Grasp
One sentence in, one reviewed pull request out: Grasp sends coding agents through a visual workflow in isolated sandboxes and leaves every approval to people. Describe a task on the home page and run it as a workflow or a Solo session. A clarify agent first asks one question at a time as clickable option cards with a recommended answer, then writes a requirement spec and plan and builds a page mock you can annotate. Workflows are drawn on a visual canvas with six node types, and failure and rollback edges send work back to an earlier step. Eight agent CLIs, including Claude Code, Codex, Cursor, and OpenCode, can run as agent nodes in a Docker, Kubernetes, or E2B sandbox shared by the nodes of a run. Runs pause at human gates in a shared inbox, and a temporary one-time link lets a reviewer without an account approve or reject. Solo sessions give a single agent an IDE, terminal, and browser, and a noVNC panel lets you watch its Chromium and take over with a click. Specs, plans, test results, and HTML previews are kept as versioned artifacts. A token page breaks cost down by workflow, source, and model. Agents push branches and open pull requests or merge requests through gh, glab, or SSH credentials stored per repository. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.
Javis OS
Javis OS turns the AI models you already pay for into a team of coworkers that share one memory, so switching to a better model never means starting over. Fourteen brains plug into the same toolbox, from Claude Code and Codex to OpenRouter, Gemini, Groq, DeepSeek, and local Ollama. Everything they learn lands in a Second Brain, an Obsidian-compatible markdown vault of memories, wiki pages, and sources, drawn as a knowledge graph you can search and edit. After each conversation, self-learning distills new memories, wiki entries, and skills, and every pass is a git commit you can undo in one tap or back up to a private GitHub repository. Hand over a goal in plain words and the Kanban dispatcher writes the spec, picks a worker, runs it in the background, and calls you only on exceptions. Loops and reminders fire on an interval, a clock time, or a cron expression. Coworkers on the Partners page get their own role, model, prompt, and skills, and teams of them chat in one room while a leader hands out work. Chatbots answer customers on WhatsApp, Messenger, Instagram, Telegram, Slack, and Zalo from one shared inbox. An MCP connection store holds several accounts per service under three hard-enforced permission levels. Hands-free voice, cost tracking, TOTP two-factor login, and in-app updates with rollback 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. MIT licensed.
AnythingMCP
Connecting autonomous AI assistants to internal enterprise databases and legacy systems is streamlined by AnythingMCP, a visual Model Context Protocol gateway with automated knowledge graph generation and granular access controls. Engineers can import OpenAPI specifications, Postman collections, SOAP WSDL files, or raw database credentials to generate standardized Model Context Protocol tools in minutes without writing custom code. The built-in knowledge graph automatically maps entity relationships across disparate databases and software platforms, teaching agents how to correlate customer records in CRM tools with live order histories in enterprise resource planning software. System administrators can enforce fine-grained access policies by restricting tool execution permissions to specific roles and scoping database operations to read-only queries with strict row limits. An interactive web console provides real-time tool inspection, payload testing, request tracing, and comprehensive audit logs that capture every upstream invocation with full parameter visibility. Enterprise teams can integrate identity providers through OAuth2, SAML single sign-on, and SCIM automated user provisioning while protecting sensitive credentials using AES-256-GCM encryption at rest. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. GNU AGPLv3 licensed.
