260 apps AI Agent
Hexis screenshot thumbnail

Hexis

Hexis gives every AI agent in your company one governed brain: skills, tool manuals, and knowledge stored as files in a git repository you own. Engineers and non-technical teammates browse the same workspace to load plugins, read company context, and propose improvements without touching git themselves. A proposed change shows its exact diff to the owners of the files it touches, and it ships only when they approve, on the branch rules you set. Agents propose too: one that hits a broken skill mid-task can suggest the fix as a change request and wait for a person to decide. Claude Code, Cursor, Cline, Codex, and ChatGPT connect over MCP and discover skills by search at call time, so the context window stays lean. Each agent acts with its user's own permissions, resolved per file, and the credentials behind tools stay in an encrypted vault the agent never holds. Roles and folder-level grants decide who sees what, and your team signs in behind your own SSO. Every save is a commit, so history, blame, and revert come free, and the knowledge base can start from the bundled template in minutes. 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
Agenticos screenshot thumbnail

Agenticos

Give each team an AI teammate that works where the team already works: AgenticOS lets colleagues and agents share one live chat and the same project files, so an agent can answer in the thread, apply a correction from a reply, and show its work as it writes. You build an agent in the browser by writing its instructions, picking a model, and switching on tools, then publish it to web chat, Slack, Teams, Discord, Mattermost, Telegram, a website widget, or an API. Agents analyze spreadsheets, run code in a sandbox, browse the web in a browser you can watch and take over, and hand programming work to Claude Code or Codex. Company knowledge comes from uploaded documents and synced drives, searched with cited answers, while reusable skills teach agents how your team writes reports, reviews code, or researches a market. Agents can draw charts and diagrams in chat and publish dashboards as apps with stable links your team opens anywhere. Administrators set roles and department groups, cap each agent's monthly budget, require approval for sensitive tools, and read a recorded run history with costs. 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
Accounted screenshot thumbnail

Accounted

Accounted is an open-source accounting platform built for Swedish sole traders and limited companies that keeps double-entry bookkeeping, invoicing, payroll, and tax filings compliant with Swedish accounting law. Create and send customer invoices with mixed VAT rates, generate PDFs, and track payment status, while supplier invoices record input VAT and feed batch payment files your bank can upload. Connect the bank feed to reconcile transactions automatically, then watch matched entries clear in passes instead of hunting through statements line by line. VAT declarations map onto the SKV 4700 form with per-rate breakdowns, and tax reports export in the formats the tax agency expects for sole traders and companies. Run payroll with salary runs and payslips, file employer declarations, and sync the tax account so booked movements reconcile against the agency record. Every receipt and document lands in an archive with integrity checks and seven-year retention, and period locks with sequential voucher numbers keep the books audit-ready. An AI agent can categorize transactions, draft vouchers, and prepare declarations through the built-in agent tools, while every posting waits for your approval before it commits. Import or export the standard SIE format to move between Swedish accounting systems, and send or receive electronic invoices through the Peppol network. 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
Coral by Subgentic screenshot thumbnail

Coral by Subgentic

No more hunting through terminal tabs for the coding agent that stalled on a permission prompt, because Coral queues every question, approval, and file review in one Inbox. Claude Code, Codex, and Antigravity run side by side as one team, each in its own terminal session, sharing a message board and a task queue where dependencies wait on outcomes and required artifacts. Goals carry a checkable Done when line, and review gates hold dependent tasks until a reviewer approves. Files an agent produces open in a versioned viewer where you comment on passages, mark up images with a pen, arrow, or box, compare version two against version one, then approve, approve with a note, or request changes. A changed-files panel shows each agent's diff beside its chat, and optional git worktrees keep the main checkout clean. Idle agents sleep and wake when a message arrives, and whole teams can sleep through a restart. Scheduled jobs and multi-step workflows run regression suites and audits on a cron, resource queues keep concurrent agents off the same build rig, and analytics break token spend down by provider, model, thinking level, team, and task. A QR-paired phone client approves prompts on the go, and a self-hosted hub follows agents across computers. 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
PandaProbe screenshot thumbnail

