Instead of one overworked chat box, Captain Claw gives you a Flight Deck for a whole fleet of AI agents: spawn specialist teams, watch each agent work live, and chat with any of them from a single dashboard. Describe a goal and Agent Forge designs the team, with roles, tools, and operating procedures, ready to spawn in one click. Agent Council runs moderated debates that end in a vote and exportable minutes, Basna sends the same question to blind specialists and merges their answers by learned reliability, and Vatra lets a team co-write a deliverable on a shared blackboard. Code takes a request through a plan you approve, a build, and three independent reviewers, committing every phase to git. Bat keeps working until an independent judge says the job is done, and Flows run deterministic automations on triggers. Mix OpenAI, Claude, Gemini, DeepSeek, OpenRouter, or local Ollama models per agent, with six memory layers shared across sessions and token and cost meters for every agent. Teams get admin-managed users and shared agents, and agents reach you through WhatsApp, Telegram, Slack, or Gmail while Claude can drive the fleet over MCP. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Autonomous AI coding agents work side-by-side with software engineers inside Its a Plan, a keyboard-driven project tracking and sprint planning workspace designed for rapid software delivery. Product teams organize development cycles through customizable Kanban boards, prioritized backlogs, nested sub-issues, and interactive roadmap timelines designed for rapid keyboard navigation. Engineers can assign work directly to AI agents or mention them inside discussion threads to trigger automated code fixes, documentation updates, and test suite generation. Integrated runners connect to popular coding models via standard protocol interfaces, executing assigned tasks in isolated environments before reporting pull requests and results back to the issue thread. Administrators manage team permissions through role-based access controls, authenticate users with passwordless passkeys or identity providers, and broadcast instant notifications via Telegram and transactional email. The platform dispatches configurable webhooks across development tools, enabling seamless bi-directional status synchronization with external version control platforms and continuous integration pipelines. Custom labels, milestone estimates, and progress metrics provide engineering managers with immediate visibility into sprint velocity and delivery bottlenecks. 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.

One self-hosted workspace holds your team's chat, tasks, notes, and calendar, and Deft lets AI agents work in it beside your people. People get real-time chat with spaces, direct messages, threads, mentions, reactions, files, and presence. Tasks open as Board, Table, Timeline, or Calendar views, with dependencies, subtasks, recurrence, and bulk actions. Notes, decisions, and channel memory become durable knowledge, with graph views and links back to the source conversation. Native calendar events sit beside read-only ICS subscriptions. Agent employees can join channels and receive task assignments. Tag the built-in assistant Defty to draft a task, answer a workspace question, or take a governed action, then review the proposal in an approval card before anything changes. Personal connections let Codex, Claude, ChatGPT, and other streamable HTTP MCP clients act as the signed-in user within revocable scopes. Approval tiers, trust levels, token scopes, revocation, activity history, and action receipts record who or what acted and what changed. OpenAI, Anthropic, OpenRouter, OpenAI-compatible endpoints, and local Ollama-style models are supported providers. Chat, tasks, notes, and calendars keep working with no AI key. Modules add company-specific records, relationships, and views, with a bundled Contacts module as the first example. 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.

To give engineering teams a Render-style workflow of connecting a repository and getting a live HTTPS URL on infrastructure they control, Bex builds and runs web services, private services, background workers, cron jobs, and static sites from Git or container images. Dockerfiles and native builds for Node.js, Python, Go, Ruby, Rust, and Elixir deploy from public or private GitHub repositories with push-to-deploy, health checks, pre-deploy commands, and manual or policy-driven autoscaling. Blueprints in render.yaml format describe multi-resource environments in one file, and a Render-compatible CLI and API let existing tooling carry over where supported. Deploy history with cancel and rollback, live log tailing with search and filters, CPU and memory charts marked with deploy events, and suspend, resume, restart, native SSH, and browser shell controls cover daily operations. Custom domains receive automatic TLS certificates, and environment variables and secret files save and deploy in one step. Managed PostgreSQL provides backups with point-in-time recovery, high availability, and read replicas, and managed Valkey-compatible Key Value adds persistence and backups. Workspaces, projects, and environments come with OpenFGA roles, OAuth 2.1, API keys, audit logs, and signed outbound webhooks. Coding agents operate the same control plane through a remote or stdio MCP server with OAuth consent, deploy-from-chat, managed sandboxes, and structured machine-readable status, since no action is dashboard-only. 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.

