1730 apps Self-Hosted
EvoScientist screenshot thumbnail

EvoScientist

EvoScientist gives a research project a team of cooperating AI agents that plan experiments, read papers, write and debug code, and draft reports, then remember what they learned so the next project starts further ahead. A researcher can schedule a weekday arXiv digest as a cron-style task, optionally graded against a rubric checklist, while a lab lead reviews the reusable skills that AutoSkills proposes from recurring patterns. The EvoSkills catalog adds ready-made skills such as academic slides, paper figures, and experiment pipelines. Six sub-agents cover planning, research, coding, debugging, data analysis, and writing, following a workflow of intake, plan, execute, evaluate, write, and verify. Each turn is distilled into a memory that links itself into a knowledge graph you can browse in the EvoMemory view, next to profile pages for you, your research taste, and the agent's SOUL. Work from a terminal UI, a browser workspace with a file tree and agent panel, or messaging channels including Telegram, Slack, and Feishu that share one session. Rubric and goal commands grade each turn against acceptance criteria you approve. MCP servers plug in extra tools with one command, shell commands ask for approval by default, and the Docker image confines file edits to the folders you mount. Choose Anthropic, OpenAI, Google, MiniMax, NVIDIA, or any OpenAI-compatible endpoint such as vLLM. 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.

Deploy
CrewAI Studio screenshot thumbnail

CrewAI Studio

Anyone who can fill in a form can run a crew of AI agents in CrewAI Studio, from defining roles to reading results, with no code to write. Each agent gets a role, backstory, goal, delegation switch, iteration limit, and temperature. Pick a provider and model per agent: OpenAI, Anthropic, Groq, xAI Grok, Ollama, or LM Studio. Tasks carry an expected output, can run asynchronously, and can take context from other tasks. Agents can search the web, scrape pages, run code, and query GitHub, YouTube, or Yahoo Finance news. Search tools also read your own PDF, CSV, DOCX, JSON, MDX, and text files. Custom tools call HTTP APIs and write files into a folder you choose. Knowledge sources accept text, PDF, CSV, Excel, JSON, or Docling files, with adjustable chunk size and overlap. Crews run tasks in sequence or under a hierarchical manager, with memory, cache, planning, and rate-limit options. Kickoff turns placeholders in agent and task text into input boxes and runs the crew in the background. A console panel shows the crew's output while it works, and a Stop button halts a run. Every run is saved, filterable by crew and date, and readable rendered, raw, or printable. Export one crew or everything as JSON, import it elsewhere, or generate a standalone single-page app. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Deploy
Paqet screenshot thumbnail

Paqet

Most proxies ask the operating system nicely for a socket; paqet skips the conversation, building its own TCP packets byte by byte to tunnel traffic between your machine and your server. The server end listens on a port you choose and speaks only in raw packets it crafts and captures itself through pcap, before the kernel's connection tracking ever sees them. On your machine, the client presents an ordinary SOCKS5 proxy on localhost plus optional port forwards, so browsers and command-line tools connect exactly as they would to any proxy. Between the two ends, KCP with smux multiplexing turns a stream of self-contained packets into fast, reliable, encrypted sessions, with AES or lighter modes selected per deployment. TCP flag cycling varies how packets present themselves on the wire, giving operators control over the traffic pattern the tunnel produces. Built-in utilities generate the shared secret, ping the server with a single test packet, and dump live traffic decoded, so a silent tunnel gets diagnosed in minutes rather than by packet-capture archaeology. One YAML file per side declares the role, network interface, gateway MAC, and keys, and the same binary runs both ends. It suits security research, hostile networks, and anyone whose ordinary proxies keep getting reset. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Deploy
Networking Toolbox screenshot thumbnail

Networking Toolbox

Subnet math, DNS lookups, DHCP options, and certificate checks share one browser tab in Networking Toolbox, a free toolkit for sysadmins and network engineers. Need to carve a /24 into departments? The VLSM planner fits named subnet requirements into a parent block, reports each subnet's efficiency and the leftover space, and exports the plan as CSV or JSON. Merging address lists? CIDR utilities summarize, split, compare, and deaggregate prefixes, with set operations for difference, overlap, and containment. Writing configs? Generators build DHCPv4 and DHCPv6 options, PXE profiles, Kea or ISC snippets, and SPF, DKIM, DMARC, CAA, TLSA, and SRV records, and DNSSEC helpers calculate key tags and DS records. Something broken? Diagnostics query DNS through Cloudflare, Google, Quad9, OpenDNS, or a resolver of your choice, read TLS certificate chains, grade HTTP security headers, trace redirects, check TCP ports, look up BGP routes and RDAP records, and test mail servers. Need a refresher? Reference guides explain private ranges, CGNAT, IPv6 address types, and common ports. A keyboard search palette puts any tool a few keystrokes away, and bookmarked tools stay available offline. Eighteen themes, four languages, custom branding, and accessibility switches make it feel like your own, and a keyless JSON API serves the subnet, CIDR, IP, and DNS utilities to scripts. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Deploy
Inbox Zero screenshot thumbnail

Inbox Zero

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.