Hermes Studio
The most comprehensive open-source control plane for Hermes Agent — a full workspace combining AI chat, visual workflows, multi-agent orchestration, coding agent management, and platform channel integration in one self-hosted dashboard. Real-time chat streaming over Socket.IO connects to any OpenAI-compatible backend including Ollama, OpenAI, Anthropic, and custom endpoints with multi-session management, tool call expansion, inline file previews for HTML, PDF, DOCX, images, and source code, plus profile-scoped uploads and workspace attachments. The visual workflow builder provides a Vue Flow canvas for constructing DAG-structured pipelines with directed edges, conditional routes, approval gates, loops, and live execution with per-node status updates. Platform channel integration configures Telegram, Discord, Slack, WhatsApp, Matrix, Feishu, DingTalk, QQBot, WeChat, and WeCom bots from one page with credential management and per-platform behavior settings. Multi-agent group chat rooms enable real-time messaging with @mention routing, automatic context compression, and SQLite message persistence. The coding agent panel installs, launches, and monitors Claude Code and Codex with built-in terminal, session history, and file diffs. Usage analytics track token consumption, estimated costs, cache hit rates, and 30-day daily trends with model distribution charts. Kanban boards plan and track agent work alongside cron job scheduling for recurring tasks. Deploy via Docker, npm CLI, or desktop installer for Windows, macOS, and Linux. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.
Cezar
Close the laptop; the agents keep shipping. Cezar is an open-source control center that runs Claude Code, Codex, OpenCode, Copilot, and eight other coding agents in parallel on your own server, around the clock. Every task gets an isolated git worktree, so a dozen agents edit the same repository at once without colliding, and overflow waits in a queue. You watch each run live: the agent's text, its tool calls, token counts, and reported cost stream into one cockpit covering all your projects. The workspace dashboard separates what needs your answer, what is running, and what finished, and the usage view totals spend and tokens per project so a runaway task shows up in dollars, not surprises. Repeatable playbooks are plain Markdown skill files, chained into short YAML workflows that can mix a different agent per step, add checks and gates, and open pull requests; nothing merges on its own. Hand it a GitHub issue in one click, connect Jira or Linear to launch from your tracker, and schedule recurring maintenance with automations. Flip Autonomous and a run stops asking questions and just finishes; run the same task two or three times and keep the best diff. State lives in plain files, no database, and the responsive interface works from your phone. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.
UnoPim
If product data is scattered across spreadsheets, supplier PDFs, and storefront admin screens, UnoPim collects it in one open-source PIM catalog and lets an AI agent do the cleanup. Ask the floating chat panel to find every product missing a description, and the agent searches, bulk edits, categorizes, exports, and drafts copy, sending risky changes to an approval queue and honoring each user's permissions. Magic AI wands generate descriptions, translations, and images through providers such as OpenAI, Anthropic, Gemini, Groq, Ollama, and Mistral, plus any service that follows the OpenAI API format. Attribute families decide which fields each product type needs, variant structures pass shared values from a parent to color and size children, and association types link related items, up-sells, cross-sells, and spare parts. Completeness scores show what each channel and locale still lacks, saved filters turn recurring searches into one-click views, and measurement families convert inches to centimeters on export. CSV, XLSX, and ZIP jobs run on a queue with a live tracker, signed webhooks alert storefronts and ERPs to changes, and API keys unlock the REST API. Digital Product Passport templates publish QR-linked pages per product and language. Admins get role-based permissions, Microsoft Entra sign-in, 33 languages, and a dark theme. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.
Proval
Proval is a self-hosted AI code review agent that reads every pull request on your GitLab, Forgejo, or GitHub server and posts a consolidated, severity-grouped review with inline comments, using a model you run yourself. When a pull request gets a meaningful push, a planning agent groups changed files into review units and dispatches specialist sub-agents in parallel, each exploring the codebase so cross-file issues surface. A writing agent merges their findings into one review, with comments on the affected lines, including multi-line ranges. Reply to any Proval comment and it reads the thread context and answers, and it works on issues too, greeting new ones and answering follow-ups on every message or only when mentioned. Choose per repository whether reviews run on first push only, every push, or not at all, skipping drafts until they are marked ready. Every review, reply, and issue comment is logged with its token usage, so each model's cost shows in the dashboard instead of hiding in an API bill. Your code is never stored; review context goes only to the LLM endpoint you configure, whether that is a cloud API or a local Ollama or llama.cpp server on your own network. Connect GitLab or Forgejo with an access token and webhooks, or GitHub through a GitHub App; Gitea and Codeberg use the same Forgejo-compatible path. 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.
