ShibaClaw
Meet an AI assistant that lives on your own server, remembers who you are, and keeps working after you close the tab. ShibaClaw opens with a four-step onboarding wizard for provider, credentials, and model, then drops you into a chat workspace with agent profiles for building, planning, reviewing, administering, and security work. Long-term memory lives in editable files, a dream diary records what the agent learned, and a Library view maps how profiles relate to each other. Agents call file, shell, and web tools, plug into external MCP servers, and hand work to isolated or forked sub-agents. The Automations page schedules one-shot, interval, or cron jobs like a weekday morning support brief, and a plugin catalog adds services like GitHub, Notion, PostgreSQL, and Google Workspace in one click. An optional knowledge base searches your own documents, and channel integrations reach the agent from Discord, Telegram, Slack, and Matrix. Provider choices span OpenRouter, Anthropic, OpenAI, Gemini, DeepSeek, Groq, Ollama, and any OpenAI-compatible endpoint. A credential vault encrypts keys, and file tools stay inside a restricted workspace. Anyone who wants research, drafting, and recurring chores handled by an assistant they host themselves will feel at home. 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.
Sara
Meet Sara, an AI companion with a personality you design and a coding partner that writes, runs, and tests real software, using any model you choose. Pick a name and pronouns, start from a character or set dials for playfulness and bluntness, and keep memories you can inspect, correct, and forget. Chat from the web app, Windows and Mac apps, Android, iPhone, Telegram, Discord, Signal, or email, and talk through live voice calls you can interrupt or video calls with her moving portrait. A planner turns plain sentences into to-dos, reminders, and notes, with a board, a Today home screen, and routines such as a morning briefing. The library reads PDFs, scans, Word, Excel, PowerPoint, and e-books, then answers with the document and page it came from. For code, each project gets a sandboxed workspace with files, a shell, and git; Sara asks before risky commands, shows test results as cards, and lists every command and its output under each reply. Goals finish only when your own check passes. Use Ollama, vLLM, or llama.cpp locally, connect OpenAI, Anthropic, xAI, or OpenRouter, or reuse the ChatGPT and Claude plans you already pay for. Connect coding agents over MCP, call an OpenAI-compatible API, and add plugins from a signed store. Business workspaces add passkeys, roles, and shared workspaces. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.
OvertChat
Your household gets one private chat front door for the models you already run, local or hosted, with voice, search, and coding agents included from the same server. Point it at Ollama, vLLM, llama.cpp, SGLang, or LM Studio, then add OpenAI, Anthropic, Gemini, DeepSeek, Bedrock, or OpenRouter beside them. Models that support tools can answer with charts, tables, forms, and follow-up buttons instead of plain paragraphs. Ask for a live conversation and speak, hear the reply, cut in mid-sentence, and keep going; Parakeet handles recognition and Kokoro speaks back on CPU or GPU. Documents open beside the chat for drafting and revising Markdown, code, web pages, SVG, and Mermaid diagrams. Attach spreadsheets, PDFs, images, Word, Excel, CSV, or source files and run Python on them in an offline sandbox that returns charts, cleaned data, or finished documents. Search the web through bundled SearXNG or Brave, read pages with inline citations, connect MCP servers, and set thinking controls per local model. Replies keep streaming after you close the tab, full-text search finds old answers, and read-only links share a conversation. Coding agents run on your machines or over SSH and stay reachable from browser, desktop, Android, or iOS. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.
Row-Bot
Conversations, goals, memory, and scheduled workflows live together in one private AI assistant that runs on your own server and opens in any browser, on a laptop or a phone. Chat with local models through Ollama, provider API keys, ChatGPT, Claude, or Grok subscriptions, or any OpenAI-compatible endpoint, and every tool call shows up in the transcript. Risky actions pause for Approve or Deny in the chat, on the Home screen, or on a connected channel. Memory grows into a personal knowledge graph with recall, review, and an Obsidian-compatible wiki vault. Ask for a deck, a mockup, or an app and a design or code panel opens beside the chat, with Present, export to PDF, HTML, PNG, or PPTX, a changes view, Git, pull requests, checks, and an interactive terminal. Goals keep going until done, delegated agents get their own conversations, and workflows run on a schedule, a webhook, or a chain, with run history and delivery to channels. Telegram, WhatsApp, Discord, Slack, and SMS channels, voice dictation, and an app catalog for GitHub, Notion, Linear, and Stripe extend it, and health checks propose one fix per problem. Pairing a phone takes a QR code and a one-time invitation, and the server serves a single owner across many devices. 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.