Deploy
Medplum screenshot thumbnail

Medplum

Building healthcare software usually means assembling a FHIR data store, an identity provider, audit logging, and clinical interfaces before any product code gets written, and Medplum ships all of it as one open-source platform. Every clinical record, from patients and encounters to observations, medications, and appointments, lives in a standards-based repository you can query through REST and GraphQL APIs with full search parameters. Sign-in and permissions come built in through OAuth, OpenID Connect, and SMART-on-FHIR, with access policies that control read and write rights down to the resource, compartment, and field level. The included web app lets your team browse and edit any resource, manage project users, clients, bots, and secrets, and review a complete audit trail where every read, write, and login is recorded. Bots run your TypeScript logic inside the platform when resources change, on schedules, or over HTTP, handling jobs like HL7 transforms, eligibility checks, and notifications without another server to operate. Subscriptions push real-time events to your services through webhooks or WebSockets with retries and signing, and projects partition data so each clinic or customer stays isolated on one deployment. Clinicians get ready-made interfaces for charting, scheduling, eligibility, and billing that you can fork and rebrand, while patients reach their records through portals and SMART health links. 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.

Deploy
OpenList screenshot thumbnail

OpenList

OpenList gathers every place your files live, local disks, S3 buckets, OneDrive, Google Drive, Dropbox, NAS shares, and forty-odd other services, into one browsable file list behind a single login. Mount each storage at its own path and the whole collection behaves like one tidy drive: documents open in the browser, whether PDF, Markdown, source code, or Office files, images get a gallery mode, and videos and audio play in place with subtitle and lyric support. Everyday file work happens in the same window: upload, delete, rename, move, and copy, including copying directly between two storages when you are migrating off a cloud plan. Offline download tasks let the server fetch links for you in the background, and multi-threaded acceleration squeezes speed out of sluggish single connections. Every folder can also be mounted as a real drive on your computer through the built-in WebDAV and FTP servers, with per-user permissions deciding who may read, upload, rename, or delete. Protected routes add passwords in front of sensitive shares, permalinks hand out direct download links, and granular user rules can hide files or open archive contents without extracting them. 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.

Deploy
Lumen screenshot thumbnail

Lumen

Ask Lumen which islands have the most penguins and it writes the SQL, runs it, and draws the chart in a split-screen explorer. Drag in CSV, Parquet, JSON, or Excel files, or point it at a database, and mark extra files as metadata so the model understands what each column means. Every answer lands in its own exploration, with follow-up questions nested beneath it, and the generated SQL or Vega-Lite chart specification sits in an editor you can change to update the view instantly. Tables sort, filter, and paginate, charts carry tooltips and annotations, and results export as CSV, Excel, PNG, or PDF. Report mode gathers all explorations into one document that downloads as a notebook with every question, query, and visualization ready to rerun. A planner agent breaks hard questions into steps, a validation pass checks that the answer matches the request, and settings choose among OpenAI, Anthropic, Ollama, and other language model providers. Developers can add custom agents, tools, and analyses, or write declarative specifications that become shareable dashboards. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. BSD-3-Clause licensed.

Deploy
Antares screenshot thumbnail

Antares

Most AI agents are a chat box with confidence; Antares is a working security specialist that shows its evidence. Point it at a target you are authorized to test and its specialist agents map the surface, test web applications against OWASP, probe APIs, and record every confirmed finding with its reproduction steps. When the run ends, the findings are already compiled into a report, because the agent kept the evidence as it went instead of reconstructing it afterward. The same workspace handles ordinary work between engagements: it reads and writes files, runs your shell, drives a real browser, searches the web, and retrieves from a built-in memory and RAG index that remembers what matters across sessions. Give it a goal and it holds to that goal across turns, schedules its own follow-up work, and answers from Telegram and Discord when you are away from the dashboard. Bring your own models, since everything runs on your machine or server from one binary, with the dashboard, terminal UI, and API served by a single process. 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.

