Support teams, IT departments, and researchers can put their own documents behind chatbots and AI agents built with MaxKB, an open-source platform that grounds answers in private knowledge. A support lead starts by uploading Markdown, DOCX, PDF, TXT, HTML, XLSX, XLS, or CSV files, or by syncing a web site, and MaxKB splits, vectorizes, and indexes the content on its own. An IT department can place the finished agent in any third-party site or internal tool with no coding, as a full-screen page, a mobile view, or a floating chat window. Researchers get replies that show, and let them download, the knowledge sources behind each answer. Simple agents pick tools, skills, and MCP connections from the question itself, while advanced agents are drawn as workflows with branching, multi-path recall, loops, and variables. Custom scripts, which AI can help write, plus schedules and event triggers extend what an agent can do. The model manager registers local models such as DeepSeek, Llama, and Qwen beside providers such as OpenAI, Claude, and Gemini, across language, embedding, reranking, vision, speech, and image generation. Conversation logs feed analysis for operations. Dozens of ready-made agent templates, knowledge base templates, tools, and skills in the template center and tool store shorten the first build. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. GPL-3.0 licensed.

Recognized by the CNCF Landscape in the AI Agent – Workflow Orchestration category alongside Dify and Temporal, Astron Agent is iFLYTEK's fully open-source platform for building, deploying, and managing enterprise multi-agent systems — backed by 8,900+ GitHub stars and the production infrastructure behind one of China's largest AI companies. Unlike pip-install frameworks such as LangGraph, CrewAI, or AutoGen, Astron Agent ships as a complete microservices platform spanning 10+ services across Java, Python, Go, and TypeScript: a ReactFlow-based visual workflow builder for low-code agent orchestration, native integration with the Model Context Protocol (MCP) for tool calling, a built-in model management layer supporting iFLYTEK Spark, OpenAI, Anthropic, and on-premises MaaS deployments, and a multi-tenant Go authentication service powered by Casdoor. The standout differentiator is native RPA integration via the companion astron-rpa project (7,200+ stars), providing 300+ pre-built automation capabilities spanning browser, Office document, and enterprise system interaction — enabling agents to execute physical UI actions rather than only API calls. Infrastructure includes PostgreSQL for multi-tenant data isolation, MySQL for application metadata, Kafka for event streaming, Redis for caching, and MinIO for object storage, all orchestrated through Docker Compose with explicit health checks and dependency chains or production Kubernetes Helm charts. 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.

Every prompt your application sends is a small buying decision, and OrcaRouter Lite makes it a smart one instead of a habit. Point your app at one OpenAI-compatible endpoint on your server, and each request is shopped across the providers whose keys you hold: OpenAI, Anthropic, Google, xAI, DeepSeek, and dozens more. Send model set to auto and the router picks the cheapest model that can actually do the job, checking whether the request needs tools, vision, or JSON mode before it commits your money. Prefer a different tradeoff and you can switch the whole gateway between balanced, cheapest, fastest, and quality strategies, with quality picks driven by real benchmark scores rather than vibes. Clients that speak Anthropic's or Gemini's native protocols connect directly too, so Claude Code, the OpenAI SDK, and google-genai all land on the same routing pipeline. Streaming responses flow through untouched, and every answer reports which model really served it. The built-in dashboard shows recent requests, spend, latency percentiles, unreachable providers, and a savings tile that tells you what your traffic would have cost if you had blindly used a flagship model for everything. Your provider keys stay encrypted on your own box, your analytics never leave it, and if every local provider has a bad day, the hosted OrcaRouter can step in as a failover safety net. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Inference Gateway puts a single OpenAI-compatible API endpoint in front of OpenAI, Anthropic, Groq, Cohere, Ollama, DeepSeek, Google, Mistral, MiniMax, Moonshot, Nvidia, and llama.cpp, so your application code never changes when you switch models or providers. The Go binary starts on port 8080 and normalizes authentication, streaming protocols, and response formats across all backends transparently. Native Model Context Protocol support auto-discovers tools from connected MCP servers and injects them into LLM requests without client-side management, enabling server-side tool execution across any provider that supports function calling. Agent-to-Agent protocol integration allows distributed agent communication through a declarative Agent Definition Language that generates production-ready Go or Rust servers from a single YAML manifest. The dedicated Kubernetes Operator manages Gateway, Agent, MCP, and Orchestrator custom resources with automatic HPA scaling, OIDC authentication, and service discovery that rebuilds MCP configurations when the discovered server set changes. Prometheus metrics and OpenTelemetry tracing provide full request-level observability across the entire inference pipeline. Middleware controls enable per-request provider selection, model routing, and fallback strategies. Official SDKs in Go, Python, TypeScript, and Rust provide typed client interfaces with streaming support. Docker Compose deployment requires only environment variables for API keys. A CNCF Sandbox applicant. 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.