Online Document Editor
Open a browser tab and a full office suite appears, with no account to create and your files kept on your own device. Start a new Word document, spreadsheet, or presentation, or drop in a file, and edit with the familiar ribbon: styles and bullets in documents, formulas and charts in sheets, slides with layouts and notes. PDFs open for reading, commenting, highlighting, and filling, then save back out. Convert Word, Excel, and PowerPoint files to PDF, or move spreadsheets to CSV and back, without uploading a byte. An optional AI assistant, off by default, can rewrite, summarize, or translate a passage, fill spreadsheet cells, draft slides, or answer questions about a PDF page, using an on-device model or an AI service you connect. WebMCP tools let compatible browser agents open, convert, and export documents. Recovery copies stay in the browser for seven days, autosave can be switched off, and the site installs as a PWA for offline use. Host it as one static container or embed the editor in your own app through an iframe API. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. AGPL-3.0 licensed.
Typing Mind
Bring your own API keys and work with OpenAI GPT models, Anthropic Claude, Google Gemini, Mistral, DeepSeek, Grok, Azure endpoints, and local models in one organized workspace: TypingMind is a unified chat frontend for large language models, replacing a browser tab per provider. Parallel chat sends the same prompt to multiple models and compares answers side by side, and models can be switched mid-conversation. A prompt library stores reusable, tagged prompts with variables, and the AI Agents system builds specialized assistants that bundle a base model, custom instructions, assigned plugins, and uploaded knowledge files for RAG. Plugins extend every connected model with web search, image generation (DALL-E, Stable Diffusion), Deep Research, URL reading via Firecrawl, and Zapier automation - plus MCP server integrations for Notion, Atlassian, and other external tools, and a JavaScript extension API for custom behavior. Chats store locally by default with optional sync. Self-hosting puts the interface on your own domain and, for teams, adds branding, member access limits, and shared prompt and agent libraries.
Coddy
A single static binary is all it takes to put a tireless AI agent on your server, ready to read your codebase, run shell commands, edit files, and report back through a web UI, a terminal console, your editor, or a Telegram chat. Start it as a server and the embedded web interface gives you streaming chat sessions with visible tool calls, session history, plan documents, a background task board, and a visual map of connected nodes. Point any OpenAI-compatible client at its HTTP API, or drive the same sessions from Zed, VS Code, or Obsidian through the built-in ACP editor server. Delegate bounded work to subagents that run in isolated contexts with narrowed permissions, then resume them later in their own sessions if a run stops short. Teach it your project once: rules are picked up from .coddy, .cursor, .claude, and .codex folders, AGENTS.md files are honored as work proceeds, and installable skill packs turn repeatable procedures into slash commands. Schedule recurring jobs as plain Markdown files on a cron timetable, keep long-term memory across conversations, and connect external tool servers over MCP globally or per workspace. A Prometheus exporter reports provider calls, tokens, and task health for the whole fleet. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.
LISA
An open-source AI personal assistant that plans your day, drafts your messages, and remembers how you like to work, LISA keeps her memory as plain files you can read and restore. Ask for a plan and she replies in chat with tool activity visible, and any reply can be cancelled or retried. After a conversation she may refine her memories, and Rêve lists each change with its source conversation and a recoverable previous version. Links, articles, and video transcripts go into a searchable linked wiki, and daily briefs come from the RSS and Atom feeds you configure. Twenty-two read-only connectors reach GitHub, Google Calendar, Gmail, Linear, Google Drive, Slack, Box, and Obsidian; you authorize each account and pick what she may read. Telegram, Discord, Slack, Feishu, and webhooks put her on your phone, with allow-lists and a remote-safe toolset by default. Durable goals, scheduled routines, and local watchers keep working between chats. MCP servers, skills, and plugins add tools. Run chat on Anthropic, OpenAI, Gemini, an OpenAI-compatible service, or a local model through Ollama or LM Studio, so you decide which provider sees your context. A pixel-art room shows what she is doing, and the optional Warden policy adds an approval inbox with scoped grants and audit records. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.
Kompl
Save a link, a PDF, a YouTube video, or a bookmark export to Kompl and it reads the material on arrival, then writes it into cross-linked wiki pages instead of leaving it in a folder you never reopen. Save more on the same subject and the existing pages are rewritten, so source number fifty improves the pages it touches. Every claim carries a numbered citation back to the original text, and when two sources disagree the page records both sides with a confirm or dismiss button. A knowledge graph shows how topics connect, each link backed by the sentence that states it. An onboarding wizard stages pasted text, URLs, uploaded files, browser bookmarks, Twitter exports, Apple Notes, and Upnote exports for review before anything is compiled. Settings pick the compile model from DeepSeek or Gemini, cap daily spend, and show wiki health. Eight MCP tools let Claude Code, Cursor, Codex, and other agents search, read, and cite pages. Full backups export as one zip that restores without further model calls. 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.
