Memory OS gives Hermes Agent a permanent memory, so a new session opens with your projects, decisions, and working style already in context instead of introductions. Seven layers divide the job: workspace files carry your standing instructions into every turn, and a full-text index makes every past conversation searchable in place. Durable facts about your stack, your projects, and your patterns live in a structured store that resolves entities and scores how much each fact can be trusted, promoting what proves itself and demoting what does not. Cross-session recall pulls relevant moments from older threads, while a vector store with hybrid dense and keyword search finds the right memory even when the wording has changed. A self-curating wiki turns raw material into concept, entity, and comparison pages that are re-ingested automatically, and a Ground Truth hierarchy tells the agent to treat injected memories as authoritative instead of re-checking them. Scheduled jobs keep the system honest: hourly ingestion, weekly curation and decay scans, dead-letter reporting, and health heartbeats. It all runs beside the agent on your own machine with whichever provider you already use, from OpenRouter and Anthropic to a local Ollama. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Enterprises requiring production-grade governance for long-running autonomous AI operations can rely on OpenGeni, a self-hosted orchestration platform with human-in-the-loop approvals, Connected Machine execution, and comprehensive audit replays. Operators can configure durable multi-turn workflows that execute continuously toward specified goals without premature termination, automatically pausing when human verification, structured multiple-choice decisions, or critical credential approvals are required. Teams can assign execution workloads across ephemeral cloud sandboxes or route them straight to enrolled Connected Machines to run commands directly against local code repositories without exposing inbound network ports. The integrated web console lets developers inspect live Server-Sent Event activity streams, replay complete turn histories from audit logs, inspect generated artifacts, and cancel or steer in-flight agent tasks on demand. Platform administrators can enforce fine-grained access policies through GitHub App repository bindings, broker temporary role-scoped secrets, and maintain a shared organizational knowledge base where agents propose findings for human review before vector indexing. 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.

Searcharvester gives your AI agents a private search and research backend that runs entirely on your server, with a web UI where you watch every research job unfold. The search endpoint speaks the Tavily schema, so existing agent code points at your host and queries more than a hundred SearXNG engines without API keys or quotas. Send a URL to the extract endpoint and it returns clean markdown with navigation, footers, and ads stripped, sized in presets from five thousand characters to fully paginated long documents. Three extractors compete on each page and a quality gate keeps the best result, so hard pages still yield readable text. For bigger questions, the research endpoint runs a team of agents: a lead plans sub-questions, researchers gather in parallel, a critic tries to disprove the findings, and a fact-checker re-verifies numbers and dates before the final report arrives with clickable citations. You assign a different model and reasoning level to each role, follow agent branches, the reading graph, sources, and media live, then read the finished report in the same UI. Search settings let you toggle engines per category, test proxies, and apply changes with a targeted restart. A loop guard enforces budgets for calls, tokens, searches, and page reads across the whole job. 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.

Your coding agents finish a session, close the laptop, and forget everything; Pad is where the project remembers. It holds the tasks, plans, bugs, ideas, and decisions in one workspace that you drive from a browser while your agents drive it from the terminal, so the next session, human or machine, picks up exactly where the last one stopped. You plan on boards, lists, and tables with drag-and-drop status columns, rich item pages, comment threads, and a dashboard that answers what needs attention and what to do next. Your agents read the queue, claim items, leave checkpoints, link their pull requests, and mark work fixed with the fixing PR attached. Conventions teach them the house rules once, like running tests before calling a task done, and playbooks hand them repeatable multi-step workflows they can invoke by name. Every change is versioned with its author, a person or a named agent, and new items appear in the browser the moment an agent creates them in the terminal. The same workspace is reachable three ways: the web interface, the pad CLI, and a bundled MCP server with a natural-language skill that plugs into Claude Code, Cursor, Codex, Windsurf, OpenCode, Copilot, Amazon Q, and Junie. 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.

