With over 14,000 GitHub stars and 41 releases since its May 2026 launch, Prime Agent delivers a fundamentally different approach to AI coding agents by treating the agent's own operating environment as programmable state that improves through use. The Recursive Language Model architecture provides the model exactly one tool — a persistent IPython kernel — where file operations, shell commands, subagent delegation via rlm() function calls, and context management all happen through code rather than rigid tool-calling schemas. Subagents launch as independent sessions with their own model, kernel, and history, communicating results through agent_message.send() without blocking the parent. The Continual Harness stores supplemental prompts, memories, skill descriptions, and reusable subagent specifications as durable state that the /refine command updates through small, evidence-backed edits with full rollback by ID. Daemon-backed sessions keep running when the terminal disconnects, with automatic context compaction summarizing older messages while preserving recent state. The TUI provides an Agent View for monitoring, switching between, and steering multiple live sessions simultaneously. Autonomous mode operates within configurable turn, token, and time budgets with user-defined quality gates. Persistent goals, heartbeats, and scheduled prompts maintain continuity across terminal sessions. Compatible with Anthropic Claude, OpenAI, Google Gemini, local models via Ollama or vLLM, and Prime Inference endpoints. Install via a single curl command on Linux or macOS. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

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-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.

Formerly known as Danswer and now backed by over 31,000 GitHub stars with 253 releases, Onyx delivers a production-ready AI platform that turns any LLM into a context-aware enterprise assistant connected to your organization's actual knowledge. The agentic RAG pipeline combines BM-25 keyword search with prefix-aware embedding models in a hybrid index, then deploys AI agents to retrieve, verify, and synthesize answers with source citations from over 40 connected workplace tools including Google Drive, Confluence, Slack, Notion, Jira, SharePoint, GitHub, and Linear. Custom AI assistants with configurable prompts, backing knowledge sets, and document-level access control enable specialized agents for engineering, sales, support, and research workflows. The platform supports every major LLM provider — Anthropic Claude, OpenAI, Google Gemini, plus self-hosted options via Ollama, LiteLLM, and vLLM for fully air-gapped deployments. Beyond chat, Onyx provides web search with Serper, Google PSE, Brave, and SearXNG integration, an in-house web crawler, code execution, file creation, and multi-step deep research with report generation. Enterprise features include SSO via Google OAuth, OIDC, or SAML with SCIM provisioning, role-based access control, usage analytics by team and agent, query history auditing, PII removal through custom code hooks, and full whitelabeling. Deploy via Docker Compose on any infrastructure. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed (Community Edition).

Your Gmail, Google Workspace, or Outlook inbox, worked by an AI assistant: Inbox Zero sits on top of the account you already have. Its core idea is rules written in plain English - tell the assistant "label invoices and file the PDF to Drive" or "archive cold outreach unless they mention my company" - and it executes against every incoming message. Emails that need a response arrive with a pre-drafted reply written in your tone, learned from your email history and calendar context. Reply Zero tracks what you owe responses to and what you're waiting on; the Bulk Unsubscriber surfaces newsletters you never read (with read-rate analytics) for one-click unsubscribe-and-archive; the Cold Email Blocker auto-archives unsolicited pitches based on your own definition of "cold." Smart Filing routes attachments - receipts, contracts, PDFs - into the right Google Drive or OneDrive folder, and Slack/Telegram integration lets you read, draft, and triage without opening a mail client. Email analytics show top senders and volume trends. It is not a new email client: everything happens in your real mailbox using native filters. Self-hosting means your mail content and the LLM calls that process it run on infrastructure you control.

