llm

Run MoE models bigger than your RAM. Frontier-size MoE on a 12 GB phone, CPU only, lossless, on stock llama.cpp

Universal MCP-Server for your Databases optimized for LLMs and AI-Agents.

Automatic memory consolidation for OpenClaw agents — like sleep for your AI. Powered by MyClaw.ai

Streamline your workflow with Lynkr, a CLI tool that acts as an HTTP proxy for efficient code interactions using Claude Code CLI.

Dataset and benchmark for RAG on company internal documents.

The complete guide to Claude Code: CLAUDE.md, hooks, skills, MCP servers, and commands

🔍 Google SEO's full docs as an AI prompt machine — drop it into your AI assistant to map every public route, audit each page against Google's rules, and fix the gaps step by step.

The User Pays AI SDK

Persistent project knowledge graph for coding agents. MCP server with semantic search, in-process embeddings, and web explorer.

A recipe for online RLHF and online iterative DPO.

One-stop handbook for building, deploying, and understanding LLM agents with 60+ skeletons, tutorials, ecosystem guides, and evaluation tools.

MiniMax M2.1, a SOTA model for real-world dev & agents.

Data driven agentic landscapes and insights. Produced by Ant Open Source and inclusionAI.

AWS Generative AI CDK Constructs are sample implementations of AWS CDK for common generative AI patterns.

Turn your workday into structured workflows agents can execute. 100% local, served over MCP.

Summarize and query from a lot of heterogeneous documents. Any LLM provider, any filetype, advanced RAG, advanced summaries, scriptable, etc

免费大模型API合集 / Free LLM api Collection

An AI Powered README and Interactive Wiki Generator for Any Projects. AI驱动的README及交互式Wiki生成工具，面向中文的开源DeepWiki。

Build a chatbot or Q&A bot of your website's content

🏗️ Fine-tune, build, and deploy open-source LLMs easily!

Menu Bar App on MacOS and Windows that cuts Claude Code and Codex token costs by ~50%

💪🏻 Blazing-Fast and Extremely-Lightweight Internet Reader driven by AI! Your AI-Powered think tank assistant.(Built with Rust, Tauri & Svelte)

Spec-driven development with smart compaction. Claude Code plugin combining Ralph Wiggum loop with structured specification workflow.

Awesome list of AI-Driven Development.

A curated collection of papers and resources on On-Policy Distillation for Large Language Models.

🚀 Universal SDK for building next-gen MCP servers

Official Implementation of ICLR 2024 paper: "Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning"

[ICML 2024] LESS: Selecting Influential Data for Targeted Instruction Tuning

Multi-LLM peer review for code decisions. Bring your own CLI; Chorus convenes 2-4 other LLMs to review the work before you ship.

Deep Research Agent CognitiveKernel-Pro from Tencent AI Lab. Paper: https://arxiv.org/pdf/2508.00414