Every AI project you build in RESTai becomes an endpoint that any app can call over plain HTTP. RESTai gives you a browser dashboard where each project gets its own model, system prompt, tools, and chat playground. Build knowledge-base assistants over uploaded files and synced web pages, ReAct-style agents that call MCP servers, or drag-and-drop block projects that need no model at all. Connect Ollama, OpenAI, Anthropic, Gemini, vLLM, Azure, Bedrock, or any OpenAI-compatible endpoint, and let teams share the ones you approve. Daily charts follow tokens, cost, and latency per project, with rate limits, guardrails, prompt version history, and evaluation runs for quality tracking. Teams, roles, two-factor sign-in, white-label branding, and an audit trail cover administration. A one-line chat widget embeds a project on any website, and connectors reach Telegram, Slack, and WhatsApp. One install can serve several branded assistants and bill each team separately. 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.

Moltis gives individuals and teams a completely private personal AI agent server that bridges conversational assistants to everyday messaging platforms while executing real-world computing tasks inside secure execution environments. Users can interact with autonomous agents across Telegram, Discord, WhatsApp, Slack, Matrix, and browser interfaces to draft correspondence, automate research, and schedule recurring cron tasks. The system coordinates multi-agent delegation by spinning up specialized sub-agents with dedicated roles for code generation, pull request reviews, quality assurance testing, and technical documentation. Built-in sandboxing isolates tool operations within container boundaries or WebAssembly modules, ensuring shell commands, web scraping routines, and script executions cannot alter underlying operating system files without explicit permission. Native Model Context Protocol integration allows operators to attach external data endpoints, database connectors, and custom command-line utilities without rewriting core routing logic. Persistent memory preserves conversational context and document embeddings across multiple sessions, allowing assistants to recall prior discussions, user preferences, and project guidelines indefinitely. Administrators can configure granular tool approvals, manage WebAuthn passkey authentication, and review real-time WebSocket communication logs through an embedded control panel. 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 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.

Claude Code Agent Monitor puts every AI coding agent session on one live control room, so you can see what each agent is doing, what it costs, and where it got stuck. Claude Code, Cursor, and Codex sessions land together in a dashboard, a sessions list, an activity feed, and a kanban board. Open any session to read the full rendered conversation with highlighted code, tool calls, command output, and sub-agent timelines. The analytics page charts spend by model and weekday, token totals, cache hit rates, and a 52-week activity heatmap. Workflow views map parent and child agents, delegation, compactions, errors, and concurrency. An Agent Config explorer lists your skills, subagents, slash commands, hooks, plugins, MCP servers, and memory files in one place. The Run Agent page starts a conversation or one-shot job, streams output, and resumes earlier sessions without leaving the browser. Webhook alerts, push notifications, and a REST API keep the rest of your tooling informed. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Drag nodes onto a canvas and ship an LLM app: Flowise is an open-source visual builder for AI agents and LLM applications, written in Node.js on LangChain.js and licensed Apache-2.0. You assemble flows by dragging nodes onto a canvas: models, prompts, memory, vector stores, retrievers, and tools, then wire them together and test in the built-in chat panel. Three builder types cover increasing complexity: Assistant for simple RAG chat over uploaded files, Chatflow for single-agent systems with techniques like rerankers and Graph RAG, and Agentflow for multi-agent orchestration with branching, looping, shared flow state, and human-in-the-loop checkpoints. Over 100 integrations connect data sources, vector databases, and both proprietary and open-source models, plus MCP client and server nodes for standard tool interop. Finished flows are exposed as REST APIs, embedded chat widgets, or via JS and Python SDKs - each flow gets an endpoint the moment it is saved, removing the deployment gap between a working prototype and something your application can call. Execution logs, visual step debugging, and external log streaming trace behavior, while input moderation and rate limiting act as guardrails; RBAC, SSO, and workspaces cover team deployments. Self-hosting keeps prompts, encrypted credentials, and conversation data on your own instance, which matters when flows handle internal documents or customer data - and wiring a model, prompt, memory, and vector store on the canvas replaces the boilerplate a hand-coded LangChain project would need.