ZeroClaw
ZeroClaw puts one personal AI agent on every messaging app you already use, answering from your own server with your own model keys. A single instance binds Discord, Telegram, Matrix, Slack, WhatsApp, Signal, email, and webhooks at once, so you can start a conversation on your phone and finish it at your desk without losing context. You choose the brain behind it: Anthropic, OpenAI, a local Ollama model, or any OpenAI-compatible endpoint, with fallback chains that keep the agent answering when one provider has a bad day. The agent acts through tools that run shell commands, drive a browser, call HTTP APIs, and talk to custom MCP servers you plug in. A web dashboard gives you chat, a memory browser, a configuration editor, cron job management, and a tool inspector from any browser. Long-term memory lives in SQLite on your disk with embedding-based recall, so past conversations stay searchable and private. Supervised autonomy is the default posture: medium-risk actions pause for your approval, high-risk actions are blocked outright, and operating system sandboxes plus cryptographic receipts keep every tool call bounded and auditable. Event-driven standard operating procedures react to MQTT messages, webhooks, schedules, and hardware events, and named agents let different personalities guard different channels. Registered as a system service, it stays online around the clock. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT or Apache-2.0 licensed.
Clay Studio
Clay Studio is a self-hosted workspace where your team and its coding agents share projects, live sessions, and project knowledge in one browser interface instead of scattering them across terminals. You organize several repositories in one sidebar and run sessions in parallel while teammates watch live activity, enter the same session, hand work off, and answer permission requests from wherever they are. Ten agent runtimes plug into the same workspace, Claude Code, Codex, Grok Build, Kimi Code, GitHub Copilot CLI, Qwen Code, Junie CLI, Antigravity CLI, OpenCode, and Kiro CLI, each keeping its own authentication and models. Persistent Mates give AI collaborators an identity, instructions, memory, direct messages, and roles in structured debates that survive beyond a single chat. Worktrees, paired sessions, spawned workers, scheduled tasks, and Ralph Loops let background jobs proceed without losing sight of what is running. You browse and edit files, inspect diffs and history, open terminals, install skills, connect MCP servers, and manage project knowledge without leaving the workspace. The installable PWA works on mobile and pushes notifications for approvals, failures, and finished work. Sessions and knowledge stay on your disk as portable JSONL and Markdown, so switching providers never means migrating your workspace. 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-only licensed.
octo-agent
One download gives you a coding agent and personal assistant that is ready to work after a single message. The agent runs shell commands, reads and edits files, searches the web, calls MCP servers over stdio or HTTP with OAuth, and splits work across parallel sub-agents. Chat from the terminal, the web dashboard, a desktop app, VS Code, Obsidian, an Android app, or IM bridges for Telegram, Discord, Feishu, DingTalk, WeCom, and WeChat. Bring DeepSeek, Kimi, Qwen, Anthropic, OpenAI, or any compatible endpoint, with prompt caching tuned for each provider to keep token bills predictable. Skills use the Claude Code SKILL.md format, so an existing skills folder works unchanged. Cross-session memory, scheduled tasks, reusable multi-agent workflows, and Chrome automation that records, replays, and repairs browser steps cover the repetitive jobs. Light Apps are small agent-built tools that run in the browser with no further tokens. Safety is built in: catastrophic commands are hard-denied, deleted or overwritten files go to a recycle bin first, and an OS sandbox can confine the terminal. There is zero telemetry, and the web dashboard loads no outside fonts or scripts. Expose the server on a VPS behind its auto-generated access key and reach the same sessions 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. MIT licensed.
Murmur
Every AI agent gets a face, a colour, and a job in Murmur, a chat app that makes running Hermes Agent as friendly as texting a colleague. Start from a template (Researcher, Writer, Planner, Coder, Coach, or Chef) or describe a new agent from scratch, then talk to one at a time or drop several into a group room and call on a single one with an at-mention. Replies stream in live, long jobs show a plan that ticks itself off, and every step appears in plain words. Connect a model with a ChatGPT plan, a local model server, or an API key from OpenRouter, OpenAI, Anthropic, and others, with the model and thinking effort chosen per agent or chat. Agents can reach Notion, Linear, Todoist, Figma, and dozens of other apps, and they ask for an Allow or Don't allow before changing anything important. Morning briefings run as routines, a memory view shows what each agent knows with controls to edit or forget it, and WhatsApp or Telegram can be linked by scanning a code. A voice call mode lets an agent answer out loud, and slash commands set long-running goals or ask quick side questions. Chats sync across browser, desktop, and phone. Solo builders, homelab fans, and small teams get a calm front door to their own agents. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.
