation and a script gate shows the full plan and price before a paid call, while a judge panel revises weak lines and a quality check can order a precise retake of only the bad segment. Ten script styles cover drama skits, unboxings, comparisons, talking heads, and pain-point pitches, with a different voice cast for each character in dialogue scenes. A library of 391 commerce templates, a variant matrix for hook and caption combinations, and resumable batch production let one person prepare dozens of platform-ready cuts for TikTok Shop, Reels, Shorts, Douyin, Kuaishou, and Xiaohongshu. Exports arrive without watermarks, with titles, hashtags, and caption copy ready to paste. 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 32,800 GitHub stars, 180 contributors, and version 3.2 shipping in July 2026, SurrealDB eliminates the database zoo by unifying document, graph, relational, time-series, geospatial, and key-value data models into a single Rust binary queried through SurrealQL — an intuitive SQL-like language that handles graph traversals, record links, subqueries, and computed fields without switching between multiple database engines. Purpose-built for AI applications, it integrates vector indexing, full-text search, and hybrid retrieval that blends semantic similarity with graph and relational intelligence for context-aware RAG pipelines and recommendation engines. Real-time subscriptions and event-driven triggers push live data changes to connected clients without requiring external message brokers like Kafka. Multi-row, multi-table ACID transactions guarantee consistency while incrementally computed views deliver pre-calculated analytics without batch processing. Role-based access control with record-level permissions, JWT authentication, and multi-tenant isolation enables backend-as-a-service usage where client applications connect directly with fine-grained security. SDKs for JavaScript, Python, Go, Rust, .NET, and Java connect via WebSocket or HTTP APIs. Storage and compute separation allows deployment as an embedded library, a single-node server, or a highly-scalable distributed cluster with TiKV or FoundationDB backends. Deploy via Docker with persistent volumes on any Linux host. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Source-available licensed.

When the connection drops, Project NOMAD keeps serving offline Wikipedia, Khan Academy courses, maps, and an optional private AI assistant from a single Debian-based Linux server. The core needs only about 5 GB of disk and under 1 GB of RAM. Content is what fills the drive, and a setup wizard sorts it into Essential, Standard, and Comprehensive tiers while a storage bar tracks the running total. Wikipedia runs from a quick-reference set of the top 100,000 articles to the complete English edition with images at about 121 GB, and Kiwix also serves medical references, survival and repair guides, and Project Gutenberg ebooks. Kolibri adds Khan Academy courses with multi-user progress tracking, and any browser on the network can study. Offline maps cover the whole globe, single countries, or regions, with markers you can search, color, and navigate to by coordinate. The AI assistant is the heavy part, bringing the install to roughly 25 GB. It chats through Ollama or any OpenAI-compatible server such as LM Studio, searches uploaded documents, lists sources with dates when known, and lets vision models read attached images. CyberChef handles encoding and hashing, and FlatNotes keeps Markdown notes. The Supply Depot adds one-click apps or your own Docker containers. Opt-in auto-updates for the Command Center, installed apps, and downloaded content run inside a window you set. 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.