MulmoTerminal is a browser cockpit for running many AI coding agents at once, laying every session out in a color-coded grid so you can see at a glance which agents are working, which are finished, and which are sitting idle waiting on you. Each cell is a real terminal running Claude Code, Codex, Muse, GitHub Copilot CLI, Cursor CLI, Grok, or Antigravity, and its border turns amber with a chime the moment a permission prompt or question blocks progress. Zoom into one session and the cockpit roster keeps the rest in view as one-line summaries with your last prompt, the agent's latest reply, and each branch's pull request phase. Agents hand you more than text: a Canvas panel renders documents, forms, charts, and generated images they produce, while per-session context, token, and cost readouts keep spending legible. Isolate parallel work in one-click git worktrees, review the diff, then commit, push, and open the pull request without leaving the grid. Sessions persist through tmux across restarts, Web Push pings your phone when a task finishes or needs input, and per-directory themes and name badges keep a wall of agents readable. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Close the laptop, keep the agents: Roamgate brings the Herdr workspace running on your server into any browser, so the terminal session you left mid-task is waiting on your phone exactly as you left it. Every workspace and recognized agent sits in one view: check what each agent is doing, read its conversation, and take over a real terminal with streaming output, split panes, scrollback, multiline paste, and clickable links. When the agent finishes, the review happens in the same place: inspect staged, unstaged, untracked, and branch changes, annotate exact diff lines, preview rendered Markdown, and send compiled feedback back into the agent pane without pre-filling a submission you did not approve. Files browse beside the terminals, and session history survives disconnects because Herdr owns the sessions, not your browser tab. Connections stay flexible: run the bridge beside Herdr on one machine, save SSH profiles to reach remote hosts, and install the whole thing as a PWA for an app window without tabs. Login is required even on loopback, push notifications flag agents waiting for input, and themes, accents, and terminal fonts make the cockpit yours. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Open Agent Builder delivers a visual canvas for orchestrating AI agent workflows without writing Python scripts or managing complex codebases. The React Flow-powered drag-and-drop interface supports seven node types — Agent, Scraper, Transform, If/Else, Loop, User Approval, and MCP Tool — each configurable with provider-specific settings for Anthropic Claude (Haiku 4.5 and Sonnet 4.5), OpenAI GPT-5, Groq, or any OpenAI-compatible endpoint. The LangGraph orchestration engine handles state management, conditional routing, and human-in-the-loop approval gates while Firecrawl integration converts any website into structured, LLM-ready data through scrape, crawl, and map operations. E2B sandboxed code execution powers Transform nodes for secure data manipulation without risking host system integrity. Real-time streaming updates show execution progress node-by-node as workflows run, with Convex providing reactive database synchronization for workflow state and execution history. The TypeScript-first architecture (96.8% TypeScript) built on Next.js 16 App Router with Tailwind CSS delivers a responsive interface across devices. Clerk handles multi-user authentication with JWT integration for secure workspace isolation. Deploy via npm install and environment configuration with Firecrawl, Convex, and Clerk API keys. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Running AI agents in production takes more than a model call: Omnara supplies the durable runtime, tools, approvals, and complete event history around any model, on your own machines. You define an agent once in a small YAML file: instructions, a model from OpenAI, Anthropic, OpenRouter, Bedrock, LiteLLM, Ollama, or your own endpoint, and the machines it may use. Launch agents from the REST API, the TypeScript SDK, the command line, or the dashboard, then stream every event live or receive it as a webhook while the agent works. Agents run shell commands and edit files on sandboxes from twelve providers, or on your own laptops, VMs, and containers through a daemon that connects outward, so no inbound ports or SSH keys are exposed. Every step is written to Postgres as an event log, which means an agent survives crashes, restarts, and disconnected machines and resumes exactly where it stopped. Tool permissions can run immediately, ask a person first, or block outright, and agents can start subagents, follow cron schedules, and keep shared memory files between conversations. Teams meet the agents where they already talk: mention the bot in Slack or Discord, or let a GitHub pull request trigger a review, with questions and approvals handled in the thread. 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.