Routerly is the one front door for every AI model your apps use: point your OpenAI or Anthropic client at it, and it chooses the right model for each request, enforces your budget, and keeps the receipts. Nothing in your code changes except the base URL, and from that moment streaming chat completions and messages flow to OpenAI, Anthropic, Gemini, Mistral, Cohere, xAI or your own Ollama models behind a single token. Nine routing policies score every candidate in parallel: cheapest, fastest, healthiest, most capable, biggest context, least rate-limited, fairest, most budget left, and one that asks a small model to judge which model fits the task. When the winner errors or times out, the next candidate takes over automatically, and the recorded routing trace shows exactly why each model won or lost. Guardrails can block or log content that breaks your rules, and phone numbers, card numbers, SSNs, IBANs and emails can be scrubbed out before anything reaches a provider. Every call is logged with tokens, USD cost and latency, and hard limits per model, project and token reject overspending requests before a provider can charge for them. Projects keep separate tokens, model lists and budgets for each team or tool, role-based permissions decide who may change what, and alerts land in Slack, email, webhooks or PagerDuty when budgets or providers misbehave. 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.

With over 164,000 GitHub stars and one of the fastest-growing open-source projects in the AI tooling ecosystem, Firecrawl is the web context API that turns any website into clean markdown, structured JSON, or screenshots optimized for large language models. The Scrape endpoint converts a single URL into LLM-ready output with approximately 67% fewer tokens than raw HTML, handling JavaScript rendering, rotating proxies, anti-bot bypasses, and dynamic content extraction with zero configuration. The Crawl endpoint recursively scrapes entire websites from a single request with configurable depth, URL filters, and concurrent page limits. The Map endpoint discovers all URLs on a domain instantly for sitemap generation. The Search endpoint performs web searches and returns full page content from results. The Interact endpoint scrapes a page then continues working with it — clicking buttons, filling forms, and extracting dynamic content using AI prompts or code. The Agent endpoint provides autonomous web data gathering where users describe what they need in plain English. SDKs are available for Python, Node.js, Go, Rust, Ruby, PHP, Java, C#/.NET, and Elixir, with an MCP server for connecting to any AI agent or MCP client. Self-hosting deploys via Docker Compose and requires Redis and a Playwright-based browser service for JavaScript rendering. 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.

Plain chunk retrieval hands an LLM disconnected excerpts; LightRAG builds a knowledge graph from your documents so answers can join facts spread across many files. Ask about one named person, product, or clause and local mode pulls its details. Ask for themes across the whole library and global mode follows the links between entities. Hybrid blends the two, naive falls back to plain chunk search, and mix combines all three. Mix is the default. Upload text, Markdown, PDF, Word, PowerPoint, and Excel files; MinerU, Docling, or the native parser can extract images, tables, and formulas. The admin console manages documents, explores the graph visually, and debugs queries, while a query-only workspace page gives everyday colleagues a clean chat screen that works on phones. A REST API covers indexing and queries, and an Ollama-compatible endpoint lets chat front ends such as Open WebUI use the knowledge base as a model. New files merge into the existing graph without a full reindex, and deleting a document rebuilds only the entities and relationships it touched from cached results. Separate model roles let an inexpensive model extract entities while a stronger one writes answers. An API key or accounts protect the server, and named workspaces keep several knowledge bases apart. Pair it with local Ollama models and no document text leaves the server. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Five teammates sharing three AI subscriptions usually means a password in a group chat; SubLane replaces that with a gateway you host, where accounts are pooled and every person gets a managed key. Connect Codex, Claude, Antigravity, and Grok Build subscriptions once, by browser OAuth or credential import, and the gateway snapshots each account's quota windows and allowances so routing knows who still has room. Add API channels for OpenAI-compatible services alongside the subscriptions, then group everything into resource pools with model allowlists, conversation affinity, concurrency controls, and cooldown recovery for accounts that hit a limit. Each member receives a personal key scoped to one group, with its own expiry, rate and concurrency limits, and an allowance measured in tokens, internal dollars, or estimated quota share; keys can be paused or revoked without touching anyone else. Whatever the client speaks, the gateway answers: OpenAI Responses and Chat Completions, Claude Messages, and Gemini formats flow over HTTP, SSE, or WebSocket, independent of which subscription actually serves the request. Administrators watch per-member and per-model usage charts, activity heatmaps, and request diagnostics, bind a fixed outbound proxy to any account, and apply workspace content rules before dispatch. It all runs as one Go process with SQLite and an embedded dashboard, backed up and restored from the interface. 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.