Deploy
Codeg screenshot thumbnail

Codeg

Run Claude Code, Codex, Gemini CLI, OpenCode, and sixteen other AI coding agents from one workspace instead of juggling twenty terminals. Every agent connects through the Agent Client Protocol, so conversations render as structured chats with tool cards, live diffs, and interactive replies rather than raw terminal scrollback. Codeg imports the session history each agent already keeps on disk, making every past conversation searchable and resumable, even when you hand the thread to a different agent. Mention one agent with an @ to delegate work to another, or run several side by side and watch their progress stream into the same conversation. Queued to-dos execute unattended in isolated git worktrees, leaving finished changes ready for your review and approval instead of touching your working tree. An infinite canvas arranges chats, files, terminals, and notes on one board, while git tooling, token usage tracking, and MCP server support stay one panel away. Deployed as a headless server, Codeg answers in any browser and through Telegram, Lark, and WeChat channels, so agent work continues while you are away from your desk. 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.

Deploy
LLMVault screenshot thumbnail

LLMVault

A hacking gym for AI apps: every lab is a chatbot or agent with a planted weakness, and your job is to exploit it and capture the flag. The dashboard tracks score, rank, badges, and a live activity feed across three tiers. Ten core labs map to the OWASP Top 10 for LLM Applications, ten advanced labs need multi-turn tactics like persona escalation, stored injection, and tool chaining, and an encrypted expert tier unlocks last. Each lab opens with a short reference panel on the weakness, offers hints, and ends with the defense that would have stopped you. Play mode uses scripted assistants so flags reproduce every time and the whole range runs offline without API keys. Live mode points attacks at a real local model through Ollama, mints a fresh secret per session, streams replies token by token, and checks the output instead of a flag box. Scenarios cover direct prompt injection, a hidden payload in an uploaded image, and unsafe rendering of model output. A RAG lab accepts text and markdown uploads, so poisoning a knowledge base is hands-on. Two themes, Neon and Phosphor green-CRT, change the look. Security teams run workshops with it, red teamers sharpen prompt injection skills, and developers see why their guardrails fail. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Deploy
SoduWork screenshot thumbnail

SoduWork

When an AI agent says the job is done, SoduWork makes a second agent check the work against your acceptance criteria and a person sign off before the request closes. You file a request, AI refines it and drafts the criteria, and you assign it to yourself, a colleague, or an agent. A failed review sends the work back with reasons. Seven harnesses are supported: Pi, OpenCode, Qwen Code, Kimi Code, DeepSeek Harness, Codex Harness, and Codex. Switch between them mid-conversation without losing history or the working folder, and any program that speaks the Agent Client Protocol joins through a catalog entry. Routine steps run on cheap or local models, hard ones on strong models, and long tasks move to a cloud runner on a server you provide. Save a chat that went well as a versioned plugin with inputs, workflow steps, and acceptance criteria, then submit it for review, grant it to chosen people, or revoke it. Plugin Developer drafts plugins from a description in chat, and the catalog already covers documents, slide decks, spreadsheets, deep research, PDF work, meeting minutes, and code repair. Admins get roles, usage and cost tracking, a model catalog, and an audit log, and connectors reach business systems through OAuth sign-in, OpenAPI documents, and MCP servers. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Deploy
OptScale screenshot thumbnail

OptScale

Idle instances, forgotten snapshots, and unattached volumes quietly inflate cloud bills, and OptScale hunts them down across AWS, Azure, Google Cloud, Alibaba Cloud, and Kubernetes from one self-hosted FinOps console. Cloud accounts connect with read-only rights, and the Recommendations page turns billing exports and monitoring data into savings cards for abandoned and underutilized instances, obsolete snapshots, detached volumes, abandoned load balancers, inactive IAM users, public S3 buckets, and Reserved Instance, Savings Plan, and Spot opportunities, each priced in monthly dollars. Cost Explorer breaks daily, weekly, or monthly spend down by data source, pool, owner, or geography, and the Cost Map plots it by region on a world map. Pools mirror your organization with limits, owners, and forecasts, while quotas and budgets, anomaly detection, tagging policies, TTL rules, and VM power schedules flag or contain overspending. Shared Environments let engineers book test stands on a calendar and see which Jira tickets and software builds each one carries. Kubernetes costs are split by namespace, workload, and label, K8s rightsizing compares CPU and memory use with requests, and Databricks cost analytics shows cluster usage and idle time. A cost comparison page lines up VM sizes and prices across providers. 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.

