Connection check
verified live · 27h ago
hugging-bay
Verified open AI artifact search, trust evidence, downloads, and agent workflows from Hugging Bay.
Tools
15
GitHub stars
—
Installs / wk
39
Licence
—
Transport
streamable-http, stdio
Last checked
27h ago
Tools & capabilities
15 toolsRead from the running server on 27h ago.
bakeoff
task*examples*
Your rows -> hashed specialist -> one call. POST-equivalent of /api/v1/bakeoff: task (toxicity | sentiment | prompt_injection | tickets | rerank | embeddings | nli, synonyms like r… Your rows -> hashed specialist -> one call. POST-equivalent of /api/v1/bakeoff: task (toxicity | sentiment | prompt_injection | tickets | rerank | embeddings | nli, synonyms like rag/moderation/guard accepted) + examples (1-50 rows: {input,label} for classification; {query,documents[2..8],relevant} for rerank/embeddings). Runs ONLY the warm, schema-fit Bay Run candidates on your rows (never a chat/coder model), returns ranked accuracy/MRR, the winner's next_call (identical to the search row and find_runnable), weight hashes, why-not-the-others, and a share URL. Provisional; nothing is marked measured.
deployment_plan
artifact*
Get a ready-to-run deployment plan for a model's HOSTED, individually hash-checked files: canonical identity, per-file { path, sha256, sizeBytes, downloadUrl }, a `shasum -a 256 -c… Get a ready-to-run deployment plan for a model's HOSTED, individually hash-checked files: canonical identity, per-file { path, sha256, sizeBytes, downloadUrl }, a `shasum -a 256 -c` verify block, and per-runtime-family REAL runnable command recipes (pull/download -> verify -> run/serve) for ollama, llama.cpp, vLLM, transformers, and MLX, referencing the exact hosted files and their SHA-256 digests. Emitted only for genuinely hosted, hashed files; honest available:false with no commands when a model has no reviewed hosted files yet. Wraps GET /api/agents/deployment-plan?artifact=. Arg: artifact (id or resolvable reference).
find_runnable
ctxgputask*commercial
One call: task -> runnable model. Composes find_model (a bounded metadata pick for your task + rig) with deployment_plan for the top pick, INLINING the hash-verified pull/verify/ru… One call: task -> runnable model. Composes find_model (a bounded metadata pick for your task + rig) with deployment_plan for the top pick, INLINING the hash-verified pull/verify/run commands when that pick has genuinely hosted, individually hash-checked files (commandsAvailable). Honest when not: deploymentPlan is null with a pointer to inspect or request a mirror. Collapses discover -> plan into one hop and points at the machine run contract, not an HTML page. Args: task (required), commercial, gpu, ctx.
get_agent_discovery
Return the single-call agent discovery contract for answer engines, OpenClaw/Hermes-style agents, MCP clients, OpenAPI users, crawlers, citation targets, and bounded API entrypoint… Return the single-call agent discovery contract for answer engines, OpenClaw/Hermes-style agents, MCP clients, OpenAPI users, crawlers, citation targets, and bounded API entrypoints.
get_artifact
id*
Fetch one full artifact JSON document by id. Fetch one full artifact JSON document by id.
get_artifact_card
id*markdown
Fetch repo-grade artifact card JSON or Markdown. Fetch repo-grade artifact card JSON or Markdown.
get_citation_pack
qslugquery
Return a compact citation pack for answer engines: safe claims, avoid claims, citation order, proof URLs, and bounded extraction rows. Return a compact citation pack for answer engines: safe claims, avoid claims, citation order, proof URLs, and bounded extraction rows.
get_ranking
slug*
Fetch one ranking as JSON so agents do not scrape ranking HTML. Fetch one ranking as JSON so agents do not scrape ranking HTML.
get_source_coverage
idsource
Return one provider's coverage, policy, rollups, and top imported records. Return one provider's coverage, policy, rollups, and top imported records.
get_source_request_status
idcaseId*
Fetch sanitized public status for one source indexing request. Fetch sanitized public status for one source indexing request.
list_files
id*toollimitcursor
List one artifact's files with bounded pagination. List one artifact's files with bounded pagination.
list_topics
limitcursor
List generated catalog topics with optional bounded cursor pagination. List generated catalog topics with optional bounded cursor pagination.
recommend_specialist
task*limitcommercial
Recommend one of the four canonical Bay Run specialists for guard, sentiment, support tickets, or document reranking. Returns the exact Pin id, honest byte status, and no decoder-o… Recommend one of the four canonical Bay Run specialists for guard, sentiment, support tickets, or document reranking. Returns the exact Pin id, honest byte status, and no decoder-only VRAM estimate.
resolve_artifact
qurlreposource
Resolve an upstream repo URL, owner/name, or artifact id to a Hugging Bay artifact plus hosted/download/mirror actions. Resolve an upstream repo URL, owner/name, or artifact id to a Hugging Bay artifact plus hosted/download/mirror actions.
search_artifacts
qsorttasktypelimitcursor
+9