ENZO is a self-hosted AI workspace where you bring your own provider API keys and chat with more than 300 models from nine providers in one streaming interface with normal, thinking, research, and coding modes. You describe an agent in plain English and a two-pass builder drafts its full operating manual, picks the tools the task needs, and keeps improving from your activity through a per-agent neural layer you can inspect. Seventy-four bundled skills give agents ready-made domain playbooks, and a skill editor lets you write your own. Agents can read Gmail, check Calendar, search the web, and run a deep-research loop that writes its own queries under hard budgets so it cannot burn your key. Coding mode writes a multi-file project, boots it, and previews it live while telling you when something is broken. A unified model marketplace compares providers with live health checks, download counts, and benchmarks, and a built-in music player streams songs with a five-band equalizer. Your keys stay sealed in a passphrase-encrypted browser vault and travel only to the provider you picked, so there is no ENZO account, usage meter, or subscription taking a cut. 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.

Self-hosting a language model is only half the job; people still need somewhere pleasant to talk to it, and Chat UI is that window, the same interface that powers HuggingChat. Point it at any OpenAI-compatible endpoint, your own Ollama or llama.cpp server, the Hugging Face router, or a hosted gateway like OpenRouter, and the models it serves appear in the picker automatically, with no per-model configuration. Conversations are saved to your database and stay browsable in the sidebar, so a thread from last week can be reopened, continued, and compared against a fresh answer from another model. Multimodal models accept image uploads right in the composer, and models that support it can call MCP tools mid-conversation to fetch data or run actions. For a shared team deployment, OpenID Connect sign-in keeps individual histories and settings separate, and per-user defaults travel with each account. Everything a consumer chatbot would keep on someone else's servers, prompts, uploaded files, and usage history, stays in the MongoDB you control on the same machine. 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.

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.

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.

Perplexity's answer-engine experience, self-hostable and open-source: Morphic searches the web and writes cited answers. Instead of returning a list of links, it searches the web, reads the sources, and generates a complete answer with inline numbered citations. The generative UI streams rich components, source cards with thumbnails, image grids, syntax-highlighted code, and LaTeX math, rather than plain markdown. Quick mode answers fast; Adaptive mode runs deeper multi-step research. Search backends are pluggable: the Docker Compose bundle ships with a private SearXNG instance so no search API key is required, and Tavily, Brave, and Exa are supported alternatives. LLM providers include OpenAI, Anthropic, Google, Ollama, and any OpenAI-compatible endpoint, with per-mode model mapping - fast, cheap models for quick searches, stronger models for adaptive research, tuning the cost-quality trade-off per query type. An inspector panel exposes tool execution during multi-step research, and AI-suggested follow-up questions keep an investigation moving. Chat history persists in PostgreSQL, results are shareable by URL, file uploads feed context into queries, and optional Supabase authentication adds multi-user or guest access. Because the default search path is your private SearXNG instance, research topics never hit a commercial search API - and with local Ollama models the marginal cost of a query approaches zero. Built with Next.js, TypeScript, and the Vercel AI SDK under Apache 2.0.

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.