Picture a small staff of AI agents clocking in on your own server, each with a name, a specialty, its own model, and a private Linux desktop it can click around in. Every agent works inside a disposable Docker workstation with a shell, persistent files, and a Chromium browser, so it can research the web, write and run code, and finish multi-step tasks without touching your own files. You watch an agent click and type in real time, and when a login, payment, or one-time code needs a human, you take over the desktop, then hand it back with a note and let it continue. Pair a Telegram bot by scanning a QR code and you can assign work, answer questions, and receive results from your phone, with no public URL or port forwarding. Routines turn recurring requests into schedules, so a morning briefing, a price watch, or a weekly report runs by itself and reports back when it is done. Each agent can use a different model, from OpenAI, Anthropic, Google, xAI, Groq, Mistral, or DeepSeek to a local Ollama endpoint, and every reply shows its cost while a monthly budget pauses paid models automatically. Agents remember what matters about you across every thread, and logins or cards you save sit in an encrypted vault the agents themselves never see. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

An 8MB Go binary that boots in under one second, uses less than 10MB of RAM, yet delivers full AI agent capabilities across 16+ chat platforms simultaneously. PicoClaw connects to Telegram, Discord, Matrix, IRC, Slack, WeCom, DingTalk, WeChat, LINE, and QQ while supporting LLM providers spanning OpenAI, Anthropic, Gemini, DeepSeek, AWS Bedrock, Azure, and local models via Ollama. Native Model Context Protocol support enables standardized tool integration, and the built-in smart routing engine directs simple queries to lightweight models to reduce API costs while sending complex tasks to capable models. Tool capabilities include secure shell execution, filesystem access, web search, cron scheduling for recurring tasks, and sub-agent spawning with status tracking. Gateway mode transforms PicoClaw into a full AI backend with REST API endpoints accessible from any client. The Skills system loads hierarchical behavior definitions from SKILL.md files, enabling customizable agent personalities and workflows. Compiles for x86_64, ARM64, ARMv7, RISC-V, MIPS, and LoongArch, making it deployable on hardware as cheap as a $10 Sipeed LicheeRV Nano. Achieved nearly 30,000 stars within six months of its February 2026 release. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

A self-hosted "second brain": Khoj indexes your own files and answers questions from them, parsing Markdown (whole Obsidian vaults included), org-mode, PDF, Word, plain text, Notion pages, GitHub repositories, and images described by a vision model, then embedding everything with sentence-transformers into a vector index for semantic search and RAG with cited sources. Any LLM backend works: local models like Llama, Qwen, or Mistral via Ollama, or cloud models like GPT, Claude, and Gemini. You can build custom agents, each with its own persona, scoped knowledge base, chat model, and tools such as web search and code execution. Scheduled automations run recurring research and deliver newsletters or notifications to your inbox, and research mode performs multi-hop web searches with inline citations. Access it from a browser, the Obsidian plugin, Emacs, desktop, or WhatsApp - all clients connect to the same self-hosted instance, making Khoj one of the few AI assistants Emacs users can point at decades of org files. Semantic search means recall works without exact keywords: "that paper about forecasting with transformers" surfaces the right PDF even when you cannot remember its title. Switching LLM backends never requires re-indexing your documents, and with a local model via Ollama, even inference stays on hardware you control - journals, research, and private notes are never sent anywhere. Python/FastAPI stack, AGPL-licensed, with PostgreSQL storage.

Your team's group chat could have a colleague who has read every email, ticket, and document, remembers all of it, and answers in seconds; MindRoom puts AI agents like that into your chat rooms as full participants. Each agent is a real user on the open Matrix protocol, so you talk to it in MindRoom Chat on web or mobile, in any other Matrix client, or through bridges in Slack, Telegram, WhatsApp, and Discord. Give every agent its own model: a local model for private rooms, a frontier model for hard coding problems, and switch per room or thread whenever the work changes. Agents connect to more than 100 tools, including Gmail, calendars, GitHub, Google Drive, Home Assistant, and any MCP server, and they search your own documents and knowledge bases for answers with sources. Memory persists across conversations and platforms, so an agent remembers people, preferences, and project context months later and can turn repeated work into reusable skills. Before an agent sends an email or runs a command, an approval card shows exactly what will happen; you tap once to allow it, and sandboxed workers keep executed code away from your credentials. Schedule morning briefings, silent inbox checks, and recurring digests in plain language, or wake an agent from any other system with a single HTTP request. 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.

