Search

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.

Unified LLM API with automatic model discovery and provider configuration (Python port of @earendil-works/pi-ai)

Azure OpenAI image generation provider for AI Media SDK

Devtool library for Wrangler — development tooling and utilities.

Chat UI components for @agentskillmania — message list, input, execution blocks.

OpenCode TUI sidebar plugin for ChatGPT Codex usage limits

Django storage backends and auto-configuration for Railway bucket storage.

A dairy-free RAG pipeline for delicious semantic similarity, clustering and NER.

Hot-pluggable Dragon Heir skin for the dsh web GUI: <edit me — one line pitch>

HexaLLM — AI coding assistant for the terminal

Test and monitor AI agents before they break in production.

Automatic provider/model fallback chains for DeepSeek Harness agents when LLM requests keep failing (retry exhausted, auth, quota, rate limit)

CLI RAG tool for local codebases

Production-ready, lightweight Hybrid RAG (Vector + Full-Text Search + Facets) engine for Supabase.

LangChain integration for Opensolr — managed Apache Solr with server-side embeddings and hybrid (BM25 + kNN) search

n8n node for Frappe CRM: leads, deals, contacts, organizations, notes and tasks

LlamaIndex 기반 RAG All-In-One 라이브러리

Unified RAG Pipeline Builder for Node.js — eliminates boilerplate across chunking, embedding, retrieval, and vector storage.

Behavioral verification coverage for React and Material UI component tests.

Replay LLM plugin: short-circuits llm/stream with model chunks reconstructed from a recorded session JSONL (keyless snapshot tests)