Unsloth puts the whole open-model workflow in one browser tab: pick a model, chat with it, train it, and ship it. Search a model hub, load a GGUF, and talk to it with web search, deep research, file uploads, and sandboxed Python or shell execution that asks before anything risky runs. Line up two models side by side to compare answers, or generate images and video with diffusion models. When a base model is not quite right, a five step wizard sets up fine-tuning with LoRA, QLoRA, FP8, or full training, and a live dashboard charts loss, gradient norm, step progress, and GPU memory. Data Recipes turn PDFs, CSVs, and Word files into question and answer pairs or instruction datasets without hand labeling. Finished models export to GGUF or safetensors for llama.cpp, vLLM, Ollama, and LM Studio. An access token screen exposes an OpenAI-compatible endpoint so Claude Code, Codex, and OpenCode can drive local models. Secure HTTPS links reach the interface from any device. 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 and AGPL-3.0 licensed.

Pinchy gives every team its own AI assistants without handing any of them the keys to the building. Create an agent per role, pick a personality preset like the Butler or the Professor, and choose a model from Anthropic, OpenAI, Google, any OpenAI-compatible endpoint, or a local Ollama. Each agent starts with nothing allowed. You switch on memory, file creation, web search, email, and other tools one by one, and point knowledge base agents at read-only folders so answers arrive with the source document and page cited. A new user meets Smithers, an onboarding assistant that interviews them to learn how they work. Colleagues reach agents in the web chat or in Telegram, with one bot per agent and the same permissions behind both. Email connects to Gmail, Microsoft 365, or any IMAP mailbox for reading, searching, and drafting, and Odoo templates handle sales and invoice chores inside your ERP. Admins invite members, and a tamper-evident audit trail records who did what, with integrity checks and CSV export. 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.

Light-Interview is a practice room for job interviews where you answer out loud and get a scored report afterwards. Fill in a target role, company, job description, and resume, and the app writes a question set to match. A digital interviewer reads each question, listens, and asks a follow-up when an answer is thin, and the browser records every answer on its own. Reports show relevance, completeness, professionalism, STAR structure, logic, speaking pace, pauses, and filler words, with the transcript beside the recording so you can jump to the moment that cost points. Rewrite a weak answer, record it again, and compare the two takes. Answers below the pass line land in a mistake book for retries, and each job goal gets a daily three question plan and a weekly review. Coding assessments run in a web editor with Java, Python, C++, JavaScript, and Go, judged in disposable containers with no network access. A resume library, spoken English and Japanese practice, and study groups with peer review round out the toolkit. 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.

OpenKnowledge turns a folder of markdown files into a workspace where you and an AI agent can write in the same document. The editor feels like a Notion page but saves plain markdown, with a visual mode, a markdown mode, a properties panel for titles and tags, and a file navigator with search and tabs. Ask Claude, Codex, or another harness to draft a recap, and the edit appears beside the chat as you watch. Select any passage and leave a comment, then send all open comments to the agent in one message. A timeline panel lists every change with a before and after diff, so an agent's rewrite is easy to review and undo. Skills Studio covers writing, browsing, and installing agent skills, and it can link one skills folder across Claude, Cursor, Codex, and others. Starter packs set up LLM wikis and second brains, and a graph view shows how wiki links connect pages. Git sync shares a knowledge base with teammates, and rich components like callouts, tabs, and diagrams make specs readable. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. GPL-3.0 licensed.

Super Agent Party gives you an AI companion with a face, a memory, and a to-do list, all running on your own server. The home screen starts a chat, summons a companion, creates a role or agent, queues a task, opens an AI browser, or adds an extension. Characters can appear as VRM 3D avatars, and character cards with long-term memory let several personas talk together in one group chat. The Task Center hands longer jobs to an agent that works in the background, calls tools through MCP and Agent Skills, and records every step in an execution timeline. A built-in browser lets agents open pages and act on them, and desktop vision tools can drive the mouse, keyboard, and terminal. One-click bot deployment connects an agent to Telegram, Discord, Slack, QQ, WeChat, Feishu, and DingTalk, and live-stream bots cover Bilibili, YouTube, and Twitch. The developer page serves an OpenAI-style endpoint, so other apps can call an agent as if it were a model. Extensions open in a sidebar or their own window. 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.

Xinference lets a team swap a hosted model API for models running on its own machines, with the same client code and a web console for managing them. The Launch Model page lists 300+ models across language, vision, embeddings, reranking, images, audio, video, and experimental world generation, and a Recommend configuration button fills in engine, size, format, and quantization for your hardware. Custom models, including traditional machine learning models, can be registered beside the built-in ones. Chat models can run on vLLM, SGLang, TRT-LLM, Transformers, llama.cpp, or MLX across CPUs, GPUs, and Apple Silicon. Workers and replicas can be added to serve one large model across several machines. Running Models shows each replica and a built-in chat window, and Performance Tests measure throughput and latency at several concurrency levels, with saved runs to compare. Endpoints speak the OpenAI and Anthropic protocols with streaming and tool calling where a model supports it. API keys, user management, and an audit center cover access control. The interface is available in five languages. 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.