PandaProbe

A looping agent burns money quietly until someone can see where it drifted, and PandaProbe is an observability and evaluation platform for AI agents that makes that drift visible step by step. Capture complete executions as sessions, traces, and spans spanning model calls, tool calls, multi-agent handoffs, and custom logic, then follow a looping or failing run back to the decision where it drifted. Score traces and sessions with agent-specific metrics, run asynchronous and sampled evaluations so judge models do not cost more than inference, and use lightweight trajectory signals to catch stalls, bad tool use, and regressions over time. Bring agents built with LangGraph, CrewAI, the Claude Agent SDK, the OpenAI Agents SDK, and other integrations, with MCP tool calls captured automatically where supported. Organize work by user, organization, and project, send data through an SDK or HTTP API with project keys, and query filtered, paginated traces when you need the raw record. Keep sensitive workflows local when that matters: prompts, traces, and evaluation results stay inside the deployment you run, instead of leaving for a hosted console. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache-2.0 licensed.

Deploy
Paca screenshot thumbnail

Paca

Paca is a self-hosted project management platform and Scrumban workspace where autonomous artificial intelligence agents collaborate with human software engineers as first-class Scrum teammates instead of external chat assistants. Engineering teams manage sprints, backlogs, and task lifecycles through a shared real-time board powered by Socket.IO where both humans and agents pick up assignments and post progress updates. A native Model Context Protocol server connects external coding assistants such as Claude Desktop and Claude Code directly into projects, tasks, and sprint data without custom scraping scripts. Distributed agents execute in isolated runtime sandboxes powered by the OpenHands software development kit, co-authoring behavior-driven development Gherkin scenarios with product owners and maintaining living system design documents. Visual event-driven automation builders compose multi-branch trigger, condition, and action pipelines that evaluate task dependency gates and cron schedules. A sandboxed WebAssembly plugin runtime allows developers to write custom backend logic and custom board views using Go or Rust. 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
VoicEra screenshot thumbnail

VoicEra

VoicEra lets you run your own voice AI phone platform, where callers talk to agents you configure and every recording and transcript stays on infrastructure you control. Build telephony agents that answer inbound calls or run outbound campaigns, choose the speech recognition, language model, and speech synthesis behind each one, and swap providers without rebuilding the platform. Connect phone numbers through telephony carriers, route live audio through the real time runtime, and let workers execute campaign calls in the background while you watch progress from the operator dashboard. Review call logs with recordings and transcripts after each conversation, including provider recordings when carriers supply them. Serve callers in Indian and low resource languages by combining Bhashini, AI4Bharat, and other Indic models, switch languages mid call, or run speech and language models locally through the optional model server gateway. Add new AI or telephony providers behind stable registry interfaces when a better model or carrier appears, authenticate operators, and keep media in your own object storage and database. Test agents in the browser before any phone number is involved, then scale the same configuration to real 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.

Deploy
Libre WebUI screenshot thumbnail

Libre WebUI

Libre WebUI is a self-hosted AI workspace that keeps chat, notes, personas, and agent tasks in one place you control. Local models run through Ollama, and hosted ones come from OpenAI, Anthropic, Gemini, Groq, Mistral, OpenRouter, or any OpenAI-compatible endpoint added on the provider settings page. Pick a model per conversation. Replies stream, prompts queue, chats fork into branches, and several models can answer side by side. Notes keep Markdown documents with revision history. Personas bundle a system prompt, a model, and memory into a reusable assistant, and prompt templates with typed variables appear when you type a slash in the composer. Knowledge collections ground answers in uploaded documents and cite their sources. The Work area gives each task its own workspace with files, a terminal, diffs, and a live preview, and automations run scheduled prompts that arrive as normal chats. Administrators create users and groups, hand out roles, issue scoped API tokens, and share chats, notes, and personas through one grant model. A private team assistant, a research desk, or a sandbox where agents build small apps all fit here. 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
Cotal screenshot thumbnail

Cotal

Cotal puts your AI agents in one shared room: Claude Code, Codex, and OpenCode discover each other, message channels, hand off work, and ask you to approve the result. Post to a channel and every subscriber hears it; message one peer and the durable inbox holds it until they are free; address a role like reviewer and one available reviewer claims the job. Presence shows who is actually there, and attention modes decide which channel traffic may interrupt an agent mid-task. A manager starts and stops agent processes in tmux or cmux, here or on remote hosts you authorize, without sitting between their messages. For work that waits and branches, Cotal Lang programs launch agents, pause at human checkpoints with deadlines, and resume from their recorded steps after an interruption. Services join the same space by publishing command contracts that authorized agents can discover and invoke; the bundled Linear adapter shows the pattern. Supervise from a terminal console with the live roster and activity feed, or from the read-only browser dashboard and its graph of agents and channels. Spaces stay separate, every message carries a checked identity, and per-agent grants decide who may delegate, spawn teammates, or call a service. 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
OpenNetWorth screenshot thumbnail