Converting inbound chat conversations into closed revenue is what Deskcomm orchestrates through an open-source sales operating system with native AI agent routing and WhatsApp integration. Sales representatives monitor incoming customer inquiries across connected WhatsApp Web sessions and official WhatsApp Cloud API channels from a real-time shared inbox with multimodal attachment previews. Autonomous AI agents qualify incoming leads, extract contact parameters, parse customer objections, and book calendar appointments before escalating complex deal negotiations to human account executives. Commercial teams organize deal progression through interactive kanban pipeline boards, where drag-and-drop movements trigger automated follow-up sequences and dynamic message templates. The built-in knowledge retrieval studio ingests internal product documentation and FAQ catalogs, allowing AI attendants to cite verified organizational knowledge during client interactions. Multi-tenant access controls enforce strict data isolation between business units with granular role assignments for managers and support operators. Administrators monitor token consumption across OpenRouter and OpenAI models while synchronizing customer records with external platforms through Model Context Protocol servers and outbound Webhooks. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

DB-GPT lets a team talk to its data: ask a business question in plain English, and an AI agent plans the work, writes the SQL, runs it, and hands back charts and a written report. Connect MySQL, PostgreSQL, SQL Server, ClickHouse, DuckDB, Doris, StarRocks, or MaxCompute, or drop in CSV and Excel files, including several at once. Every step appears in a live task view with its query, result table, code, and console output, and the agent pauses to ask clarifying questions, with answer options, when the data cannot settle the matter. Reusable skills package proven procedures, including CSV analysis, SQL analysis, and financial report analysis, and a skill creator helps write new ones. Code executes in a sandbox, parallel sub-agents split larger jobs, and an agentic knowledge-base search answers questions over uploaded documents. Scheduled tasks run saved conversations on a cron timetable with on/off switches and execution history, while MCP connectors link tools like Notion, Linear, Tavily, and GitHub. Pick OpenAI, DeepSeek, Qwen, SiliconFlow, Ollama, or vLLM for the model, then use the application and AWEL workflow tools to build data apps of your 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.

big-AGI is an open-source generative AI workspace that provides a unified, local-first interface for orchestrating multi-model reasoning, automated code execution, and custom persona workflows across private infrastructure. Users query multiple large language models simultaneously through the Beam scatter-gather engine, which prompts independent AI systems in parallel, compares candidate completions side by side, and merges optimal passages into a single refined response. Knowledge workers assemble tailored AI personas equipped with specialized system instructions, custom temperature settings, and predefined document context to handle domain-specific tasks ranging from architectural design reviews to legal contract analysis. The application renders rich multimedia outputs including interactive Mermaid sequence diagrams, LaTeX mathematical formulas, syntax-highlighted code blocks with live execution previews, and AI-generated image generation canvases. Teams integrate local inference servers like Ollama and LocalAI alongside commercial API endpoints to route confidential datasets strictly through internal networks while monitoring per-prompt token usage and operational latency. Users attach complex PDF documents, spreadsheets, and source code repositories for automatic parsing and semantic retrieval, while local-first storage engines ensure private chat transcripts and custom presets remain encrypted on host drives. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

In seven wizard steps, PandaWiki sets up a product docs, manual, FAQ, or blog site whose built-in AI answers visitors using only your own content. Those visitors can chat with an assistant that cites its sources and accepts image questions, or switch to a docs-only search that lists ranked pages with summaries. Publishing stays under control: each document has three switches, visible in navigation, reachable by URL, and answerable by AI, and nothing appears or gets learned until it is published. Authors write in a Markdown and HTML editor, or import from URLs, RSS and Atom feeds, sitemaps, offline .txt, .md, .xlsx, .docx, and .pdf files, Notion, Yuque, SiYuan, Wiki.js, Feishu, Confluence, and DingTalk. Pages export to Word, PDF, or Markdown. The wizard covers models, domain, HTTP or HTTPS ports, import, publishing, answer testing, and page decoration. One knowledge base can also feed a web widget and DingTalk, Feishu, WeCom, and Discord bots. Administrators get a dashboard of visits, questions, visitor regions, hot documents, and referring domains. Chat models come from Baizhi Cloud, DeepSeek, OpenAI, or Ollama, while vector and reranking models are built in. The open-source edition covers one wiki site, 300 documents, and one admin, and its console and documentation are in Chinese. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. AGPL-3.0 licensed.