PilotDeck introduces a WorkSpace-first architecture where each project receives its own isolated file system, memory store, and skill set, preventing context bleed between parallel tasks. White-box memory makes generation, extraction, storage, and retrieval fully visible, letting users audit, edit, pin, and rollback individual entries when the agent misremembers, while Dream Mode consolidates memory fragments during idle windows. Smart Routing auto-detects task difficulty and sends complex calls to flagship models like Claude Sonnet or GPT-4o while routing simple requests to lighter models, achieving claimed 70% cost savings through on-device and cloud co-orchestration with TokenSaver tiering and sticky session binding. Always-on background execution keeps agents running after the user closes the browser, with Discovery and Cron-based scheduling for recurring workflows. The platform natively supports the Model Context Protocol for first-class MCP server integration, community skills via ClawHub on npm, lifecycle hooks intercepting PreToolUse and UserPromptSubmit events, and custom memory store providers. Multi-provider fallback automatically switches to backup providers on timeout or rate-limit errors. The WebSocket and HTTP gateway serves web, CLI, desktop, and Feishu IM channels from a single configuration. 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.

Aegra runs your LangGraph agents on your own infrastructure with the same SDK and APIs you would use on the managed platform, so moving in does not mean rewriting your agents. You deploy an agent once and clients connect through Agent Chat UI, LangGraph Studio, or CopilotKit, while threads, runs, and checkpoints persist between sessions instead of vanishing when a process restarts. Streaming answers arrive token by token over server-sent events, and if a connection drops, the stream reconnects and replays missed events rather than losing the run. Human-in-the-loop gates pause an agent at the step you choose, wait for a person to approve or edit, and then resume from exactly that state. Scheduled cron jobs trigger runs on standard or seconds-level expressions with timezone support, which turns agents into recurring workers for reports, checks, and follow-ups. When traffic grows, Redis-backed workers process runs with lease-based crash recovery, so a dead worker's job is picked up instead of disappearing. Authentication handlers plug in JWT, OAuth, or Firebase, custom endpoints sit beside the agent API, and traces fan out to the observability backend you already run. 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.

NextClaw is an AI workspace where a request for a report, a chart, or a small tool becomes organized research, files, and steps, with the result shown beside the conversation. Pick the engine for each task from Native, Claude Code, Codex, Hermes, or OpenCode, and the agent keeps its memory, skills, and workspace. A right-hand browser opens code, Markdown, HTML, Word, Excel, and PowerPoint files without losing the task that produced them. Connect providers like OpenRouter, OpenAI, Anthropic, Gemini, DeepSeek, or any OpenAI-compatible endpoint, and message the same agents from Telegram, Discord, Slack, WhatsApp, Feishu, or email. Scheduled tasks start from templates like a daily AI news brief or a competitor change tracker, and finished reports land in an AI Inbox you can read later or continue as a chat. A skill market installs new abilities, MCP servers extend tools, and Panel Apps keep the small pages an agent builds for you. Dedicated agents get their own role, home directory, and memory. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Every AI agent gets a face, a colour, and a job in Murmur, a chat app that makes running Hermes Agent as friendly as texting a colleague. Start from a template (Researcher, Writer, Planner, Coder, Coach, or Chef) or describe a new agent from scratch, then talk to one at a time or drop several into a group room and call on a single one with an at-mention. Replies stream in live, long jobs show a plan that ticks itself off, and every step appears in plain words. Connect a model with a ChatGPT plan, a local model server, or an API key from OpenRouter, OpenAI, Anthropic, and others, with the model and thinking effort chosen per agent or chat. Agents can reach Notion, Linear, Todoist, Figma, and dozens of other apps, and they ask for an Allow or Don't allow before changing anything important. Morning briefings run as routines, a memory view shows what each agent knows with controls to edit or forget it, and WhatsApp or Telegram can be linked by scanning a code. A voice call mode lets an agent answer out loud, and slash commands set long-running goals or ask quick side questions. Chats sync across browser, desktop, and phone. Solo builders, homelab fans, and small teams get a calm front door to their own agents. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Unify fragmented corporate knowledge across chat channels, documents, and cloud drives with PipesHub, an open-source workplace context platform providing permission-aware search and verifiable answers for teams and autonomous agents. Employees can query enterprise knowledge bases through a conversational interface that retrieves relevant information across Google Workspace, Microsoft 365, Slack, Confluence, Jira, and GitHub while strictly respecting individual user access permissions. Knowledge workers can verify every answer through clickable citation blocks that trace claims directly back to source documents, spreadsheet rows, or chat messages. Teams can assemble custom AI agents visually using a drag-and-drop builder, combining retrieval collections with interactive toolsets to automate multi-step operations like drafting customer responses or creating issue tickets. Autonomous agents connect via Model Context Protocol to inspect shared company knowledge and perform external actions across connected SaaS tools. Organizations can index scanned PDFs, slide decks, markdown pages, and spreadsheets with OCR and document parsing, maintaining synchronized records through automated schedules. Administrators can inspect synchronized records, monitor query history, and manage connector credentials across all integrated business applications. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache License 2.0 licensed.