Unla puts a friendly front door on every API you already run, so AI clients can call it as an MCP server without anyone writing a line of glue code. Describe an endpoint in YAML or the form editor, name its arguments, choose where each one goes in the request, and the gateway exposes it as a tool over SSE or streamable HTTP. Import an OpenAPI file to generate a whole server at once, or proxy a third-party MCP server and route it under a prefix of your choice. The Gateway Manager shows every server as a card or table row with its routes, enabled tools, and tool counts. Every save creates a numbered config version with its author and timestamp, so changes are easy to audit and roll back. Tenants keep teams separate, user accounts carry roles, and CORS settings sit next to each route. Configuration hot reloads, syncs across replicas, and persists to disk, SQLite, PostgreSQL, or MySQL. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Kortix Suna is an AI management system where autonomous agents run on isolated Linux sandbox computers, producing finished deliverables that humans review through a change request workflow before anything merges. With 20,000+ stars, it positions itself against Claude Cowork and ChatGPT Work by storing every agent persona, skill, memory artifact, and connector in a git repository: versioned, diffable, and shared across an organization. Each session launches a dedicated sandbox with full terminal access, Playwright-controlled Chromium, writable filesystem, and internet connectivity. Over 3,000 app connectors are available through MCP, OpenAPI, GraphQL, and raw HTTP, with credentials brokered server-side so tokens never enter the sandbox. Skills (reusable markdown-plus-script packages encoding company workflows) load automatically into every session, compounding institutional knowledge over time. Bring-your-own-key model routing through LiteLLM connects to OpenAI, Anthropic, Google, Mistral, or local models without vendor lock-in. The deployment runs as a single Docker Compose stack bundling the Next.js frontend, FastAPI backend, Supabase, Redis, and Caddy with automatic TLS certificates. Enterprise features include SAML/OIDC SSO, SCIM provisioning, RBAC, and audit logging. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Elastic License 2.0.

OpenClaw Dashboard is a secure real-time monitoring dashboard for OpenClaw AI agents that tracks live sessions, API costs, rate limits, and host health from one browser page. The overview refreshes every five seconds with live session activity, token totals, and lifetime spending, so you can see what every agent is doing right now. Cost views break spending down by model, session, and time period, and rate limit panels track Claude and Gemini usage against rolling windows with browser alerts before quotas run out. A live feed streams agent messages across all sessions, and a session browser adds search, status filters, timelines, and a 30 day activity heatmap. You can read agent memory files (MEMORY.md, HEARTBEAT.md, daily notes) and edit workspace files, skills, and configuration with JSON validation and automatic backups. Host panels report CPU, memory, disk, and temperature with 24 hour sparklines, plus Docker containers, cron jobs, real-time logs, and one-click service restarts. A security page shows firewall rules, open ports, fail2ban status, and SSH login history, and sign-in uses PBKDF2 hashed passwords with optional TOTP two-factor codes. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Put a one-click approval gate between your AI agents and anything destructive or expensive. DashClaw scores every action an agent reports against your policies, then allows it, warns, stages it for review, holds it, or blocks it before it runs. Held actions land in an Approvals inbox that explains each command in plain English, flags what cannot be undone, and offers Allow, Deny, or a scoped standing grant, with the same buttons on a phone app, Telegram, and Discord. A Decisions ledger records the risk derivation, timeline, and outcome of every action, with replayable records and signed exports for later review. Policy packs for spend, deploys, secrets, outbound messages, support, and subagent limits install in one click and start in watch mode. Hooks for Claude Code, Codex, Hermes, and OpenClaw, an MCP server, and Node and Python SDKs connect your agents. Overnight coding runs stay supervised without anyone staying awake. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

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.