Bionic
Bionic gives a company its own private AI workspace where models can read documents, use approved tools, run code, and hand back finished files. Staff open a chat, pick a model, and ask for work; the agent searches datasets, calls connected systems including Gmail, Google Drive, Salesforce, ServiceNow, and Jira, and saves spreadsheets, reports, and PDFs as artifacts. Skills package reusable instructions for jobs like release readiness, incident briefings, policy gap reviews, and RFP responses, so a good workflow gets written once and reused by everyone. Datasets collect security policies, product docs, handbooks, and support archives for grounded answers. Administrators manage API keys, watch token usage and request charts, set rate limits, configure providers, and divide people into teams with their own assistants. SSO, role-based access, and an audit trail keep the rollout governed. Developers can issue model and assistant keys and turn any OpenAPI specification into a new integration. 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.
Open Agent Email
Every AI agent that deals with people eventually needs an email address, and Open Agent Email gives each one a real inbox on your own domain. Agents receive mail in proper threads, reply in place, send new messages, schedule sends up to 90 days ahead, and handle attachments, labels, search, trash and restore from one mailbox. A human approval gate can hold any outgoing message until a person clicks approve or reject, with an expiry and a full history, so a risky reply never reaches a customer unchecked. Incoming mail is screened for prompt-injection tricks and hidden text, checked against SPF, DKIM, and DMARC, and can be scanned for viruses before an agent reads it. Agents connect through a REST API with an OpenAPI file, dependency-free Python and TypeScript SDKs, the oae command line, signed webhooks, a live WebSocket stream, or 96 MCP tools for coding agents. The browser dashboard covers guided setup, inboxes, pending approvals, the outbox queue with retries, delivery metrics with bounce and complaint tracking, contacts, templates, domains with DNS verification, and API keys. Sending runs through your own relay, SES events feed suppression lists automatically, and scoped per-inbox keys limit what each agent may do. 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.
Platypus
Platypus gives a whole team always-on AI agents that reason, call tools, and keep working on your own servers while everyone is offline. Build an agent once by choosing a provider and model, writing its instructions, and capping its tool-calling loop, then reuse that preset across chats and scheduled runs. Agents load reusable Skills on demand and delegate specialist work to sub-agents that appear to the parent as tools. Connect local and remote data through Model Context Protocol servers, or expose an agent to outside agents and chat platforms through A2A endpoints with a token per client. Triggers run agents on a cron schedule, as one-off jobs, or when workspace events such as a card moving on a board occur, and every run records its result. Kanban boards give agents work they can move and update themselves, while notifications and HMAC-signed webhooks push board and workspace events into your own systems with filtering and retries. Facts and preferences are extracted from conversations in the background and injected into future chats, so returning users are remembered. Sandbox backends give agents shell and filesystem access inside an isolated per-workspace environment instead of the host. Organizations and workspaces keep each team's agents and data separate, and blueprints package shared agents, skills, MCP servers, and providers so a new workspace starts pre-equipped. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.
Codeman
Codeman is a self-hosted mission control for AI coding agents that runs Claude Code, Codex, OpenCode, Gemini, Copilot, and five more agent CLIs in persistent sessions you can watch and steer from any browser, phone included. Sessions live in tmux, so agents survive server restarts, network drops, and laptop sleep, with full scrollback replay when you return. Run up to twenty sessions as tabs or in a six-up tile grid, each streaming its real terminal with token and cost tracking, and tabs that blink when an agent goes idle or needs an answer. Idle detection re-prompts stalled agents, and when a subscription usage limit hits, Codeman parses the reset time, waits it out, and resumes the run unattended. Subagents appear as floating live windows tethered to their parent session, with real-time transcripts, token counts, and status badges. Agents can drive Codeman too, through a bundled skill, CLI verbs, and an MCP server that let one agent start, prompt, and collect answers from workers in other CLIs. Run a project in an isolated Docker container or on another machine over SSH, preview agent-created files in the browser, and reach everything from your phone with QR login and push notifications, or over Tailscale with a real certificate. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.
