Models, agents, tools, and the mesh between your machines, running on devices you control. No cloud required, no per-token bill.
Up and running in under 5 minutes.
drop a screenshot at assets/hero.png(Overview page)
Files, shell, APIs, skills, subagents: an agent that carries long multi-step work end to end, with you approving what executes.
How agents work
drop a screenshot at assets/agents.png(agent chat with tool calls)
bash · npm testCatalog → quantization → pull → loaded on your GPU. Aliases let apps ask for qwen while the router picks the model.
drop a screenshot at assets/models.png(Models page)
qwen → Qwen3.6-35BAttach the inference servers you already run and register keyed cloud providers. Their models land in one list, behind one router, with real measured tok/s.
How providers work
drop a screenshot at assets/providers.png(Providers page)
qwen3.6:35b63.6 tok/s measuredOne Try button from any model to a raw conversation. Thinking streams in, tokens-per-second on every turn, nothing saved. Need the ceiling instead of a single turn? The built-in benchmark swarms the box to measure how many agents it can host.
About the Playground
drop a screenshot at assets/playground.png(Playground mid-answer)
A swarm of real agents with real sessions, driven against your instance until it bends. Density, completion rate and the breakpoint, measured by running it on your hardware, not read off a spec sheet.
About Benchmark
drop a screenshot at assets/bench.png(Benchmark mid-run)
mimOE nodes discover each other. The workstation's 35B model shows up on your laptop, usable by name.
How the mesh works
drop a screenshot at assets/mesh.png(Models → Nearby)
{node-id}/Qwen3.6-35BAgents don't wire their own MCP servers. Attach any MCP server once, scope it with client keys, and every tool call flows through one governed MCP gateway.
How the MCP gateway works
drop a screenshot at assets/gateway.png(MCP Gateway page)
Switch to another instance in one click. If its IP changes, Studio finds the node on the mesh and follows it.
How remote connections work
drop a screenshot at assets/remote.png(Manage Connections overlay)
Each call through the router becomes an OpenTelemetry trace, capturing model, routing, tokens, timing, and content on-device. Governance, the policy and audit layer, is being built on exactly these records.
How trace & governance work
drop a screenshot at assets/trace.png(Trace view)
Models, agents, tools, mesh, and the receipts to prove what happened.
One-click runtime install includes the engine, model store, router, and a tool gateway. Works offline.