Anyone who pays for Claude Code, Codex, and Gemini CLI separately ends up juggling three endpoints, three sets of keys, and three kinds of rate-limit surprise, and CliRelay collapses all of that into one self-hosted gateway with a control panel. Clients speak the OpenAI Chat or Responses, Anthropic Messages, or Gemini protocol, and CliRelay translates each request for whichever upstream account is healthy. Channel groups limit where each key may send traffic, round-robin, fill-first, and session-sticky scheduling spread it, and cooldowns with automatic failover move requests off accounts that have run out of quota. Add upstreams from the /manage console through browser sign-in, device codes, or bulk credential import, covering Claude, Codex, Gemini, Antigravity, Vertex AI, AWS Bedrock, Grok, Qwen, Kimi, and any OpenAI-compatible service. Portal accounts own client keys with daily, period, and lifetime quotas, RPM and TPM limits, and per-model pricing. A monitor center scores health and charts live traffic, P50 to P99 latency, and time to first token, while every request lands in a searchable log with tokens, latency, and cost. Tenants, roles with resource.action permissions, content moderation profiles, an outbound proxy pool, and an audit trail make shared deployments workable, and the console speaks English, Simplified Chinese, and Russian. 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 56,000+ GitHub stars and over 240 million Docker pulls, LiteLLM delivers the open-source AI gateway trusted by Netflix, Lemonade, Rocket Money, and thousands of engineering teams to route every LLM request through one unified API. The Rust-core gateway adds sub-millisecond overhead per request with 8ms P95 latency at 1,000 RPS, 15x throughput improvement and 11x lower memory footprint compared to Python-only proxies. A single OpenAI-compatible endpoint connects to 100+ providers and 1,800+ models spanning OpenAI, Anthropic, Google Gemini, AWS Bedrock, Azure OpenAI, Vertex AI, Hugging Face, vLLM, Nvidia NIM, Ollama, and Mistral with day-zero support for new model releases. The Auto Router V2 classifies request complexity across four tiers using rule-based scoring, semantic keyword matching, and adaptive Thompson sampling to route each request to the most cost-effective model without API calls or training data. Virtual API keys enable multi-tenant governance with per-team, per-user, and per-project cost tracking, budget caps with automatic fallback rerouting, and role-based access control. Built-in guardrails provide PII masking, prompt injection detection, and model-graded evaluation before requests reach providers. The Agent Gateway extends routing from model calls to agent workflows with MCP server integration. Observability integrates with Langfuse, Arize Phoenix, OpenTelemetry, and MLflow for complete request tracing. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

CubeSandbox gives every AI agent its own hardware-isolated MicroVM with a dedicated Linux kernel — not a shared-kernel container but a true KVM virtual machine — booting in under 60ms with less than 5MB of memory overhead per instance, enabling thousands of concurrent sandboxes on a single server via kernel sharing and Copy-on-Write memory. The Rust-built CubeProxy exposes an E2B SDK-compatible REST API on Axum, so existing E2B Cloud applications switch by changing one environment variable with zero client code changes. CubeMaster orchestrates cluster-level scheduling in Go while Cubelet manages node-local sandbox lifecycles including create, run, pause, resume, snapshot, and destroy operations. CubeVS, the eBPF-powered network layer, enforces per-sandbox isolation with LPM trie-based egress policies entirely in kernel space — no userspace context switches — while CubeEgress provides an L7 security proxy with per-domain, per-path, and per-method allowlists plus automatic credential injection that keeps secrets invisible to sandbox code. Hundred-millisecond-granularity snapshots enable checkpoint, rollback, and parallel fork from any saved state. The volume framework supports E2B-compatible pluggable storage with independent lifecycle and cross-sandbox sharing. Production deployment uses Terraform on Tencent Cloud or Helm charts on Kubernetes, K3s, or TKE, with full ARM64 support alongside x86_64 and AutoPause/AutoResume for cost optimization. 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.

Autonomous red team execution without manual script coordination is what PentaGI delivers through a multi-agent penetration testing platform engineered for automated security assessments. Security engineers configure testing scopes, target IP ranges, domain lists, and rules of engagement through an interactive web console with real-time execution graphs. Autonomous agent personas break down high-level assessment goals into discrete tactical phases, orchestrating network port discovery, service banner fingerprinting, web application crawling, and CVE verification. Specialized agents query integrated Graphiti knowledge graphs and local vulnerability repositories to synthesize attack paths, validate exploitability, and confirm finding veracity before issuing alerts. Operators monitor live agent terminal streams, inspect sandboxed tool executions, and adjust active LLM provider routes across OpenAI, Anthropic, or local Ollama endpoints. The template editor allows red teams to compose reusable testing playbooks with customizable security prompt chains, safety constraints, and automated remediation reporting. Audit logs capture full command histories, raw tool outputs, and LLM reasoning steps to generate compliance-ready technical 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.