OpenNetWorth

Open Net Worth is a self-hosted personal finance system where an AI agent named Lucius works a real multi-currency ledger, a zero-based budget, and an investment book through guarded write tools instead of merely describing your money. Record every account you own or owe, from bank accounts and cards to loans, retirement funds, and brokerages, then reconcile balances, split transactions, and review statement imports before anything books. Budget with Ready to Assign envelopes, category targets, and credit card payment tracking, or switch to a simple 50/30/20 split and project cash flow months ahead. Track holdings, buys, sales, dividends, tax lots, realized gains, options, and equity grants, with watchlists and price alerts for the positions you follow. Lucius can categorize transactions, reconcile accounts, build reports, and act in connected apps, and every tool carries a permission level you control, so sensitive changes pause on a confirm card before they land. Schedule automations for a daily briefing, a weekly report, or a bank sync, and save repeatable jobs as skills he follows again. Connect SimpleFIN, Plaid, Enable Banking, Alpaca, or Interactive Brokers, import from YNAB or Lunch Money, and bring an Anthropic, OpenAI, or local Ollama model. 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
Yuxi screenshot thumbnail

Yuxi

Navigating organizational knowledge, visualizing concept graphs, and orchestrating cooperative AI agents converge inside Yuxi, an open-source multi-tenant workspace built for enterprise research and deep archive exploration. Users can upload diverse business documents including scanned PDFs, spreadsheets, and slide presentations to automatically extract structured text blocks, tables, and entity relationships for semantic querying. Knowledge teams can inspect interactive topological graph views to explore connections between company entities, cross-referencing subgraphs against original file sources. Practitioners can configure autonomous agents with specialized subagents, assigning dedicated roles for concurrent research, deep data synthesis, and code execution. Human reviewers can inspect agent thought chains in real time and evaluate interactive confirmation cards before agents execute irreversible external actions or modify shared workspace files. Operators can execute sandboxed tasks that produce downloadable reports, interactive data charts, and rendered HTML pages stored within isolated workspace file systems. Administrators can govern model endpoints, set granular permission boundaries across departments, and monitor token consumption through live system analytics. 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
Calnode screenshot thumbnail

Calnode

One binary replaces your booking link and your meeting room: Calnode is a complete scheduler you run yourself, small enough to audit and cheap enough to forget. Create event types with durations, custom questions, and locations, set DST-correct availability with date overrides, and share a booking page where guests pick a slot, reschedule, or cancel without an account. Two-way sync with Google Calendar, Microsoft 365, and CalDAV checks real free and busy time across every connected calendar, then mints Meet or Teams links automatically. Teams route bookings round-robin, collectively, or by priority, while paid event types collect through Stripe before the slot confirms. Choose Calnode Rooms and the meeting itself happens in the browser on your LiveKit server, with host controls, consent-aware recording into your own storage, and an AI notetaker that files a transcript and summary on the booking. Agents get first-class access through the REST API, HMAC-signed webhooks, and a native MCP server, and visitors can even book by describing a time in plain language. Everything runs from one static binary and one SQLite file with streaming Litestream backups. 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
QwenPaw screenshot thumbnail

QwenPaw

Designed as a unified personal AI workstation, QwenPaw operates as an autonomous digital copilot that coordinates scheduled automations, interactive coding sessions, and multi-channel team communication across everyday messaging apps. Users can dispatch long-running research tasks, process office documents including PDF, Excel, and Word files, and execute browser-based data collection without manual intervention. The built-in web console and terminal interface provide full visibility into agent reasoning, allowing operators to inspect intermediate thinking steps, review proposed file edits, and approve sensitive tool calls. Through direct connectors for Discord, Telegram, DingTalk, Lark, and WeChat, teams can trigger specialized skills or query shared workspaces directly from their existing group channels. A self-evolving personal memory system continuously indexes chat interactions and local resources into editable Markdown files, ensuring knowledge persists across restarts and task delegations. Built-in guardrails including a sandboxed execution runtime, tool access policies, and automated skill scanners protect underlying host files from unauthorized modifications during autonomous scripting runs. 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
OpenSERP screenshot thumbnail

