Reusable AI skills and capabilities for agent workflows
yusangeng
Core runtime utilities and base types for agent debugging and development workflows.
hughchen
On-device LFM2 / LFM2.5 inference for React Native & Expo via Liquid AI's LEAP SDK. Streaming chat, thinking models, constrained JSON, function calling — powered by Nitro Modules.
...moreMario Zechner
Unified LLM API with automatic model discovery and provider configuration (Python port of @earendil-works/pi-ai)
0mar_k
OpenCode TUI sidebar plugin for ChatGPT Codex usage limits
Kenneth Stott <[email protected]>
A dairy-free RAG pipeline for delicious semantic similarity, clustering and NER.
btspoony
Automatic provider/model fallback chains for DeepSeek Harness agents when LLM requests keep failing (retry exhausted, auth, quota, rate limit)
...moreOpensolr <[email protected]>
LangChain integration for Opensolr — managed Apache Solr with server-side embeddings and hybrid (BM25 + kNN) search
snaketech
n8n node for Frappe CRM: leads, deals, contacts, organizations, notes and tasks
Amjad Ullah
Unified RAG Pipeline Builder for Node.js — eliminates boilerplate across chunking, embedding, retrieval, and vector storage.
...morehuiliyi37
Replay LLM plugin: short-circuits llm/stream with model chunks reconstructed from a recorded session JSONL (keyless snapshot tests)
...moreLetter2025
Model-based permission approval (approve-for-me) for DeepSeek Harness: an approval/request answerer backed by a separate reviewer model
...morehflin
Provider discovery, matching, health checks, and pre-output failover for DeepSeek Harness.
Opensolr <[email protected]>
LlamaIndex integration for Opensolr — managed Apache Solr vector store with server-side embeddings and hybrid BM25+kNN search
...moreeinskyle
DeepSeek vision bridge for the dsh web GUI: route image attachments to a vision model (pi-ai / llama.cpp Qwen3-VL) and continue the conversation with the text description on a text-only LLM (DeepSeek)
...moreruihuahe
OpenAI Codex OAuth provider and model adapter for dsh-oauth and DeepSeek Harness
snaketech
n8n node for Frappe Learning (LMS): courses, chapters, lessons, batches, enrollments, quizzes, assignments and certificates
...moresnaketech
n8n node for Frappe Lending: loan products, applications, loans, disbursements, repayments, securities and write-offs
OpenAI-compatible HTTP API for the Needle 2 tool-calling model
dgpisces
DeepSeek Harness LLM provider for Codex models using managed ChatGPT OAuth
PromptLatch contributors
Local OpenAI-compatible proxy and Python library for redacting secrets before prompts leave your machine.
Andrew VanDyke <[email protected]>
A friendly terminal browser for local Codex CLI and Claude Code sessions
snaketech
Generic n8n node for Frappe and ERPNext: create, read, update, delete, submit, cancel and rename any doctype, and call whitelisted methods
...morearichiardi
Pi extension that injects per-skill, per-model, and per-provider request parameters (temperature, top_p, thinking, etc.) into every provider payload.
...more