Your apps keep using the OpenAI SDK while Antirion, a self-hosted AI gateway, decides which provider answers, what each team may spend, and what gets logged. Clients speak the OpenAI, Anthropic, Gemini, or Bedrock APIs, and Antirion translates between them, so a Claude deployment can answer an OpenAI-style call, streams included. Add providers such as Amazon Bedrock, Vertex AI, Mistral, Groq, DeepSeek, or a vLLM server, then publish them as named Models. Routing rules send traffic by team or project with fallback chains, weighted splits, least-cost or least-latency targets, retries, hedging, and circuit breakers. Budgets and rate limits in dollars or tokens apply per organization, team, project, and key, with projections and alerts before money runs out. Guardrails check for personal data, secrets, keywords, and regex matches, then block, redact, flag, or divert. Exact and semantic caching answers repeated prompts without calling a provider. The request log records every attempt, route, token count, cost, and guardrail verdict, with Prometheus metrics and OTLP traces. An MCP gateway and A2A proxy put tools and agents behind the same keys. Sign in with OIDC, SAML, or GitHub, provision users with SCIM, and review every change in the audit log. Changes you choose can require a change request or a second person's approval, and the Playground sends requests from the console. 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.

PenX delivers an open-source structured note-taking application that functions as a personal database disguised as an elegant editor — combining the outline workflow of Workflowy and Roam Research with the structured data capabilities of Tana through MetaTags that transform every note into a queryable database record. The local-first architecture stores all data on-device using PGLite, an in-process PostgreSQL-compatible engine, ensuring data ownership regardless of cloud connectivity. End-to-end encryption protects all synchronized data so that even the sync server cannot read your notes, tasks, ideas, or documents. GitHub-based version control provides out-of-the-box backup and history with full commit-level recovery. MetaTags are the core innovation — attaching structured tags to any note converts it into a database entry with typed fields, enabling table views, filters, and queries across your knowledge base without imposing rigid folder hierarchies. The daily notes workflow encourages free-form capture while MetaTags handle organization automatically, letting you record thoughts without deciding physical location upfront. AI-driven features assist with content generation, summarization, and intelligent search across your personal data hub. Real-time sync keeps web, desktop, and mobile in perfect alignment. Cross-platform availability includes web, desktop for Windows, macOS, and Linux, iOS, and Chrome extension. Deploy the web service via Next.js with pnpm using tRPC and Prisma. 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.

GeoLook shows you what AI search engines actually say about your brand, then turns that uncomfortable answer into a fix list you can work through and verify. You sample real answers across a wide matrix of AI engines and watch mention rate, ranking, and citation share appear per engine, with raw answer replay when a number looks suspicious. Competitor tables reveal which rival each engine prefers and which citation sources they rely on that you do not. A structured question bank sorts buyer, education, and probing questions, flagging the ones where you are absent, outranked, or described negatively. The site audit checks whether crawlers can reach, understand, and quote your pages, in the order those failures actually block visibility. Findings become tickets with an owner, effort estimate, risk grade, and acceptance check, and later sampling rounds confirm whether a fix worked or reopen the ticket when results slip. A content workbench ranks the topics most worth writing, checks drafts for citability, and prepares assets such as llms.txt and structured data snippets for publishing. 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 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.

With over 5,000 GitHub stars since its June 2026 launch, OOMOL OpenConnector bridges the gap between AI agents and the real world by handling the authentication nightmare that stops LLMs from calling external APIs safely. The runtime connects to more than 1,000 SaaS providers — GitHub, Gmail, Notion, Slack, Microsoft, HubSpot, Google Workspace, and hundreds more — through 10,000+ prebuilt typed Actions that agents can discover and execute without ever touching raw credentials. OAuth2 flows, API key rotation, custom credentials, and no-auth providers are all managed centrally with AES-encrypted storage, scoped runtime tokens, and configurable action allowlists and blocklists that enforce least-privilege access. Agents interact through five access surfaces: the Model Context Protocol endpoint at /mcp for Claude and other MCP-capable hosts, a full REST API at /v1 for programmatic control, an auto-generated OpenAPI specification for code generation, a TypeScript SDK for application integration, and the oo CLI for local agent relay. The built-in Web Console provides browser-based administration for configuring OAuth apps, managing connections, inspecting action schemas, and reviewing execution logs with redacted inputs. Deploy via Docker Compose with SQLite for single-server setups, run from source on Node.js 22+, or push to Cloudflare Workers with D1 and R2 for edge deployment. 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 7,700 GitHub stars and thousands of Cloudflare employees using it daily across every function, Cloudflare OS delivers an open-source AI workspace where every employee gets a personal agent grounded in company context, systems, and skills — not a generic chatbot but a programmable workspace that builds real applications, automates workflows, and connects to internal tools through governed access. The Code Mode agent writes and immediately executes code snippets to perform arbitrary tasks, build full-stack Gadgets with client code, server code, APIs, and durable SQLite state, debug errors, and test results within isolated sandboxes. Gadgets are private application instances running in separate sandboxes — each document, spreadsheet, or tool is its own secure runtime that cannot leak data even to attackers with access to other Gadgets. Blueprints enable sharing application code as templates that others instantiate with independent state, credentials, and resources. Gatekeepers provide security governance giving system owners precise control over what agents can see, change, and when human approval is required before actions execute. Built on Cloudflare Workers using Durable Objects for workspace persistence, Dynamic Workers for Gadget execution, and Facets for access management. Zero Trust security via Cloudflare Access verifies every user and request before granting access. Real-time collaboration lets colleagues use shared Gadgets. Deploy to your own Cloudflare account or self-host on workerd, the open-source Workers runtime, on your own servers. 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.