Anyone who pays for Claude Code, Codex, and Gemini CLI separately ends up juggling three endpoints, three sets of keys, and three kinds of rate-limit surprise, and CliRelay collapses all of that into one self-hosted gateway with a control panel. Clients speak the OpenAI Chat or Responses, Anthropic Messages, or Gemini protocol, and CliRelay translates each request for whichever upstream account is healthy. Channel groups limit where each key may send traffic, round-robin, fill-first, and session-sticky scheduling spread it, and cooldowns with automatic failover move requests off accounts that have run out of quota. Add upstreams from the /manage console through browser sign-in, device codes, or bulk credential import, covering Claude, Codex, Gemini, Antigravity, Vertex AI, AWS Bedrock, Grok, Qwen, Kimi, and any OpenAI-compatible service. Portal accounts own client keys with daily, period, and lifetime quotas, RPM and TPM limits, and per-model pricing. A monitor center scores health and charts live traffic, P50 to P99 latency, and time to first token, while every request lands in a searchable log with tokens, latency, and cost. Tenants, roles with resource.action permissions, content moderation profiles, an outbound proxy pool, and an audit trail make shared deployments workable, and the console speaks English, Simplified Chinese, and Russian. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Backed by the Linux Foundation with contributions from AWS, Cisco, IBM, Microsoft, Red Hat, and Shell, Agentgateway is the first data plane built from the ground up for AI agent workloads — providing a unified Rust-based proxy that handles conventional HTTP and gRPC traffic alongside MCP tool servers, A2A agent communication, and LLM inference endpoints through a single deployment. The LLM gateway routes requests to OpenAI, Anthropic, Gemini, AWS Bedrock, and other providers through an OpenAI-compatible unified API with per-tenant budget controls, spend tracking, prompt enrichment, load balancing across multiple model endpoints, and automatic failover when providers experience outages. The MCP gateway federates multiple tool servers behind one endpoint, supporting stdio, HTTP/SSE, and Streamable HTTP transports with built-in OAuth authentication compliant with the MCP auth specification, integrating Auth0 and Keycloak out of the box. OpenAPI integration exposes existing REST APIs as MCP-native tools without code changes, enabling legacy services to participate in agent workflows. Policy-based RBAC controls which agents access which tools, while OpenTelemetry integration provides distributed tracing across agent communication chains. Deploy as a standalone binary with flat YAML configuration or on Kubernetes using the built-in controller with Gateway API support for declarative infrastructure-as-code management. 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.

SandBase Harness gives your AI agents a proper home with sessions, tools, sandboxes, and an audit trail instead of a pile of scripts. The console lists agents with their model, status, and version, and an agent page shows its system prompt, attached tools, and skills. Every session keeps a resumable event log, and a transcript view opens any user or agent message as a rendered or raw event. Built-in tools run in a local process, per-session Docker containers, Kubernetes, or a self-hosted worker queue, and permission policies can always allow a tool or always ask a human first. MCP toolsets, credential vaults, and skill packages extend what an agent can reach, with Anthropic's xlsx, pptx, pdf, and docx skills listed next to your own. Memory stores, webhooks, scheduled deployments, and outcome definitions cover longer-running work. Settings include a model provider form, API keys for bearer authentication, and an interactive API reference for sessions, agents, environments, and vaults. A TypeScript SDK and a bundled MCP bridge connect other tools to the same runtime. 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.

DopplerTask is the control layer where AI agents build your automations and you decide what goes live. You describe the outcome in plain language, and your agent assembles a task from a library of eighty-one ready-made steps spanning messaging, ticketing, sales, operations, documents, databases, queues, and AI models. The proposal lands in a visual editor that people and agents share, with new and changed steps marked and the old value of each field beside the new one. Nothing goes live until you approve it, and the previously approved version keeps running untouched in the meantime. Once a task is live it can start from a webhook, a schedule, a message queue, a manual click, or the agent itself, and every run is recorded with the output of each step, the person who started it, and the person who approved the version. Failed runs resume from the step that failed, with retries and continue-on-failure where you want them. Agents reference your credentials by name only; the values stay encrypted on your server, beyond the agent's reach, and separate tokens for people and agents plus single sign-on keep access tidy. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

An agent run can finish without errors and still give the wrong answer, so TraceRoot traces every model and tool call, flags the production runs that missed the mark, and helps your coding agent ship verified fixes. Each run becomes a browsable call tree with inputs, outputs, latency, and cost, searchable by session or filter. Instrument with the Python or TypeScript SDK, the agent-native CLI, or any OpenTelemetry exporter, with ready integrations for LangChain, LangGraph, OpenAI Agents SDK, CrewAI, Vercel AI SDK, Mastra, and Pydantic AI. Detectors use LLM judges to score live traffic against the behavior you define and can post alerts to Slack. Judge outputs cluster into signals, then a background coding agent reads the traces and your connected GitHub code in a sandbox and recommends changes down to the commit, file, and line. Datasets, test cases, and scored eval runs compare versions so regressions surface before a release, and dashboards of widgets chart your trace data. The CLI hands your coding agent, such as Claude Code or Codex, the traces, signals, detectors, and evals to work from. Self-hosting keeps all of that trace data on infrastructure you control. 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 (core edition).