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.

Your laptop, a desktop, and a build box each have a coding agent installed, and until now nothing has coordinated them. ADHDev is a self-hosted control plane that puts Claude Code, Codex, Kimi, Cursor CLI, Antigravity CLI, Grok CLI, and OpenCode behind one shared task queue and one web and mobile dashboard. Machines pair directly with an address and a one-time code on your own network, and a mesh binds to a single repository. Idle nodes claim tasks themselves. Dependencies order the queue, retries absorb failures, and missions group the work that belongs together. Every task gets an isolated git worktree the moment it starts. Agents build in parallel without touching each other's files, and the coordinator's prompt is rendered from live mesh state at launch, with events pushed in as they happen. Difficulty tags route easy work to cheap models and hard work to strong ones. The dashboard also reads how much of each subscription window remains, skips plans that are nearly empty, and shows the routing forecast before anything runs. Finished work enters the Refinery. Your repository's gates decide, the branch is rebased onto main, and the merge happens only when main has not moved, followed by automatic worktree cleanup. 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.

Statewave is the memory runtime that compiles what your AI agents experience into typed, provenance-tagged memories, so the same subject asked the same question receives the same context every time. Recording is append-only: your application writes events as episodes (chat, ticket, commit), and a compiler distills them into structured memories with confidence scores, each traceable to its source episodes. When an agent needs context, Statewave assembles a ranked bundle inside the token budget you set; the same request at the same moment returns identical bytes, so retrieval sampling noise never leaks into an answer. Every bundle leaves an HMAC-signed receipt that a replay endpoint can re-evaluate under the same rules. Memories carry sensitivity labels for personal data, financial details, and secrets, and YAML policies deny or redact them per tenant. One instance serves many products: tenants are isolated by header, pinned to a region for residency with cross-region requests refused, and erasable by subject on request. The default compiler runs fully local on regex heuristics with no API key, or point extraction at any of 100+ LiteLLM providers. Reach it over REST from any language, through typed Python and TypeScript SDKs, LangChain, CrewAI, and AutoGen integrations, or the built-in MCP server that lets Copilot, Claude, and Cursor share one memory. Support agents recognize returning customers across sessions, and coding agents keep project decisions between conversations. 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.

With over 2,100 GitHub stars in its first month and benchmarked at 30-75% lower cost than Claude Managed Agents on enterprise task suites, TrueForge is the open-source agent harness that provides the complete runtime layer for turning any LLM into a working production agent on your own infrastructure. The TypeScript server runs the full execution loop — streaming every step, routing tool calls through MCP servers with centralized header-auth and in-chat OAuth, delegating parallelizable work to isolated subagents, and pausing for human approval on sensitive actions. Context engineering keeps token costs low: deferred tool-schema loading delays MCP schemas until invoked, large-result offloading moves oversized outputs to files, Code Mode processes structured data through sandboxed execution, and automatic compaction summarizes older history at a configurable 50,000-token threshold while preserving the full transcript. The sandbox-as-a-tool architecture provisions isolated Daytona environments only when code execution is required, allowing one server to run many concurrent agents without idle overhead. Agents are configured from shipped YAML catalogs of models, MCP servers, git-backed SKILL.md instruction packs, and sandbox providers, then saved to an Agents Library accessible via the chat UI, TypeScript SDK, or embeddable React UI SDK. Run locally with SQLite via a single npx command, or deploy for teams with Docker Compose or Helm using Postgres and Redis with OIDC authentication. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.