OpenSERP

Search the web from your own server, with no API key and no per-query bill: OpenSERP is a self-hosted search API that returns structured results from Google, Bing, Yandex, Baidu, DuckDuckGo, and Ecosia through one interface. Every answer arrives as ranked JSON with titles, URLs, snippets, source engines, and timing, ready for an agent, a RAG pipeline, or an SEO tracker to consume. A mega search aggregates and deduplicates across engines in a single call, image search does the same for pictures, and an extract mode reads linked pages back as clean Markdown for models to cite. AI agents connect over MCP with tools for search, mega search, fast search, image search, and batch extraction, and it is a built-in web search provider in Open WebUI. Developers get Python and TypeScript SDKs, an n8n node, a full OpenAPI reference, and a CLI that runs the same searches from a terminal. Engines load in a real browser session, proxy support routes traffic through HTTP or SOCKS5, and one Docker command serves everything on port 7000. 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
Prime Agent screenshot thumbnail

Prime Agent

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.

Deploy
OneCLI screenshot thumbnail

OneCLI

OneCLI gives every employee a sandboxed personal AI agent that works across company tools without ever seeing the real credentials it uses. Create an agent for each person, grant only the services that person may touch, and chat with it from its dashboard page or directly inside Slack channels and direct messages. The agent keeps its own filesystem, shell, memory, and skills between conversations, so follow up messages can redirect work in progress instead of starting over. Schedules wake agents at the right time to run recurring checks, reports, and follow ups without a person remembering to prompt them. When an agent calls Gmail, Salesforce, HubSpot, GitHub, Sentry, or another connected service, the gateway checks the request against team policy and injects the stored credential only for that call. Sensitive actions can pause for a deterministic human approval in chat, so sending an email, deleting a ticket, or changing a deal stage waits for your yes. Shared team connections let administrators connect a service once and grant it per agent, while memory remains readable and editable by the owner at any time. 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
Lightpanda screenshot thumbnail

Lightpanda

Lightpanda is a headless browser built for AI agents and automation that loads and runs web pages without ever drawing them, so crawling, scraping, and agent browsing finish far faster and lighter than in Chrome. You drive it with the tooling you already have: Puppeteer, Playwright, and Chromedp connect over the Chrome DevTools Protocol, Selenium works over WebDriver BiDi, and existing Chrome automation scripts keep running against the new endpoint. Scripts can execute JavaScript on real pages, wait for network activity, read and mutate the DOM, submit forms, and pull structured data out of dynamic sites that plain HTTP clients cannot see. An MCP server mode hands the browser to AI applications as a callable tool, so a model can open pages, follow links, and read content in the middle of an agent workflow. The built-in agent accepts plain-language browsing tasks and can export what it did as PandaScript, a replayable JavaScript file that runs later with no model call at runtime. A fetch command loads one or more URLs and prints the result as HTML or Markdown, which turns page extraction into a single shell step inside data pipelines. In the project's published crawl benchmark it processed pages roughly nine times faster than headless Chrome at a fraction of the memory, so one server can hold many more concurrent browsing sessions. 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
Kwant screenshot thumbnail

Kwant

Instead of one chatbot that confidently declares victory, Kwant gives you a whole team of AI bots that check each other's work before anyone says done. Create spaces for work, a side project, and home, each with its own bots, teams, channels, routines, and accounts, then watch messages route automatically to the bot whose skills fit, with a line under every reply explaining why that bot answered. Bots hand tasks to each other with a mention, and every hand-off becomes a card on the Mission board showing verified results this week, their cost, and what still needs you. A card turns Verified only when Kwant runs the check itself, such as a test or a file check, and keeps the receipt, because files a bot attaches are evidence, never proof. Connect several Claude, Codex, or Grok logins plus Anthropic, OpenAI, or xAI keys, set a priority order, and a turn moves to the next account when one runs out of usage. Schedule routines that run while you are away, collect waiting, finished, and failed work in one Inbox, and approve risky steps like pushes or payments from a card that shows the exact command first. 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