cvENGINE takes a domain name and returns a verdict on which of today's exploited vulnerabilities can actually reach you, with evidence attached. Continuous discovery builds a Shodan-style inventory of subdomains, IPs, ports, products, versions, certificates, and technologies, then rates every CVE as fire, smoke, or ice from real exploitation sources and scores each host from 0 to 100. Read-only validation reproduces a finding and records the exact command used. Optional AI triage sorts matches into confirmed, likely, or needs validation. A live dashboard, a change timeline with screenshot diffs, saved searches with alerts, and one-click PDF reports keep teams current. Sentinels run scans from other machines, including inside private networks, and an optional OpenVAS add-on extends coverage. Hygiene checks cover TLS, email and DNS records, exposed databases, cloud storage buckets, and WordPress sites. Organizations, roles, two-step sign-in, a REST API, and Slack, Discord, Telegram, and Lark alerts support shared use. A bug bounty workbench imports program scope and drafts reports. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. GPL-3.0 licensed.

Voicebox is a voice studio that clones a voice from a few seconds of audio and then speaks any script in it, all on hardware you control. Eight speech engines cover multilingual cloning, preset voices, voices described in plain words, and expressive tags like laughs and sighs, across 23 languages. Long scripts are split at sentence boundaries and crossfaded, so chapters and articles render in one pass. A post-processing rack adds pitch shift, reverb, delay, chorus, compression, and filters, with presets like Robotic and Radio. The Stories editor lays voices on a multi-track timeline for podcasts and dialogues, then exports the mix. Voice profiles can be recorded in the app, imported, exported, and given personas that a bundled local language model uses to compose, rewrite, or respond. Global dictation turns a held hotkey into transcribed text with optional cleanup of filler words. A built-in MCP server and REST API let coding agents call a single speak tool and talk back in a cloned voice. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Daily Stock Analysis reads your watchlist every trading day and hands back a decision dashboard, with a score, a trend call, entry and exit levels, risk alerts, and catalysts for each stock. Quotes, K-lines, technical indicators, announcements, news, and fundamentals from several data sources feed a report written by the language model you connect, including Gemini, Claude, OpenAI-compatible endpoints, DeepSeek, or a local Ollama model. The web workspace covers manual analysis, task progress, history, full Markdown reports, backtesting, portfolio tracking, settings, and light and dark themes. Strategy chat answers follow-up questions in multiple turns using 15 built-in strategies, from moving-average crossover to Chan theory and wave theory. Smart import reads a screenshot, CSV, Excel file, or clipboard text to build the watchlist, with code, name, pinyin, and alias autocomplete. Reports are delivered to WeChat Work, Feishu, Telegram, Discord, Slack, or email on a schedule that skips market holidays. A market review summarizes index moves, breadth, and leading sectors. ETF rotation backtests compare annual results and flag data quality problems. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

GPUStack is a control plane that turns a pile of GPU servers into a model-serving platform, where you pick a model from a catalog and the system decides which machine, engine, and settings run it. Deploy language, embedding, reranker, speech, and image models from the Catalog page, then watch each replica move from downloading to Running on the Deployments screen. A built-in Playground offers chat, side-by-side model comparison, embedding and rerank testing, audio, and image generation and editing, so a model gets judged before it is wired into an app. Add GPU workers with a generated Docker command, register a Kubernetes cluster, or provision cloud machines, and manage several clusters from one server. Create API keys for teammates, apply access control, and read token, GPU-hour, and storage usage by user, key, or model. Auto Tune benchmarking searches for the highest throughput that still meets your latency targets. GPU Instances hand out SSH-accessible machines for fine-tuning and interactive work. Single sign-on works through OIDC or SAML. 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.

Describe a website, slide deck, document, 3D scene, or animation, then shape it with chat and a full visual editor in your own workspace. Templates give every project a head start, and a short brief about the goal and audience steers the first draft. The editor offers layers, flex and grid layouts, reusable design systems with palettes and fonts, component libraries, and live human and agent editing on one versioned document. The 3D mode handles materials, lighting, camera, rigging, and morph targets, and the motion tools animate bones, skins, and clips. Bring your own keys for OpenAI, Anthropic, Gemini, OpenRouter, or DeepSeek to generate text, images, speech, music, and video. Finished work exports as HTML, SVG, PNG, PDF, PowerPoint, WebM, GLB, or a React prototype, and snapshots can be shared publicly. Agents connect through REST, an authenticated MCP endpoint, or a command line tool, and an activity view records provider calls and usage. Accounts use email and password, with optional GitHub sign-in. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Watch every coding agent you run, on every machine, from one live browser dashboard. Sessions appear as cards, a sortable list, or a graph, grouped by machine or project, each showing its plan and current step, subagents, model and effort, context fill, git branch, and cost. Anything waiting on you, like a permission, a question, or a plan to approve, rises to a Needs you panel with the longest wait first, and you can answer it from the page or in the terminal. A Problems panel flags sessions that are stuck, failed, or colliding on the same file. The Plans board sorts every plan step into pending, in progress, review, blocked, and done. A session page adds a timeline of loops and subagents, changed files, and token and context charts. Spend is broken down by model and machine, and plan windows show how close each provider is to its limit. History keeps ended sessions by day, a wall view suits a spare screen, and browser alerts fire when a session needs you. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Point every coding agent and chat client at one self-hosted gateway, then choose which model answers from a single browser console. Add providers by preset or custom OpenAI-compatible URL, or sign in with the subscriptions you already pay for. Routing groups bundle several models into one name and move to the next member when a quota runs out, so the calling agent never sees the error. Create a gateway key per client, cap each with daily token or cost budgets, restrict its models, and watch usage counted separately. The Usage pages chart tokens, cost, request counts, cache hit rate, and a yearly heatmap, split by model, provider, or agent, with CSV export. A Routing view replays how each request was routed, with timing for masking, connecting, and the vendor. Masking swaps passwords, API keys, and tokens for placeholders before a prompt leaves your server and restores them in the answer. The browser page is protected by a key you set at launch. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