Lampline
Once a voice agent is imported or built, Lampline connects it to a phone line, sends an AI caller to grade real calls, and keeps it all on your own server. Start by importing a Dialogflow CX or CX Agent Studio export along with a report of anything to check, or build fresh in a drag-and-drop builder that mixes LLM steps with scripted pages for exact lines and form fields. Next, pick one of 20 model providers, including Claude, OpenAI, Gemini, Bedrock, Groq, and DeepSeek, or run Ollama with local speech and no API keys. Test by chat or microphone while each step lights up, and let agents call HTTP and MCP tools and save records in collections of their own. Then connect callers through Twilio, Telnyx, or any SIP trunk, PBX, or session border controller via jambonz, with transfers to a person that carry the call's details as SIP headers. Finally, evals phone the agent over a real line, where an AI Test Caller brings background noise, accents, and interruptions, grades each transcript check by check, and reports typical and p95 response times as callers hear them. Each agent stays a folder of YAML and Markdown that you can review in git and lint or test with the vk CLI. 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.
Sugabots
Give your team a shared chat workspace where AI bots sit next to people, answer questions, and pick up recurring work. Organize conversations into pods with channels and threads, and keep a private personal pod for each member. Mention a bot with @ to hand it a task, mention several and each one replies, or let a bot ask another bot for help. Every bot gets its own name, avatar, instructions, and model, picked from OpenRouter, Anthropic, OpenAI, Google Gemini, or any OpenAI-compatible endpoint you add. Connections link a pod to GitHub, Linear, Stripe, Notion, Sentry, Jira, any MCP server, or any HTTP API, and bots act through them with approvals where you want a human check. Routines run a bot on a schedule, a webhook, or a GitHub event, then post the result to the pod channel. Computers give bots an isolated machine for heavier jobs, and web search lets them look things up and cite pages. A Usage page breaks down what bots cost by bot, model, and pod. Use it for a support desk, an engineering ops room, a morning briefing, or a shared research assistant. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.
Opik
When an AI agent goes wrong at step seven of twelve, Opik, an open-source LLM observability platform, shows the exact trace, tool call, and prompt behind it, then scores your fix against test datasets. Full trace trees capture every LLM call, retrieval step, and tool execution, and you can annotate traces and spans with feedback scores in the UI or through the SDK. Native integrations for OpenAI, Anthropic, LangChain, LlamaIndex, CrewAI, Google ADK, and DSPy, plus OpenTelemetry for any language with an OpenTelemetry SDK, feed traces in, or add the @track decorator to your own functions. Datasets and experiments compare prompt and model versions, scored by LLM-as-a-judge metrics for hallucination, moderation, and RAG relevance, with a PyTest integration to run evaluations in CI. A Prompt Playground tests prompts across models, and the Agent Optimizer SDK helps improve prompts and agents. Production dashboards track feedback scores, trace counts, and token usage, online evaluation rules score live traces, and optional guardrails add safety checks. An MCP server lets Claude Code, Cursor, VS Code Copilot, Codex, or opencode read traces and run evaluations from chat. Run it yourself with the ./opik.sh script on Docker Compose, or a Helm chart on Kubernetes, so trace data stays in your infrastructure. 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.
