@jack: mesh-llm allows you to distribute/share compute privately or publicly
Summary
mesh-llm is a tool that enables private or public distribution and sharing of compute resources, and is included in the Buzz platform.
View Cached Full Text
Cached at: 07/22/26, 10:27 AM
mesh-llm allows you to distribute/share compute privately or publicly
Derek Ross (@derekmross): wow… Buzz also includes mesh-llm. huge potential there.
Similar Articles
Mesh LLM: distributed AI computing on iroh
Mesh LLM is a distributed AI computing platform that pools idle GPUs across multiple machines to run large language models, exposing a single OpenAI-compatible API. It leverages iroh's peer-to-peer networking to enable private, decentralized inference without a central server.
@TheTechDiggest: [OpenSource - Distributed AI & Mesh LLM Inference] Buying an expensive enterprise GPU isn't the only way to run massive…
A tweet thread introduces mesh-llm, an open-source tool that pools local network devices into a unified, OpenAI-compatible API for running large LLMs without expensive enterprise GPUs.
@jack: it's one click in buzz to make a local model available to agents AND share your compute with other people. just one. an…
Buzz introduces a one-click feature to share local models and compute with agents, who automatically select the best shared model available.
MeshFlow: run governed multi-agent workflows on any local model — Ollama, LiteLLM, Bedrock — with cost caps and audit trails [Open Source]
MeshFlow is an open-source framework for running governed multi-agent workflows on any local or self-hosted model, with cost caps, audit trails, and sandbox mode.
Lobstah Net, a grid plugin for p2p inference
Lobstah Net is a new ClawHub plugin that enables peer-to-peer federated inference by routing LLM calls to a network of idle Mac minis running local models like Qwen via Ollama. It provides an OpenAI-compatible interface for OpenClaw agents and uses Nostr for secure receipt gossiping.