Tela keeps a team's documentation as canonical markdown in a self-hosted wiki that AI agents read, search, and write alongside humans through a built-in MCP server. People edit together with live multi-cursor collaboration, threaded comments, backlinks, and full revision history, so every page shows who changed what and why. PostgreSQL full-text search works immediately, and adding an embedder unlocks semantic retrieval and grounded ask-your-docs answers that cite their sources. Connect Claude, Cursor, or another MCP client with a personal access token and the agent can search the wiki, draft and patch pages, answer comment threads, build spreadsheets with real formulas, and assemble presentation decks exportable to PDF and PPTX. Atlas, the built-in documentation engine, points at a git repository or Jira project and drafts cited wiki pages, then keeps them fresh as the sources change. Teams organize work into spaces, invite members by email, and flip any space public to publish a login-free blog with per-author home pages. Content syncs over WebDAV and exports to zip or PDF, and optional AI features run against your own endpoint or a bundled local Ollama profile, so nothing leaves your server unless you wire it up. 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.

II-Agent is an autonomous AI agent platform that ranked first on the GAIA benchmark by combining multi-step task planning with a full-stack execution environment spanning research, coding, browsing, and content creation. The platform runs a React frontend on port 1420 backed by FastAPI on port 8000, with PostgreSQL for persistence, Redis for task queuing, and MinIO for S3-compatible file storage, all deployable via Docker Compose. Users switch between Anthropic Claude, OpenAI GPT, and Google Gemini mid-conversation using bring-your-own-key authentication. Task domains include deep research with source triangulation, website and mobile app generation from prompts, storybook creation with illustrations, video and image generation via Google Veo and Imagen, presentation building with live collaborative editing, and document manipulation covering PDF extraction, Excel formulas, Word editing, and PowerPoint creation. Built-in connectors integrate Gmail, Slack, GitHub, Notion, Google Calendar, Discord, Dropbox, and Canva for workflow automation. A sandboxed code interpreter runs Python while browser automation with vision capabilities handles web interactions. Custom skills let teams package and reuse workflows. Context management handles up to 120,000 tokens with intelligent window sizing. 3,400+ GitHub stars. Apache-2.0 licensed.

Every AI agent session starts from zero, and Busabase fixes that: it is an open-source workspace where agents and people share records, docs, skills, and apps, and every agent write arrives as a reviewable change. Bases hold typed records with relations, views, and forms, while Docs, Files, Whiteboards, and Workflows live in the same tree, so a project's data and context stay together. Skills are SKILL.md playbooks that any connected agent can look up before it acts. Each write becomes a Change Request carrying a message, a field-level diff, an author, and history; your permissions decide whether it merges at once or waits in the Inbox for approval, and any change can be reversed. Ask an agent to turn a Base into a dashboard, CRM, or content desk and it runs as an AirApp on live workspace data. Claude Code, Codex, Cursor, Gemini CLI, n8n, or your own process can connect through MCP, OpenAPI, the CLI, TypeScript and Python SDKs, or an in-app chat session. Templates install a complete setup, with sample data and an agent manual, in one command. Start it with one command and no accounts, because the open-source edition is a single-user workspace with no sign-in screen. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

GoRaven transforms AI chat from a question-answer window into a full engineering workstation where agents read files, write code, run shell commands, query databases via MCP tools, and deliver structured results — orchestrating across OpenAI, Claude, DeepSeek, Gemini, Qwen, GLM, and Ollama with task-based routing that allocates the right model for each job based on cost and capability. Built on a Go backend using the Freedom framework with Iris HTTP and a React/TypeScript frontend powered by Vite and Tailwind CSS, each user operates in an isolated workspace with team-shared project areas and centrally managed model quotas. The skill marketplace packages prompts, scripts, and workflows as reusable installable units with automatic dependency resolution and centralized versioning. MCP toolchain integration connects agents to internal APIs, databases, private services, and CLI tools so they query data, invoke services, and trigger actions directly. RAG-powered knowledge bases ingest policies, documentation, and business data for real-time retrieval during planning, coding, and Q&A with source attribution. Long-running task support decomposes complex work through a main agent coordinating sub-agents that execute in parallel across sessions. Plugin hooks inject custom logic at conversation start and end, tool calls, and SSE event streams without forking core code. The operations dashboard tracks usage metrics, model consumption, and team activity. Supports SQLite, MySQL, or PostgreSQL with Redis or local memory caching. Deploy with a single Docker command. 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.