PanWatch's three scheduled AI agents plan the trading day before the bell, watch the session, and review it after the close for your China A-share, Hong Kong, and U.S. holdings. Day one begins with the portfolio: several brokerage accounts, holdings and profit and loss, and search for stocks or listed ETFs by code or name. The pre-market agent folds overnight moves, news, and technical structure into that plan and skips exchange holidays. Through the session, the intraday monitor watches for unusual moves and technical signals. Price alerts combine price, percentage change, turnover, and volume ratio with AND/OR logic, cooldowns, and expiry times. Each rule picks its own channel from Telegram, WeCom, DingTalk, Feishu, Bark, or a webhook. Spot something odd? The brain icon next to a holding starts TradingAgents, where four analyst roles feed a bull and bear debate, a risk review, and a portfolio-manager decision, with the reasoning trail in the app and your notifications. The opportunities screen ranks AI-scored ideas with entry levels and targets, and paper trading simulates signal-based entries and exits and tracks equity and performance. At day's end, the daily report reviews the session and prepares the next trading day's plan. OpenAI-compatible providers or local Ollama models power the analysis, and the PWA installs on a phone in English or Simplified Chinese. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

When shuffle algorithms start feeling sterile, Subwave transforms your self-hosted Navidrome or Subsonic music library into a live 24/7 personal internet radio station hosted by AI DJ personas. Every listener tunes into a single shared Icecast broadcast simultaneously. Curated tracks play alongside spoken station idents, local weather reports, news briefings, time checks, and track introductions. Want to hear something specific? Listeners submit plain-language song or mood requests directly from the web player, native mobile and desktop apps, or an MCP client, and the on-air DJ weaves those selections into the rotation. Operators staff up to 24 distinct DJ personas with guest co-hosts, programme a 24x7 weekly show grid with multi-hour episode arcs, and customize between-track skills from the browser admin console. Acoustic analysis measures BPM, musical key, loudness, vocal ranges, and track endings so crossfades and voice ducking sound like a studio broadcast across MP3, Opus, AAC, and lossless FLAC streams. An interactive Library Observatory maps every analyzed track by genre and energy. Runtime-swappable LLM providers (Ollama, OpenAI, Anthropic, and OpenRouter) and six local or cloud TTS engines keep voices flexible. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

When an AI agent breaks in production, Tracely freezes that exact run into a replayable regression test and blocks the pull request that would ship the bug again. Span soup hides the failure. OTLP/HTTP traces group into conversation threads, and a waterfall marks the failing span in red with its input and output. Nobody knows if an answer was good. Evaluators sit as columns on the trace table, mixing model-free checks with LLM judges at conversation, run, or span level. Thirty-one broken runs, one issue. Clustering turns them into a single counted issue and can suggest the evaluator that would have caught it. A fix nobody can prove. One click promotes a failing trace into a hermetic case with recorded fixtures and a fail-to-pass contract, and scenarios send a red-team model after an adversarial goal. Model bills on every CI run. The suite replays offline with no API keys and no model spend, and tracely gate posts a commit status, comments on the pull request, and blocks regressions. No warning when it breaks again. Alert flows drawn on a canvas react to failed gates, broken conversations, unseen failure modes, or rising failure rates by messaging Slack, sending email, calling a webhook, or prompting an LLM. Coding agents can read traces and write evaluators through an MCP endpoint. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Which agent should answer a question that just arrived in your QQ group, and how much of the conversation should it see? RabiRoute is the self-hosted message gateway that answers those routing questions before your agent ever wakes up. Chat messages from QQ groups and direct chats (through NapCat and OneBot), webhooks, schedules, voice, desktop selections, and device events all arrive at one gateway, and message Routes decide which agent or local program receives each one. Every role keeps its own message history plus references to plans, memories, and skills, while each Route limits how many recent messages travel with a delivery. Roles can also fire agents on interval, time-window, daily, or one-time schedules, or run a configured local script, so recurring checks and reports happen without anyone typing a prompt. Replies to QQ, RabiLink, and other channels leave through a single sending API that validates targets, quoted messages, and sender identity, then records receipts for everything delivered. The Windows desktop side adds selected-text actions, screenshots, and annotations; speech, phone, glasses, wearable, and remote-computer clients connect as experimental integrations, and the Linux Host serves the Manager and browser WebGUI from a Node.js process. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

salt.md is an open-source, self-hosted workspace where your team and its AI agents work on the same documents and databases, under the same permissions and with the same history. A slash-menu block editor handles checklists, tables, callouts, columns, code, diagrams, and embeds. Page links, backlinks, and a graph view show how pages connect. Any page can become a collection with typed properties like select, date, person, relation, rollup, and formula, shown as a table, board, list, gallery, calendar, timeline, or form. Ctrl+K searches titles, body text, row values, and the text inside uploaded PDFs. Two people can type in the same paragraph at once with live cursors. Comments, page history, and an activity log record who changed what. Publish a page as a read-only link with an optional password and expiry, or hand people without accounts a form that adds rows to a collection. Agents connect over MCP with 33 tools for searching, writing, building databases, and commenting, using tokens scoped to one workspace or read-only. Signed webhooks, iCalendar feeds, and Google or Microsoft sign-in link it to the rest of your stack. Import Markdown, ZIP archives, or a Notion export, and export pages as Markdown, HTML, or PDF. Use it for handbooks, meeting notes, project boards, and a knowledge base your assistants can read. 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.