Codeman is a self-hosted mission control for AI coding agents that runs Claude Code, Codex, OpenCode, Gemini, Copilot, and five more agent CLIs in persistent sessions you can watch and steer from any browser, phone included. Sessions live in tmux, so agents survive server restarts, network drops, and laptop sleep, with full scrollback replay when you return. Run up to twenty sessions as tabs or in a six-up tile grid, each streaming its real terminal with token and cost tracking, and tabs that blink when an agent goes idle or needs an answer. Idle detection re-prompts stalled agents, and when a subscription usage limit hits, Codeman parses the reset time, waits it out, and resumes the run unattended. Subagents appear as floating live windows tethered to their parent session, with real-time transcripts, token counts, and status badges. Agents can drive Codeman too, through a bundled skill, CLI verbs, and an MCP server that let one agent start, prompt, and collect answers from workers in other CLIs. Run a project in an isolated Docker container or on another machine over SSH, preview agent-created files in the browser, and reach everything from your phone with QR login and push notifications, or over Tailscale with a real certificate. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

taOS is a self-hosted operating system for AI agents that lives on hardware you already own, offline by default and cloud only when you invite it. Open one URL and a full web desktop appears: floating windows, a dock, launchpad, widgets, notifications, and 43 bundled apps, from mail and kanban projects to an app store with over a hundred one-click installs. Agents deploy through a guided wizard into isolated containers (LXC on bare metal, Docker on a VPS), each with its own memory store, files, secrets, and network identity. taOS owns the agent lifecycle outside the framework, so you can swap SmolAgents for LangChain or OpenClaw and the agent keeps its history, channels, trained adapters, and API keys untouched. Long-term memory is a temporal knowledge graph with hybrid search on your disk, not a row in a vendor database, and the messages app works like a private Discord that also installs as a phone PWA. Local inference spans Apple Silicon, NVIDIA, AMD, Rockchip NPUs, Raspberry Pi boards, and salvaged Android phones, with auto-clustering that pools idle machines into one compute fabric. Messaging connectors cover Telegram, Discord, Slack, Matrix, email, and webhooks, and a rollback command returns the system to a known-good state when an experiment misbehaves. 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.

Minimax Music UI turns a self-hosted MiniMax-Music3 model into a private song factory, giving you a Suno-style studio where you describe a track, add lyrics, and watch finished songs appear in your own library. The Create panel works in Simple or Custom mode: write a style description covering genre, BPM, key, vocals, and arrangement, then shape words in a lyrics editor with one-tap [Verse], [Chorus], [Bridge], and [Instrumental] section chips. One submit can queue up to four takes at 5 to 360 seconds each, and the render queue shows queued, rendering, and done states with elapsed time, cancel, and retry, surviving a server restart without losing your place. When you run the bundled inference server, you can even press play on a track that is still rendering and hear the waveform grow in real time. A magic wand rewrites rough ideas into structured music captions, and a second wand drafts original lyrics sized to your chosen duration, both through any OpenAI-compatible model you point it at. Finished renders land in a searchable library with cover art, seeds, and render times, ready to download as WAV, reuse as a template, or open in a detail panel with the prompt and lyrics. A sticky waveform player with seek and keyboard shortcuts keeps music going while you work, and an optional access token locks the whole studio down. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.