Designed for developers on the go, Yep Anywhere turns any smartphone browser into a full-featured control center for supervising, steering, and reviewing autonomous AI coding agents. Operators can monitor live execution across multiple active projects simultaneously without sitting at a desktop terminal. Real-time reasoning feeds. Instant push alerts for permission prompts. One-tap tool approvals. Developers can unblock pending tasks mid-turn, redirect active workflows, or queue sequential follow-up prompts for automatic delivery at the next safe milestone. An integrated source control viewer displays syntax-highlighted working-tree and commit diffs, allowing reviewers to attach line-level comment bundles directly back into the agent context. Mobile voice transcription lets users dictate instructions straight into running sessions, while photo library integration makes uploading bug screenshots effortless. All agent credentials, CLI configurations, and repository data remain private on the host server without requiring third-party cloud database accounts or proprietary device pairing. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Kept is a self-hosted home inventory that answers where things are, what they are, and what is due. Locations, rooms, shelves, and boxes nest inside each other, so moving a box moves everything in it, and each location can be viewed as a list, a grid, or a 3D map with pins for low stock, loans, and due items. Every thing gets a short ID and a QR code for label sheets or roll printers, and scanning a label opens the box. Capture a thing, receipt, or whole room from the installable phone web app, offline too; an AI provider you choose, including Ollama, then suggests details for you to confirm. Receipts, manuals, and warranties attach to items, reminders arrive in the app, by email, by push, or in a calendar feed, and an insurance report exports photos, serials, and receipts. Lending tracking, vehicle readings and services, moving-house box lists, and stocktakes cover the rest of the household, with shared locations and roles for everyone you live with. An assistant answers questions like where the HDMI cable is, and an MCP endpoint lets Claude or other AI agents add and move things, with changes waiting for your approval. Nightly backups and imports from Homebox and CSV round it out. 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.

Your house already has lights, locks, sensors, thermostats, and speakers from many brands, and Home Assistant gives them one local control room with no vendor cloud in the loop. To close the shutters when the outdoor temperature holds above 25 °C, or to be alerted when the garage door is left open, build the routine in the visual editor: When, And if, Then do. Scenes, scripts, and blueprints package it for reuse, and run traces show what it did. More than 1,500 integrations cover Zigbee, Z-Wave, Matter, Thread, MQTT, ESPHome, Bluetooth, Hue, and Sonos, and network discovery offers known devices for one-step setup. To see the house at a glance, drag tile, thermostat, gauge, graph, and map cards into a dashboard, then put it on a TV with Home Assistant Cast. The Energy dashboard answers where the power goes, drawing solar, grid, battery, gas, and water as one distribution diagram with cost totals and per-appliance tracking. To talk to the house, use Assist: natural-language commands, wake words, and custom sentences run locally or through Home Assistant Cloud. The map panel shows who is home, plotting people against zones such as Home, Work, and School from the iOS and Android companion apps. Areas and labels keep large setups tidy, and multi-factor authentication guards each account. 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.

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.

Built for e-ink screens, Tesserae composes calm wall dashboards from your calendar, weather, and Home Assistant data in a browser, then renders each frame at the panel's exact resolution. Lay out pages as a grid of cells or on a free canvas of widgets, text, and shapes, with a live preview. What you see is what paints. Dozens of bundled widgets cover weather, calendars, clocks, news, to-do lists, and photos, and a community catalog adds more widgets, themes, and templates. Frames are dithered to each panel's measured palette, so photos and gradients stay clean on Spectra 6 color, mono, and grayscale screens. One server drives a whole fleet. Each panel keeps its own dashboards, schedules, and rotations, and smart sync renders just before a battery panel wakes while quiet hours let it sleep overnight. Seeed reTerminal and XIAO panels flash from the browser, and Pimoroni Inky, Waveshare, M5Stack, TRMNL-compatible devices, and KOReader Kindles and Kobos work too. Inside Home Assistant it runs as a sidebar App. Home Assistant widgets show entities, history, energy, and cameras, and MQTT discovery turns each panel into a device with its frame, battery level, and signal. No account is needed, and update checks stay off unless you opt in. Ask Claude or any MCP client to lay out a dashboard, check a preview, and push it. 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.