One self-hosted admin console runs a team of AI agents you can reach by voice, chat, webhook, or schedule. Each agent gets its own model backend, system prompt, memory, tools, and voice, with OpenAI, Anthropic, Gemini, Ollama, or any OpenAI-compatible API behind it. A visual flow editor chains agents with routers, joins, loops, parallel fan-out, templates, and small code blocks, so a question can be sorted and answered by the right specialist. Every run is recorded as a step-by-step timeline you can open and read, and conversations are browsable per client. Connect tools through the Model Context Protocol, keep long-term memory in PostgreSQL, and store API keys as secrets that models only ever see as placeholders. Voice runs on the server with wake word detection and speech models, and clients cover a voice web app, Telegram, Discord, Slack, webhooks, and cron jobs. One password-protected console manages every agent, flow, and client. 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.

Put a one-click approval gate between your AI agents and anything destructive or expensive. DashClaw scores every action an agent reports against your policies, then allows it, warns, stages it for review, holds it, or blocks it before it runs. Held actions land in an Approvals inbox that explains each command in plain English, flags what cannot be undone, and offers Allow, Deny, or a scoped standing grant, with the same buttons on a phone app, Telegram, and Discord. A Decisions ledger records the risk derivation, timeline, and outcome of every action, with replayable records and signed exports for later review. Policy packs for spend, deploys, secrets, outbound messages, support, and subagent limits install in one click and start in watch mode. Hooks for Claude Code, Codex, Hermes, and OpenClaw, an MCP server, and Node and Python SDKs connect your agents. Overnight coding runs stay supervised without anyone staying awake. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Hand your security alerts to a team of AI specialists and keep the final say on every action. Argus pulls events from cloud, identity, code, endpoint, and Kubernetes sources, runs fifteen detection rules, and turns matches into deduplicated findings enriched with CISA KEV and EPSS scores. Nine specialist agents hunt for evidence, build timelines, estimate blast radius, and propose fixes, but their only write path is a pending request that waits for human approval. Response playbooks can block an attacker or isolate a laptop through a catalog of 27 typed actions, starting in shadow mode with dry runs, caps, automatic rollback, and a tenant kill switch. Plant canary tokens aimed at rogue AI agents, replay eight simulated agent-driven attacks, and route OpenAI and Anthropic traffic through a gateway with model allowlists and budgets. Every step is written to a signed audit chain. A self-hosted command center with roles, TOTP sign-in, and Slack approvals fits small teams that have no SOC of their own. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Give your AI assistant a name, a memory you can actually inspect, and a permanent seat on your own server. OhMyBuddy has two sides that share the same models and tools. The Buddy side keeps one ongoing conversation, learns your preferences, and shows a receipt under any reply that saved something, so every memory can be reviewed, edited, or undone. The Workspace side opens real project folders with threads, streaming tool calls, file diffs, side chats, and a branching history view. Add scheduled tasks, an artifacts library, and a media lab for image, video, and speech generation. Connect extensions, MCP tools, a browser, and subagents when a job needs more hands. Sessions live on the server, so a laptop, a tablet, and a phone home screen all continue the same chat, with notifications when a reply finishes. Bring Claude, GPT, Gemini, DeepSeek, or any OpenAI-compatible relay, and protect the instance with an access token. Keep a personal AI on hardware you control, reachable from every device you own. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. ISC licensed.

See exactly what your documents look like before a retrieval pipeline swallows them. Chunky puts the original PDF next to the converted Markdown with page-aware scrolling, so broken tables, scrambled columns, and stray artifacts are visible at a glance. Pick a converter, edit the Markdown by hand, then split it into color-coded chunks you can edit, delete, or enrich one at a time. Compare two converters on the same pages in a side-by-side dialog to find which one handles your layouts best. Try token, recursive, sentence, semantic, table, code, and heading-based splitters with adjustable size and overlap, and save the chunk sets that work. Optional model-powered enrichment adds titles, one-sentence context, summaries, keywords, and retrieval questions to each chunk. Process many documents in one batch and export everything as a ZIP. Judge chunk quality by eye, not by guesswork, before any of it reaches an embedding model. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.