SuperPlane
SuperPlane is an open-source engineering automation platform that turns routine backlog tickets into verified, review-ready pull requests while orchestrating complex multi-system workflows across your developer tools. Engineers use the visual infinite canvas to assemble event-driven pipelines with trigger nodes, conditional routing, loops, and human-in-the-loop approval gates. You can delegate pull request code reviews, automated QA testing, documentation generation, and release management to coding agents operating within strictly defined policy boundaries. Custom operational consoles let teams build live monitoring dashboards displaying key delivery metrics, active incident states, and execution histories from connected tools. Integrations connect natively with GitHub, GitLab, Datadog, PagerDuty, Slack, AWS, and leading AI models through webhook events and bi-directional actions. Every automation run maintains durable state persistence across process restarts, ensuring failed steps resume with full input payloads and debugging context intact. Developers can define reusable work orders, configure canvas memory for long-term state retention, and execute fleet commands over SSH or containerized runners. 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.
Manifold
One workspace, a whole roster of AI specialists: Manifold is an agent platform for long-horizon objectives that run through chat, visual workflows, and scheduled tasks. Specialists carry their own model, prompt, and tool allow-list, group into teams, and collaborate across many turns in a chat view that renders HTML visualizations beside text. Models come from OpenAI, Google, Anthropic, or any server that speaks the OpenAI API, such as llama.cpp or vLLM, and image generation reaches OpenAI, Google, or local ComfyUI. The flow editor draws workflows on a canvas, exposes MCP tools as nodes, and turns a saved workflow into a tool that specialists and other flows can call. Pulse schedules specialist tasks at intervals, daily, or once at a chosen time and delivers results to Matrix rooms. Projects isolate agent workspaces to their own folders, load skills from each project's skills directory, and include a file browser with upload, download, and Markdown preview. A Playground versions prompts and datasets and runs experiments that show how a prompt change shifts behavior, while the overview dashboard charts token usage, traces, and logs. Sign-in through OIDC or OAuth2 is optional and adds user and admin roles. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.
Saiku Analytics
Point Excel, dashboards, and AI agents at one governed cube and Saiku Analytics, an open-source semantic layer, answers all three with the same numbers. The Query Editor writes the MDX as analysts drop measures and levels onto rows, columns, and filters, then shows a pivot grid or 16 chart types such as treemap and sunburst. Dashboards mix KPI, chart, table, text, and image tiles with cross-filtering, drill-down, conditional formatting, and forecast overlays, then export to PDF or PNG, share read-only links, or embed as a web component. An Excel add-in drops governed PivotTables that refresh live, and a Google Sheets add-on inserts cube data as tables that refresh in place. Agents get a typed REST API that lists cubes and measures, accepts JSON questions at /ai/query, and returns the exact field and legal values when validation fails. An MCP server connects Claude Desktop, Cursor, and Cline with a one-click .dxt install, and agent spaces limit each persona to chosen cubes and markdown skills. No semantic model yet? Saiku drafts cubes, dimensions, measures, and joins from a warehouse schema for review. Queries run on DuckDB, ClickHouse, Snowflake, BigQuery, Postgres, and dozens more databases, and model diff flags every saved query or dashboard a schema change would break. Okta and Entra ID provision accounts over SCIM 2.0, and sign-in runs through OIDC or SAML. 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.
OpenHermit
Run a whole fleet of AI agents as managed services, each with its own model, memory, schedules, and sandboxed workspace, from one admin console. Create an agent, point it at OpenAI, Anthropic, OpenRouter, or any OpenAI-compatible endpoint, store its API keys encrypted, and it is ready to chat in the browser. People sign in with a device key and get a session list, streaming replies, and file attachments. The Agents table shows status, last activity, sessions, errors, and token spend for the past 24 hours, and the Stats page tracks users, sessions, events, and total tokens. Cron or one-shot schedules let an agent send a daily brief, and each run is logged. Owner, user, and guest roles control who may talk to an agent or change it, and policy and approval tabs gate risky tool calls. Skills and MCP servers are registered once and enabled for one agent or the whole fleet, and instructions can be pushed to every agent at once. Sessions, memories, and secrets sit in PostgreSQL, so state persists across gateway restarts. Use it for an internal agent platform, a support desk, or one agent per customer. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.