llm

LLM.swift is a simple and readable library that allows you to interact with large language models locally with ease for macOS, iOS, watchOS, tvOS, and visionOS.

An local, offline (after initial setup), portable OCR software that can process images and PDF files, using DeepSeek-OCR-2 AI (running directly on your machine).

LM Studio Python SDK

✨ AI Gist 是一款隐私优先的 AI 提示词管理工具，致力于让个人收藏的 AI 提示词能够发挥最大价值。支持变量替换、Jinja 模板、AI 生成与调优、历史版本记录、云端备份等核心功能。

Run LLMs inside a PDF file.

xpander.ai is the runtime and control plane to build, run, and ship reliable AI agents fast and anywhere

Neum AI is a best-in-class framework to manage the creation and synchronization of vector embeddings at large scale.

马良写作 AINoval — AI novel writer for Chinese webnovels（网文）| 多智能体AI小说创作平台：三级大纲、知识图谱一致性、30万字连载

A curated, non-BS library of the best resources for building and evaluating AI agents — papers, blogs, talks, tools, benchmarks. Maintained by BenchFlow.

Infrastructure for the next generation of voice agents, designed to provide universal memory. It is divided into a left brain and a right brain, storing information and emotions respectively, while a fully streaming architecture eliminates latency at the fundamental level.

Code and implementations for the paper "AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning" by Zhiheng Xi et al.

🤖 Automatically collected AI repos, tools, websites, papers & tutorials. 实用AI百宝箱 💎

An LLM-powered advanced RAG pipeline built from scratch

Go SDK for Google Generative AI

🔥机器学习/深度学习/Python/大模型/多模态/LLM/deeplearning/Python/Algorithm interview/NLP Tutorial

The simplest and lowest-cost AI integration solution. If you like this project, please give it a Star~ | 最简单、最低成本的AI接入方案。喜欢本项目的话点个 Star 吧~

大模型驱动的拼音输入法

RAG for Local LLM, chat with PDF/doc/txt files, ChatPDF. 纯原生实现RAG功能，基于本地LLM、embedding模型、reranker模型实现，支持GraphRAG，无须安装任何第三方agent库。

GLM-ASR-Nano: A robust, open-source speech recognition model with 1.5B parameters

Local-first privacy guard: anonymize your documents before sharing with LLMs.

Declarative language for composable Al workflows. Devtool for agents and mere humans.

AI Commits for IntelliJ based IDEs/Android Studio.

We introduced a new model designed for the Code generation task. Its test accuracy on the HumanEval base dataset surpasses that of GPT-4 Turbo (April 2024) and GPT-4o.

pi coding agent in a technicolor web trenchcoat

OpenSwarm — Autonomous AI dev team orchestrator powered by Claude Code CLI. Discord control, Linear integration, cognitive memory.

cuVS - a library for vector search and clustering on the GPU

Code and implementations for the ACL 2025 paper "AgentGym: Evolving Large Language Model-based Agents across Diverse Environments" by Zhiheng Xi et al.

🔥🔥 LLaVA++: Extending LLaVA with Phi-3 and LLaMA-3 (LLaVA LLaMA-3, LLaVA Phi-3)

Unified Reinforcement Learning Framework

The most atomic way to train and inference a GPT in pure, dependency-free C