Magec
One self-hosted admin console runs a team of AI agents you can reach by voice, chat, webhook, or schedule. Each agent gets its own model backend, system prompt, memory, tools, and voice, with OpenAI, Anthropic, Gemini, Ollama, or any OpenAI-compatible API behind it. A visual flow editor chains agents with routers, joins, loops, parallel fan-out, templates, and small code blocks, so a question can be sorted and answered by the right specialist. Every run is recorded as a step-by-step timeline you can open and read, and conversations are browsable per client. Connect tools through the Model Context Protocol, keep long-term memory in PostgreSQL, and store API keys as secrets that models only ever see as placeholders. Voice runs on the server with wake word detection and speech models, and clients cover a voice web app, Telegram, Discord, Slack, webhooks, and cron jobs. One password-protected console manages every agent, flow, and client. 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.
Retinue
Retinue shows who is doing what across a fleet of AI agents, on a shared board where every task is a card with exactly one holder, a written acceptance check, and a receipt chain that cannot be rewritten. Operators publish cards, agents claim them through MCP or a token-scoped HTTP API, report progress, and hand off, and an agent that is not the holder gets a refusal when it tries to write. The Home dashboard counts what is waiting, running, and blocked, charts task flow and dispatch, and shows quota gauges for Claude, Codex, Cursor, Grok, and Kimi subscriptions. A collaboration workspace draws delegation graphs, device and model timelines, module contributions, and message conversations for any selected task. Operations pages report token usage by worker, and a data health page flags stale reports and duplicate identities. Read-only importers pull session data from Claude Code and Codex, and optional Lark, Feishu, and Telegram bridges turn chat messages into intents. The interface switches between English and Simplified Chinese. 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.
LangGraph GUI
Building LangGraph agents in code means imagining the graph; LangGraph GUI turns that graph into something you draw, wire, and run from the browser instead. You place a start node, add step nodes, and drag edges between ports to define the flow, with cycles created by simply connecting nodes back toward each other. Condition nodes split execution into green true paths and red false paths, info nodes append context to stage output, and subgraph nodes run a whole named graph inside another one. Tool steps call real Python functions that you define in tool nodes with the familiar decorator style, so file saving, lookups, and custom logic sit inside the visual flow. Graphs save to JSON on your computer, load back for editing, and upload to the server as workflow files ready to execute. You configure which LLM to use and its API key in the panel, run against local models through Ollama or hosted APIs, then download every file the run produced in the workspace. Files upload to the server workspace as working environment, and a cache clean clears it between runs. Example graphs for role-playing loops, lottery branch switches, and tool-using flows show patterns you can copy and refine with your own prompts. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.
PharosRAG
Your team's documents sit in folders nobody can search, and the answer to a simple question hides on page 40 of a PDF someone saved last year. Pharos ingests PDFs, scans, Word documents, presentations, and spreadsheets into a local knowledge base, then answers questions against that library with citations traced back to the exact page. Hybrid retrieval finds the passages that matter, and every answer carries its evidence so readers can verify the claim in the source. Access control decides visibility per person: an API key resolves to an identity with a tenant and group memberships, retrieval filters hard to only the documents that identity may see, and a document with no permissions attached stays invisible to everyone. Two doors lead into the same library. The HTTP API runs a closed question-answering pipeline that retrieves, grounds, and answers in one call, and coding agents connect through MCP to decide for themselves when to retrieve, how to rewrite a query, and when a question needs multiple hops. A resident daemon keeps the search index and models warm, so every session shares one backend instead of reloading heavy resources. The deployment scales from one machine to replicated application tiers behind a load balancer. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.