#llm

Accelerate local LLM inference and finetuning (LLaMA, Mistral, ChatGLM, Qwen, DeepSeek, Mixtral, Gemma, Phi, MiniCPM, Qwen-VL, MiniCPM-V, etc.) on Intel XPU (e.g., local PC with iGPU and NPU, discrete GPU such as Arc, Flex and Max); seamlessly integrate with llama.cpp, Ollama, HuggingFace, LangChain, LlamaIndex, vLLM, DeepSpeed, Axolotl, etc.

Jan is an open source alternative to ChatGPT that runs 100% offline on your computer.

LangServe 🦜️🏓

PrimeUIX is a shared package used by all Prime libraries, allowing PrimeTek teams to unify theming.

The Security Toolkit for LLM Interactions

Archived: use github.com/ronhuafeng/llm-go/llmcaller/codex; legacy v0.4.2 is immutable

Archived: use github.com/ronhuafeng/llm-go/llmkit; legacy v0.5.0 is immutable

superglue (YC W25) builds integrations and tools from natural language. Get production-grade tools for long tail and enterprise systems.

🤖 Chat with your SQL database 📊. Accurate Text-to-SQL Generation via LLMs using Agentic Retrieval 🔄.

Framework + detection service for the @plurnk/plurnk-mimetypes-* handler family

Vanexa Agent — your sovereign AI, controlled from your phone. Proprietary (BUSL-1.1); installs via npm. This repo is the public home + security-transparency record (no source).

Опис репозиторію не опубліковано.

Tools for the Griptape Framework.

Python framework for LLM middleware tools. Build once, run anywhere: LangChain, ChatGPT Plugins, Fixie.ai, etc.

Framework + contract for @plurnk/plurnk-providers-* sibling packages (LLM transports + tokenizer + cost accounting).

Model Context Protocol (MCP) server for VK (VKontakte) social network API