Odysseus
Agents with tool use, deep research, a document editor, an IMAP/SMTP email client with AI triage, notes, tasks, and a CalDAV-synced calendar - Odysseus bundles all of it into one open-source, self-hosted AI workspace. It runs local models through Ollama, vLLM, or llama.cpp and cloud APIs like OpenAI and OpenRouter, with a hardware-aware Cookbook that scans your machine and recommends quantized models that fit. Persistent memory uses ChromaDB with hybrid vector-plus-keyword retrieval, web search runs through a bundled SearXNG instance, and agents can use MCP servers, files, and shell access with safety controls, plus custom skills and scheduled agent tasks. A blind Compare mode runs side-by-side model duels with identities hidden and accumulates Elo-style ratings from your votes, so model selection is based on your actual workloads rather than leaderboard claims. Deep research mode - adapted from the Tongyi DeepResearch approach - reads sources through SearXNG and produces cited reports, while the email client tags, summarizes, sets reminders, and drafts replies locally rather than through a third-party mail AI. The writing-first document editor adds AI edits, Markdown and HTML support, and version history. The stack is Python 3.11 with FastAPI, SQLite for state, and a vanilla JS frontend, licensed AGPL-3.0 with zero telemetry. Because agents can read email and execute commands, keep authentication enabled and never expose it as a public unauthenticated service.
Open Canvas
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.
AI Real Estate Assistant
AI Real Estate Assistant puts a conversational search engine on top of your own property catalogue, so buyers type a request in plain language and receive matched listings in return. A query about a two-bedroom apartment in a named city under a price limit becomes extracted filters, semantic ranking over the catalogue, and a shortlist that matches the words instead of a rigid form. Behind the chat sits a working toolbelt: a mortgage calculator, a rent-versus-buy comparison, ROI and total-cost-of-ownership estimates, and an AI valuation that projects a property value one, three, five and ten years ahead with a confidence band. Every listing card shows an estimated monthly payment, and every property page carries an AI neighbourhood summary covering district character, nearby amenities and ease of getting around. Interactive maps cluster markers by area, a city overview page compares markets across districts, and a documents section accepts uploaded files that visitors can question in the same conversation. An agent directory presents the people behind the listings together with their stock, and the interface speaks nine languages with compliance labels on AI output. The demo mode answers with a local model and needs no paid key, and a real deployment routes each request to any of sixteen providers. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.
OpenVoiceUI
OpenVoiceUI is the voice-first front end for a self-hosted AI agent that lives entirely on your own hardware; you talk, it answers out loud, and it builds live pages on screen while the conversation runs. Hold a hands-free conversation with wake word, push-to-talk, and the ability to interrupt, or switch to text when the room is quiet. Speech recognition runs in the browser for free or through Deepgram, Groq Whisper, or your own Whisper server, while nine speech providers from local Supertonic to ElevenLabs give the agent its voice, cloned voices included. As it talks, the agent opens live canvas pages, dashboards, galleries, reports, and tools, and files them on an OS-style desktop you can reopen from the start menu. Ask for music and it generates songs with a built-in player and playlists; ask for images and it creates those too, alongside an audio clip maker and a soundboard. Profiles swap the agent's persona, voice, and model provider, animated faces react while it speaks, and sub-agents and workspace files stay visible in the admin dashboard. The agent itself runs in the OpenClaw gateway with your choice of model provider, so your keys, conversations, and files never leave your 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.
stella
A legal team's matters, documents, and research can finally live in one tab that an AI agent can read. stella organizes work into matters, each with a file list showing author, version, status, and notes, plus correspondence and custom lists. Ask the agent about a whole data room and it replies with cited document chips and can turn the answer into a generated view for the partner meeting. Tabular Review pulls structured answers out of dozens of contracts into a table with status pills, due dates, and document types, ready to export as CSV, XLSX, or DOCX. A browser editor opens .docx files with version history, review, and anonymization panels, and a template library speeds up supply, lease, and share purchase agreements. The legal database covers court decisions, with search by case number or keywords and questions answered from the paragraphs of a judgment. Timesheets, contacts, and an inbox sit in the same sidebar, and an MCP server opens stella data to other agents. 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.