Search
@vitest/istanbul-lib-coverage
Vitest Team
Data library for istanbul coverage objects
@resili/llm
Nitin Kaushal
Provider-neutral LLM resilience, usage accounting, cost control, and observability for Resili.
@resili/llm-openai
Nitin Kaushal
OpenAI provider adapter for the Resili LLM resilience foundation.
@unieai/uad-llm
unieaidev
Provider-neutral LLM service interface for the DeepSeek Harness
@boyeep/nextjs-python-rag-kit
Boyeep
Next.js and Python RAG starter with ingestion, retrieval, citations, and chat.
@ai-matrx/agents
GitHub Actions
Portable AI Matrx agent stream protocol, event projection, and safe result-presentation primitives.
n8n-nodes-secure-webhook
mustafa01010101
n8n custom node: Secure Webhook — redacts Authorization, Cookie and other sensitive headers from execution output
@tjpa/n8n-nodes-keycloak-guard
plenonn
Community node for n8n that protects webhooks with Keycloak: injects Authorization Code + PKCE login into HTML pages and validates the returning token.
...morevercel-blob-storage
Surya Sekhar Datta
A demo hello-world package
promptveil
Total Tensor Labs
Privacy and safety middleware for LLM applications
@socialrobot-io/n8n-nodes-socialrobot
GitHub Actions
n8n community node for SocialRobot.io: schedule and publish posts across Instagram, X, LinkedIn, TikTok, Facebook, Pinterest, Bluesky, Mastodon, and Threads
...moren8n-nodes-rooyai-image
rooyai.com
Rooyai Image / Vision Model node for n8n - Multimodal AI image analysis, OCR, visual reasoning, and question answering
llm-d-planner
Confidently navigate LLM deployments from concept to production
llm-pricing
GitHub Actions
Time-aware LLM token pricing: resolve a model name to a rate card and turn token counts into USD.
kaggle-vllm
kaggle-vllm contributors
A lightweight Kaggle compatibility SDK around upstream vLLM for Tesla T4 GPUs.
llmns
4thel00z
Parse, normalize, and compare llm:// references (llmns, a name system for language models)
@empirio-ai/n8n-nodes-empirio-ai
GitHub Actions
n8n community nodes for empirio.ai: build, publish and analyse surveys, and trigger workflows on every new survey response.
...morerag-core-engine
MD NASIR WAHID
Framework-agnostic RAG engine: crawl, chunk, embed, store, retrieve, answer — plus general-purpose LLM tasks (summarize, extract) over the same documents.
...morellmwiki-suite
LLM-compiled personal wiki toolkit: BM25 + wikilink-graph recall, lint, and chat channels over plain Markdown notes.
@synergyconsulting/n8n-nodes-servicely
konstantin.s
n8n community node for the Servicely ITSM/ESM JSON REST API (v1)