Character-based chat and storywriting with large language models: TavernAI is the open-source frontend that leaves model choice to you. It generates no text itself; it connects to the backend of your choice - OpenAI (including GPT-4), Anthropic Claude, KoboldAI and KoboldCpp, Oobabooga's Text Generation Web UI, NovelAI, Ollama, and the crowdsourced Horde - so cost, model quality, and content policy are decided by your backend, not the interface. Characters are defined by portable card files in PNG or JSON format with personality, scenario, and example dialogue, and tens of thousands of community-made cards from sites like Chub.ai import directly. Conversations support group chats with multiple characters, a story mode for long-form writing, message swiping to branch between alternative responses, and full editing of any message. World Info injects lore into context when keywords trigger, keeping long roleplays consistent. Themes, custom backgrounds, and configurable generation settings round out the interface. It runs on Node.js, and the SillyTavern project began as a fork of it.

Live web search plus an LLM of your choice: Farfalle is an open-source, self-hosted answer engine in the Perplexity mold. Queries route through one of several search providers - self-hosted SearXNG for a fully independent stack, or Tavily, Serper, and Bing APIs - and the model composes a cited answer from the retrieved results. Model flexibility is the core design: run llama3, mistral, gemma, or phi3 locally through Ollama for zero per-query cost and full privacy, use cloud models like GPT-4o or Groq-hosted Llama 3 for speed, or route to any provider via LiteLLM. An Expert Search mode uses an agent that plans a multi-step search strategy and executes it for harder questions, and chat history keeps prior research sessions available. The stack is a Next.js and shadcn/ui frontend over a FastAPI backend with Redis rate limiting, shipped as a pre-built Docker image. A browser search-engine entry pointing at your instance makes it the default search from the address bar. Paired with SearXNG and Ollama, the whole pipeline runs with no external API at all.

WeKnora turns scattered corporate documents into a searchable, reasoning-capable knowledge asset that your team can query in plain language and receive cited, sourced answers. Upload PDFs, Word files, web pages, Feishu wikis, Notion databases, Yuque docs, GitLab repositories, or RSS feeds into structured knowledge bases, and three distinct modes make the content actionable: RAG Quick Q&A retrieves relevant chunks and generates answers with source citations; the ReAct Agent autonomously orchestrates multi-step reasoning across knowledge retrieval, MCP tool calls, web search, and sandboxed code execution to produce comprehensive research reports; and Wiki Mode deploys LLM agents to distill raw documents into an interlinked markdown knowledge base with an interactive knowledge graph, revision history, and one-click rollback. Connect 20+ LLM providers including OpenAI, DeepSeek, Qwen, Claude, and local Ollama models without vendor lock-in, and choose from seven vector database backends (Qdrant, Milvus, Weaviate, and more) for embedding storage. Enterprise features include four-tier RBAC with per-resource ownership and per-workspace audit logs, AES-256-GCM credential encryption, scoped API keys, Langfuse observability tracing for every agent loop and tool call, and a runtime task-queue dashboard for worker-pool governance. Cross-session long-term memory preserves conversational context across interactions. The Agent Skills catalog lets teams install and share sandboxed scripts executed in Docker or E2B containers. A Chrome Extension captures web content directly into knowledge bases. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Edict is a multi-agent orchestrator that runs every AI request through a court-style chain: a crown prince agent triages it, a planning department drafts the work, a review department can veto the plan, and specialist ministries execute what survives. Casual chat gets a direct reply, while real commands become kanban tickets whose titles are scrubbed of file paths and metadata. A vetoed plan returns for rework; an approved one is dispatched in parallel to ministries for finance, documentation, engineering, compliance, infrastructure, and HR. Commands arrive through Feishu, Telegram, or Signal channels configured in OpenClaw. The dashboard shows cards by state with heartbeat badges and stop, cancel, and resume controls, plus a department monitor and a memorial archive that turns finished work into five-phase timelines you can copy as Markdown. Nine edict templates add parameter forms and cost estimates, an officials panel ranks agents by merit score while tracking token spend, and per-agent model switching restarts the gateway in about five seconds. Agent thinking, tool calls, and results stream live. A permission matrix limits who may message whom, illegal state jumps are rejected, and every transition lands in an audit log. Worked examples cover competitive analysis, code review, and weekly reports. Dashboard login protects the console, and a systemd unit keeps it running across reboots. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.