llm

Demystify RAG by building it from scratch. Local LLMs, no black boxes - real understanding of embeddings, vector search, retrieval, and context-augmented generation.

WikiChat is an improved RAG. It stops the hallucination of large language models by retrieving data from a corpus.

Cross-platform desktop application for content-aware file organization and renaming. Supports local and remote LLMs, preview-based workflows, and fully user-controlled changes.

Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback

Lightweight coding agent written in Rust, optimized for memory footprint and performance

Awesome-Jailbreak-on-LLMs is a collection of state-of-the-art, novel, exciting jailbreak methods on LLMs. It contains papers, codes, datasets, evaluations, and analyses.

The official GitHub page for the survey paper "A Survey on Evaluation of Large Language Models".

`llm-chain` is a powerful rust crate for building chains in large language models allowing you to summarise text and complete complex tasks

Fast Multimodal LLM on Mobile Devices

WebGLM: An Efficient Web-enhanced Question Answering System (KDD 2023)

ExtractThinker is a Document Intelligence library for LLMs, offering ORM-style interaction for flexible and powerful document workflows.

Chat language model that can use tools and interpret the results

Route, manage, and analyze your LLM requests across multiple providers with a unified API interface.

Chat with your data - AI data analysis and visualization on CSV, Postgres, MySQL, Snowflake, SQLite...

Amica is an open source interface for interactive communication with 3D characters with voice synthesis and speech recognition.

Korea Investment & Securities Open API Github

INT4/INT5/INT8 and FP16 inference on CPU for RWKV language model

Open-source desktop AI agent for tools, files, knowledge, workflows, and real deliverables.

A curated list of awesome LLM agents frameworks.

A powerful tool for automated LLM fuzzing. It is designed to help developers and security researchers identify and mitigate potential jailbreaks in their LLM APIs.

ktx is an executable context layer for data and analytics agents 🐙 Allow Claude Code, Codex, or other AI agents to query analytical databases accurately and with full context of your company

Claude reads its own source code — 17-chapter architectural deep-dive into Claude Code v2.1.88. EN/ZH bilingual.

[EMNLP 2025 Oral] MemoryOS is designed to provide a memory operating system for personalized AI agents.

Tiny Model, Big Logic: Diversity-Driven Optimization Elicits Large-Model Reasoning Ability in VibeThinker-1.5B

🤖 MLE-Agent: Your intelligent companion for seamless AI engineering and research. 🔍 Integrate with arxiv and paper with code to provide better code/research plans 🧰 OpenAI, Anthropic, Gemini, Ollama, etc supported. :fireworks: Code RAG

Lemon AI is the first Full-stack Open-source Self-Evolving General AI Agent, offering a fully local alternative to Agentic platforms like Manus & Genspark AI.🔔 Official updates X(twitter) @LemonAI_cc

Open Source Implementation of Karpathy's LLM Wiki. Upload documents, connect your Claude account via MCP, and have it write your wiki !

High-performance OpenAI and Anthropic compatible LLM inference server for Apple Silicon. Native MLX, continuous batching, multimodal models, MCP tool calling, and Claude Code support.

🦭 会记忆、能持续推进目标、会动态编排多 Agent 的跨端桌面 AI 助手，也可服务化常驻 NAS / 云端 | A cross-device desktop AI agent with memory, autonomous goals, dynamic workflows, and headless deployment

AgentEvolver: Towards Efficient Self-Evolving Agent System