Deploy
Ferret screenshot thumbnail

Ferret

From the tent in the garage to the warranty on the fridge, Ferret keeps one searchable home inventory that your household runs on its own server. Properties, rooms, and boxes hold things with photos, receipts, manuals, serial numbers, and prices, and a quick add accepts a photo, a barcode scan, or a picture of a whole room to sort through. Printed QR labels on boxes and shelves open the list of what is inside. Warranties count down to the last day with a claim shortcut, return windows warn before they close, and maintenance repeats by date or by use, with reminders and how-to videos. Stock levels feed a shopping list, a lending log remembers who borrowed the saw, and a replacement forecast estimates what wears out and when. An insurance report totals value by room and category, exports PDF and spreadsheet files, and can be shared by link. Households have owners, admins, members, and read-only viewers, with invitations and single sign-on. Optional AI reads receipts, suggests details from photos, and answers questions in plain words, while a built-in MCP server lets Claude search, add, and update items with a key that can be read-only. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Deploy
Nod screenshot thumbnail

Nod

Nod is a personal AI assistant with its own computer, so you can hand it an errand like chasing an unpaid invoice or cancelling a trial and watch it finish the job on real websites. One ongoing conversation follows you from the browser to Telegram and WhatsApp, and long jobs become saved tasks with live status lines on a Scheduled page. Connect Gmail, Calendar, Slack, Notion, Linear, or an n8n instance, and it reads threads, drafts the replies you owe, and prepares a one-page brief before each call. Every action that could change something is checked against your rules, and anything uncovered waits for your yes. Passwords, codes, and cards sit in a Vault that the server types into websites, so the model never sees them. Memory notes are visible, editable, and tied to the message they came from. Schedules run recurring checks like a weekly recap or a price watch that speaks up only on change. Usage lists every action with costs and a monthly spending limit. Pick OpenAI, Anthropic, Gemini, OpenRouter, Bedrock, or a local Ollama server as the model. 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.

Deploy
Promptfoo screenshot thumbnail

Promptfoo

Promptfoo replaces vibes-based prompt tweaking with measurable tests, then attacks your AI app the way a hostile user would. An evaluation matrix lines up every prompt and model side by side, with pass or fail badges, assertion messages, latency, token counts, and cost in each cell. A red team wizard walks through the target, application details, plugins, and strategies, then probes for prompt injection, data exposure, broken access control, and harmful content. Preset bundles map plugins to the OWASP LLM Top 10, NIST AI RMF, MITRE ATLAS, GDPR, ISO 42001, and the EU AI Act. Meta Agent and Hydra Multi-Turn strategies adapt attacks across a whole conversation instead of firing one-shot prompts. Providers span OpenAI, Anthropic, Gemini, Bedrock, Azure, and local Ollama models, and any HTTP endpoint, Python script, or JavaScript function can be tested as a target. The history page lists every run with pass rates and raw scores, and prompt and dataset pages show which templates and test sets each run used. A provider allowlist file narrows the models offered in the web editor for cost control. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Deploy
LibreDesk screenshot thumbnail

LibreDesk

LibreDesk unifies live chat, email, and future channel integrations into a single agent inbox where every customer conversation converges regardless of origin, replacing per-seat-priced tools like Zendesk, Intercom, and Freshdesk with a zero-cost alternative that has surpassed 2,000 GitHub stars. Built on a Go backend with a Vue.js 3 and ShadcN UI frontend, it ships as a single binary requiring only PostgreSQL and Redis. The embeddable live chat widget drops onto any website with a snippet, while the AI assistant handles initial customer queries using answers grounded in your knowledge base before escalating to human agents when needed. Agent copilot drafts replies, summarizes conversation threads, and rewrites messages for tone adjustment directly within the inbox interface. Automation rules trigger on conversation events to tag, assign, and route tickets based on configurable conditions, while auto-assignment distributes workload by agent capacity or custom criteria. SLA management tracks response and resolution time targets with breach notifications, and automated CSAT surveys measure satisfaction after conversation closure. Macros save frequently sent responses as reusable templates that simultaneously set tags and assign conversations. Role-based access control provides granular per-action permissions for teams and individual agents, and SSO supports Google, Microsoft, and any OIDC provider. The HTTP/JSON API and webhook system enable custom integrations with external tools. 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.

Deploy
calrs screenshot thumbnail

calrs

Share a link, and let people book time with you without the email volley that usually decides when a meeting happens. calrs connects to the calendar you already use, whether that is Nextcloud, Fastmail, BlueMind, iCloud, or any other CalDAV server, computes your real free and busy times from synced events and your availability rules, and shows guests only the slots that genuinely work. Create event types for intro calls, support sessions, or coaching, each with its own duration, buffers, minimum notice, booking limits, and confirmation mode, then publish them on your public profile or keep them private behind single-use invite links. Teams get round-robin scheduling that picks the least busy member, collective meetings that require everyone free, and dynamic group links that intersect several calendars on the fly for a one-off call. Guests pick a slot in their own timezone, receive HTML email with calendar invites attached, and can cancel or reschedule themselves from the confirmation email, while you approve pending bookings from the dashboard or straight from your inbox. When a slot looks wrong, the availability troubleshooter draws a timeline showing exactly which event or rule blocked it. Reminders go out before meetings, credentials are encrypted at rest, and the whole interface speaks ten languages with seven themes. 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.

Deploy