Luftpause MCP server

luftpause

The runtime layer under your agent harness. Every tool call is an await; the engine forgets the run, luftpause keeps it.

Tool calls split an agent into turns. To an inference engine each turn is a new request from nobody: when the tool returns, the continuation queues behind every batch request that arrived while it waited, and its KV cache may be gone. luftpause sits between the harness and the engines and keeps the run:

work; batch turns leave room for the interactive runs that will come back.

• Continuations go first. A run paused on a tool call resumes ahead of batch

tool, its turns go only to the replica that holds its KV cache; new turns are admitted by the engine's own queue.

• A run stays where its prefix is. While a run is generating or paused on a

loop), or connect over MCP and get spawn / await sub-agents that survive a restart.

• One caller cannot starve another. Held turns drain fairly across callers.
• Any harness, two doors. Point base_url at it (OpenAI-compatible, your own

Measured on one 8 GB laptop GPU, engines saturated (48 batch runs flooding, 4 interactive runs beside them):

Try it

docker compose up -d                # fake engines, no GPU needed
claude mcp add --transport http --scope local luftpause http://localhost:7000/mcp

docker compose up -d pulls the published images; add --build to build them from source instead (first build takes a few minutes). It pulls latest; pin a release with LUFTPAUSE_VERSION=v0.1.4 docker compose up -d. The runtime is also listed in the official MCP Registry as io.github.vmedvedovskiy/luftpause.

Claude Code now has spawn, await, run, status, cancel, approve, tools and decide. The fake engines answer with filler, and the sub-agents' only tools are fake-mcp's lookup and deep_search, which wait a random second or so and return filler too — enough to see the fan-out. For real answers from an Ollama already on your machine, with Wikipedia as the sub-agents' tool instead of the fake ones:

docker compose -f compose.yaml -f compose.ollama.yaml up -d scheduler dataplane runtime

Wikipedia's API rate-limits anonymous callers, so a tool call can take tens of seconds while wikipedia-mcp retries. Llama 3.2 1B sometimes passes a tool's schema instead of its arguments; the runtime rejects the call and the sub-agent may answer without it, so ask again or pull a larger model.

Ollama needs the model pulled (ollama pull llama3.2:1b, or set OLLAMAMODEL) and must listen beyond loopback (OLLAMAHOST=0.0.0.0) unless Docker Desktop already reaches it (it does on Windows and macOS with the default loopback binding). Ollama serves one request at a time unless OLLAMANUMPARALLEL is raised, so sub-agents queue behind each other there; luftpause sees no queue metric from it and does not cap it. SGLang on your GPU (compose.testbed.yaml) or any OpenAI-compatible endpoint (compose.runpod.yaml shows a hosted vLLM pod) work the same way.

How it differs

Shortened. The full README is on GitHub.