Mesh-LLM

Mesh-LLM/mesh-llm

Agent Codex

Validates the next MeshLLM release against the last GitHub release on approved real hosts and produces a formal evidence-backed readiness report.

Mesh-LLM/mesh-llm

Skill Claude CodeCodex

Use this skill when running, debugging, interpreting, or documenting mesh-llm benchmark tune model-serving throughput trials, including choosing ctx/batch/ubatch/mmap/mlock/speculative-decoding sweeps, running benchmark tune on local or SSH hosts, collecting JSON evidence, and applying tolerance-aware recommendations.…

Mesh-LLM/mesh-llm

Skill Claude CodeCodex

Use this skill when adding, renaming, removing, validating, or exposing mesh-llm config settings, including built-in settings, plugin config schemas, owner-control apply behavior, CLI validation, and UI configuration surfaces.

Mesh-LLM/mesh-llm

Skill Claude CodeCodex

Use this skill when connecting agent tools or OpenAI clients to mesh-llm — launching or configuring Goose, Claude Code, OpenCode, Pi, curl, or any OpenAI-compatible client against a local or remote mesh, picking a model, or validating tool-call reliability.

Mesh-LLM/mesh-llm

Skill Claude CodeCodex

Use this skill when deploying, installing, launching, or serving mesh-llm on a remote Linux GPU node (rented GPUs like Vast.ai or RunPod, or a self-managed CUDA server), including installing the CUDA build, choosing a model, keeping it alive under a supervisor, and verifying it serves.

Mesh-LLM/mesh-llm

Skill Claude CodeCodex

Use this skill when deploying, installing, launching, or serving mesh-llm on a macOS machine (local or remote over SSH), including installing a release, shipping a dev build bundle, codesign/quarantine fixes, choosing a model, and verifying it serves.

Mesh-LLM/mesh-llm

Skill Claude CodeCodex

Use this skill when installing, deploying, launching, serving, or troubleshooting mesh-llm on a Windows machine — PowerShell install via install.ps1, flavor selection (CUDA/ROCm/Vulkan/CPU), source builds, the contrib helper scripts, and verifying it serves.

Mesh-LLM/mesh-llm

Skill Claude CodeCodex

Use when converting Hugging Face SafeTensors checkpoints into split BF16 GGUF model repos with skippy-quantize on Hugging Face Jobs or a local machine, then publishing the artifact to Hugging Face.

Mesh-LLM/mesh-llm

Skill Claude CodeCodex

Use when creating, monitoring, validating, or documenting low-memory Hugging Face Jobs or local runs that quantize split BF16/FP16 GGUF model repos into custom quant GGUF repos with skippy-quantize.

Mesh-LLM/mesh-llm

Skill Claude CodeCodex

Use when changing mesh-llm automation or CLI flows that discover Hugging Face GGUF models, plan CPU Hugging Face Jobs for layer-package splitting, estimate max cost, or publish skippy layer packages/catalog entries.

Mesh-LLM/mesh-llm

Skill Claude CodeCodex

Use when running quantization of a BF16/FP16 GGUF repo and Skippy layer-package creation as one local or Hugging Face Jobs workflow, publishing both artifacts to Hugging Face.

Mesh-LLM/mesh-llm

Skill Claude CodeCodex

Use this skill when certifying mesh-llm KV/cache stability under repeated OpenAI tool-call loops, same-prefix cache reuse, suffix-prefill limits, or native Skippy slot/decode/eviction failures.

Mesh-LLM/mesh-llm

Skill Claude CodeCodex

Use when changing mesh-llm's llama.cpp patch queue, upstream pin, prepare/build scripts, or carried RPC, MoE, and mesh-hook llama.cpp patches.

Mesh-LLM/mesh-llm

Skill Claude CodeCodex

Use this skill when changing mesh-llm's patched llama.cpp Skippy ABI, runtime hooks, model introspection, tensor filtering, activation-frame execution, GGUF writer surface, upstream pin, or patch queue.

Mesh-LLM/mesh-llm

Skill Claude CodeCodex

Use this skill as the mandatory starting point whenever inspecting, running, debugging, defining, editing, reviewing, or documenting MeshLLM CI/CD. It governs GitHub Actions workflows and local actions, triggers and routing, runners, caches, artifacts, permissions, releases, deployments, and CI infrastructure.

Mesh-LLM/mesh-llm

Skill Claude CodeCodex

Use this skill when creating, joining, publishing, or connecting mesh-llm nodes into a mesh — private meshes with invite tokens, the public mesh via --auto, named/published meshes, client-only nodes, NAT/firewall/bind issues, or verifying multi-node setups.

Mesh-LLM/mesh-llm

Skill Claude CodeCodex

Use this skill when working on benchmark telemetry ingest, metrics-server run lifecycle, OTLP collection, SQLite storage, benchmark report export, or separating telemetry/reporting ownership from staged runtime servers.

Mesh-LLM/mesh-llm

Skill Claude CodeCodex

Use this skill when maintaining the plugin web UI projection contract, docs, exemplar coverage, or recovery flow for mesh-llm plugin web UI work.

Mesh-LLM/mesh-llm

Skill Claude CodeCodex

Use this skill when validating a MeshLLM release candidate or current HEAD against the last GitHub release, assembling the canonical feature/fix/modification inventory, testing locally built release bundles on user-approved real hosts and private meshes, deciding release readiness, or producing a formal…

Mesh-LLM/mesh-llm

Skill Claude CodeCodex

Use this skill when starting, supervising, debugging, holding open, or stopping any remote process over SSH that needs an operator-like interactive environment, a TTY, login-shell startup files, long-running observation, logs, readiness checks, or later inspection.

Mesh-LLM/mesh-llm

Skill Claude CodeCodex

Use this skill when running benchmark orchestration, local single-stage or split benchmarks, benchmark report flow, or performance-oriented skippy runtime checks.

Mesh-LLM/mesh-llm

Skill Claude CodeCodex

Use this skill when benchmarking Skippy exact-prefix cache across model families, comparing Skippy against llama-server, producing README benchmark tables, updating crates/skippy-cache/README.md evidence, or diagnosing cache benchmark gaps by family or Hugging Face use case.

Mesh-LLM/mesh-llm

Skill Claude CodeCodex

Use this skill when validating skippy staged execution against full-model execution, adding model families, changing split boundaries, testing activation wire dtypes, or diagnosing mismatch behavior.

Mesh-LLM/mesh-llm

Skill Claude CodeCodex

Use this skill when certifying a GGUF model family for skippy stage-split serving, reviewing capability data, promoting family evidence into topology policy, or updating staged split certification docs.