Reusable AI skills and capabilities for agent workflows
himboslice
OpenCode plugin that uses your Claude Code credentials — no separate login needed.
leohenon
Anthropic OAuth plugin for OpenCode-compatible clients.
jungyoun
Tool registry and implementations for Robota SDK
okanenas
Opinionated, adaptive block-based status line for Claude Code with bin-packing layout, rate limit tracking, and campaign monitoring
...morekitsudo1412
CLI bootstrapper for Claude Teammate.
alexgxmemory
n8n node for xmemory read/write operations
GitHub Actions
n8n community node for making gRPC calls. Supports server reflection, multi-file proto with import resolution, TLS, mTLS, and automatic schema discovery.
...moreClient Python pour Cedric7-Thinking — 50 personnalités, Helper, CLI, fichiers .cdy, profils, conversations, batch, streaming.
...moresemcod
A complete toolkit for validating LLM-generated code
KGP Talkie Private Limited <[email protected]>
RAGWire — Production-grade RAG toolkit for document ingestion and retrieval with hybrid search support
kunyuan <[email protected]>
High-performance LLM client with batch processing, caching, and checkpoint recovery
fairyhunter13
The **[Anthropic provider](https://ai-sdk.dev/providers/ai-sdk-providers/anthropic)** for the [AI SDK](https://ai-sdk.dev/docs) contains language model support for the [Anthropic Messages API](https://docs.anthropic.com/claude/reference/messages_post).
...moreJason Mars <[email protected]>
byLLM Provides Easy to use APIs for different LLM Providers to be used with Jaseci's Jaclang Programming Language.
axxoul
Strapi plugin for managing and automating translation of content
LLMHosts Team
Your Personal AI Cloud -- intelligent proxy, router, and cache for LLMs
sbassompierre
Remote notification and response relay for Claude Code CLI sessions
GitHub Actions
Rune is a CLI framework built around the concept of file-based command routing.
lpil01
n8n node for Camoufox anti-detect browser automation via Playwright
renebello
n8n community node for AzuraCast Web API
javasop
Multi-provider LLM client with rate limiting, token tracking, structured outputs, and continuation handling
gijungkim
Expo module for on-device LLM inference via Apple Foundation Models (iOS) and Gemini Nano (Android)
vLLM-Omni Team
A framework for efficient model inference with omni-modality models
schipiga
LLM-as-a-Judge abstraction layer using ai-sdk and plugins
GitHub Actions
Distributed AI code review agent — poll, review, and submit PR reviews using your own AI tools