skippy-serving
Skill3.8k starsChanged 20 days agoApache-2.0View on GitHub
Use this skill when running, configuring, debugging, or embedding skippy-serving, binary stage transport, OpenAI frontend integration, activation wire dtype settings, stage configs, lifecycle status, or nonblocking telemetry.
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 10
Use this skill for skippy serving, embedded runtime lifecycle, and binary stage-to-stage transport.
- Distinctive: line 31
Run cargo commands serially:
- Very specific: line 48
Do not reintroduce standalone kv-server or ngram-pool dependencies into mesh.
≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
skippy-serving
Use this skill for skippy serving, embedded runtime lifecycle, and binary stage-to-stage transport.
Current Repo Shape
The mesh integration embeds skippy-serving through Rust APIs instead of
launching it as mesh's public OpenAI surface. Public OpenAI compatibility
belongs in skippy-inference-api; skippy-serving should remain the backend stage
runtime.
Important crates:
skippy/crates/skippy-serving
skippy/crates/skippy-protocol
skippy/crates/skippy-runtime
mesh/crates/mesh-llm/src/inference/skippyValidation
Run cargo commands serially:
cargo check -p mesh-llm
cargo test -p skippy-serving --lib
cargo test -p skippy-protocol --lib
cargo test -p mesh-llm-host-runtime --lib inference::skippyFor lifecycle/status changes, also run:
cargo test -p mesh-llm-host-runtime --libRules
Do not reintroduce standalone kv-server or ngram-pool dependencies into
mesh. Keep structured outputs, tools, logprobs, and /v1/responses
compatibility in skippy-inference-api.
Stage status exposed by mesh should be backend-neutral at the API boundary. Backend-specific details can remain in internal skippy structs.
Trending
Quiet since April.about the whole repository
Who's talking about michaelneale/mesh-llm
- A Hacker News story“Pool spare GPU capacity to run LLMs at larger scale”Hacker News · Mar 24, 2026 · 11 points
- @rusttrending.bsky.social“michaelneale / mesh-llm: reference impl with llama.cpp compiled to distributed inference across machines, …”Bluesky · Apr 11, 2026 · 2 likes
- @yug1224.com“複数のLLMを連携させてタスクをこなすための分散型エージェントフレームワークらしい 複雑なワークフローを構築する際に役立ちそうかな yug1224 starred michaelneale/mesh-llm…”Bluesky · Apr 8, 2026 · 1 likes
- Mesh-LLM/mesh-llm“Add mesh-llm MoE planning, analysis, and ranking contribution commands”GitHub · Apr 11, 2026
- Mesh-LLM/mesh-llm“Simplify model for node states”GitHub · Apr 10, 2026
The biggest 5 of 18 mentions linking to the repository that our crawl found. Each line is their own headline.
See all 18
Talked about on GitHub, Bluesky and Hacker News (18 times).
On GitHub · 15
- Apr 11, 2026Add mesh-llm MoE planning, analysis, and ranking contribution commands — Mesh-LLM/mesh-llm0 reactions · 1 comment
- Apr 10, 2026Simplify model for node states — Mesh-LLM/mesh-llm0 reactions · 2 comments
- Apr 10, 2026revise mesh publication rules — Mesh-LLM/mesh-llm0 reactions · 1 comment
- Apr 5, 2026Roll out config as local node config first, then reconcile mesh-wide desired state — Mesh-LLM/mesh-llm0 reactions · 2 comments
- Apr 3, 2026CommitLLM sumi capture: working on Apple Silicon Q8_0 — michaelneale/llama.cpp0 reactions
10 more on GitHub
- Apr 2, 2026Add hardware runtime status enrichment without changing model metadata sources — Mesh-LLM/mesh-llm0 reactions
- Apr 2, 2026Design owner identity propagation and direct verification — Mesh-LLM/mesh-llm0 reactions · 4 comments
- Apr 2, 2026Design owner keystore and Rust signed+encrypted message primitives — Mesh-LLM/mesh-llm0 reactions
- Apr 2, 2026Track splitting PR #130 into smaller rollout PRs — Mesh-LLM/mesh-llm0 reactions · 2 comments
- Apr 2, 2026research: mesh-llm integration — p2p inference mesh + model sharding under obol-stack economic layer — ObolNetwork/obol-stack0 reactions
- Apr 2, 2026[WIP] Make PR 103 mergable on top of PR 127 — Mesh-LLM/mesh-llm0 reactions
- Apr 2, 2026refactor: decompose mesh.rs and app/mod.rs into focused submodules — Mesh-LLM/mesh-llm0 reactions · 1 comment
- Mar 28, 2026Autoupdater — Mesh-LLM/mesh-llm0 reactions
- Mar 27, 2026Add a staged auto-updater for release bundles — Mesh-LLM/mesh-llm0 reactions
- Mar 27, 2026Add generic bulk transfer support to mesh plugins — Mesh-LLM/mesh-llm0 reactions
On Bluesky · 2
- Apr 11, 2026michaelneale / mesh-llm: reference impl with llama.cpp compiled to distributed inference across machines, with real end to end demo ★720… — @rusttrending.bsky.social2 likes and reposts
- Apr 8, 2026複数のLLMを連携させてタスクをこなすための分散型エージェントフレームワークらしい 複雑なワークフローを構築する際に役立ちそうかな yug1224 starred michaelneale/mesh-llm… — @yug1224.com1 likes and repost
On Hacker News · 1
- Mar 24, 2026Pool spare GPU capacity to run LLMs at larger scale11 points · 3 comments
Other versions1 project uses a version of this.
Word for word · 1
- Mesh-LLM/mesh-llm★ 3.5k100% same
Edited · 0
None found.
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository32 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .github/AGENTS.mdAGENTS.md
- mesh/AGENTS.mdAGENTS.md
- skippy/AGENTS.mdAGENTS.md
- benchmark-tuneSkill
- config-settings-managementSkill
- connect-agentsSkill
- deploy-linux-gpuSkill
- deploy-macosSkill
- deploy-windowsSkill
- hf-bf16-gguf-conversion-jobsSkill
- hf-gguf-quant-jobsSkill
- hf-layer-package-jobsSkill
- hf-quant-and-layer-package-jobsSkill
- kv-tool-loop-stabilitySkill
- llama-patch-changesSkill
- llama-stage-patch-changesSkill
- manage-ciSkill
- mesh-joinSkill
- metrics-serverSkill
- plugin-web-ui-extensionSkill
- release-notesSkill
- release-validationSkill
- remote-observable-processSkill
- skippy-cache-family-benchSkill
- skippy-correctnessSkill
- skippy-family-certificationSkill
- skippy-metricsSkill
- skippy-model-packageSkill
- skippy-promptSkill
- skippy-spec-benchSkill
- telemetry-privacy-reviewSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.