Choose skills by scenario, quality, and trust signals.

Convert documents into Markdown for agent-readable context

Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More

A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows

📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG

🐙 Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents.

Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation. Built for scalable agents, RAG, multimodal applications, semantic search, and conversational systems.

OpenViking is an open-source context database designed specifically for AI Agents(such as openclaw). OpenViking unifies the management of context (memory, resources, and skills) that Agents need through a file system paradigm, enabling hierarchical context delivery and self-evolving.

A Claude Code plugin that shows what's happening - context usage, active tools, running agents, and todo progress

Memory control plane for AI Agents in 6 lines of code

"DeepCode: Open Agentic Coding (Paper2Code & Text2Web & Text2Backend)"

Memory layer for AI Agents. Replace complex RAG pipelines with a serverless, single-file memory layer. Give your agents instant retrieval and long-term memory.

Turn any AI Agents into world-class data analysts through the open context layer that gives AI agents grounded, governed memory, context, SQL across 20+ data sources, that helps you build GenBI, agentic BI, text-to-sql, dashboards, and agentic analytics.

newspaper3k is a news, full-text, and article metadata extraction in Python 3. Advanced docs:

PM Skills Marketplace: 100+ agentic skills, commands, and plugins — from discovery to strategy, execution, launch, and growth.

Incremental engine for long horizon agents 🌟 Star if you like it!

Collection of AI-related utilities. Welcome to submit pull requests /收藏AI相关的实用工具，欢迎提交pull requests

Trail of Bits Claude Code skills for security research, vulnerability detection, and audit workflows

AI suite powered by state-of-the-art models and providing advanced AI/AGI functions. Includes AI personas, AGI functions, world-class Beam multi-model chats, text-to-image, voice, response streaming, code highlighting and execution, PDF import, presets for developers, much more. Deploy on-prem or in the cloud.

Open-source context retrieval layer for AI agents

🔥 基于大模型和 RAG 的智能问数系统，对话式数据分析神器。Text-to-SQL Generation via LLMs using RAG.

MineContext is your proactive context-aware AI partner（Context-Engineering+ChatGPT Pulse）

The AI-native database built for LLM applications, providing incredibly fast hybrid search of dense vector, sparse vector, tensor (multi-vector), and full-text.

The 100 line AI agent that solves GitHub issues or helps you in your command line. Radically simple, no huge configs, no giant monorepo—but scores >74% on SWE-bench verified!

A collection of agent skills for CAD, robotics and hardware design

Enhanced LanceDB memory plugin for OpenClaw — Hybrid Retrieval (Vector + BM25), Cross-Encoder Rerank, Multi-Scope Isolation, Management CLI

Memory library for building stateful agents

High-performance open-source in-memory graph database for GraphRAG, AI memory, agentic AI, and real-time graph analytics. Cypher-compatible, built in C++.

The missing DevTools for Claude Code — inspect session logs, tool calls, token usage, subagents, and context window in a visual UI. Free, open source.

CADAM is the open source text-to-CAD web application

总结Prompt&LLM论文，开源数据&模型，AIGC应用

Agent Skills as a Memory Layer

🔥 Comprehensive survey on Context Engineering: from prompt engineering to production-grade AI systems. hundreds of papers, frameworks, and implementation guides for LLMs and AI agents.

The Context Layer for unstructured data: typed, versioned datasets over S3, GCS, Azure

A curated list of skills, tools, tutorials, and capabilities for AI coding agents (Claude, Codex, Antigravity, Copilot, VS Code)

Agent Package Manager

Deep dive into Claude Code internals — architecture, agent loop, context engineering, and more. / 深入解析 Claude Code 源码：架构、Agent 循环、上下文工程、工具系统等

Read and extract text and other content from PDFs in C# (port of PDFBox)

Like htop, but for AI coding agents. Monitor Claude Code & Codex CLI sessions, tokens, context window, rate limits, and ports in real-time.

iText for Java represents the next level of SDKs for developers that want to take advantage of the benefits PDF can bring. Equipped with a better document engine, high and low-level programming capabilities and the ability to create, edit and enhance PDF documents, iText can be a boon to nearly every workflow.

Awesome resources for in-context learning and prompt engineering: Mastery of the LLMs such as ChatGPT, GPT-3, and FlanT5, with up-to-date and cutting-edge updates.

基于 Spring Boot 4.0 + Java 21 + Spring AI + PostgreSQL + pgvector + RustFS + Redis，实现简历智能分析、AI模拟面试、知识库RAG检索等核心功能。非常适合作为学习和简历项目，学习门槛低。

Document scanning app

📰 Must-read papers and blogs on LLM based Long Context Modeling 🔥

iText for .NET is the .NET version of the iText library, formerly known as iTextSharp, which it replaces. iText represents the next level of SDKs for developers that want to take advantage of the benefits PDF can bring. Equipped with a better document engine, high and low-level programming capabilities and the ability to create, edit and enha

The headless Chrome/Chromium driver on top of Puppeteer. Take screenshots, generate PDFs, extract text and HTML with a production-ready API.

Practical productivity tools for Claude Code, Codex-CLI, and similar CLI coding agents.

The SILE Typesetter — Simon’s Improved Layout Engine

MORT 번역기 프로젝트 - Real-time game translator with OCR

A lightweight 2D graphics library for modern GPUs, delivering high-performance text, image, and vector rendering across major platforms.

OpenOCR: An Open-Source Toolkit for General-OCR Research and Applications, integrates a unified training and evaluation benchmark, commercial-grade OCR and Document Parsing systems, and faithful reproductions of the core implementations from a wide range of academic papers.

Fess is very powerful and easily deployable Enterprise Search Server.

OCR engine for all the languages

What are the principles we can use to build LLM-powered software that is actually good enough to put in the hands of production customers?

converts binary PDF to JSON and text, for server-side PDF processing and command-line use. Zero dependency.

A CLI text-to-speech tool using the Kokoro model, supporting multiple languages, voices (with blending), and various input formats including EPUB books and PDF documents.

Specify a github or local repo, github pull request, arXiv or Sci-Hub paper, Youtube transcript or documentation URL on the web and scrape into a text file and clipboard for easier LLM ingestion

YouTube Full Text Search - Search all of YouTube from the command line

Read Japanese manga inside browser with selectable text.

Python & Command-line tool to gather text and metadata on the Web: Crawling, scraping, extraction, output as CSV, JSON, HTML, MD, TXT, XML

AI video agents framework for next-gen video interactions and workflows.

Free Offline OCR 离线的中文文本检测+识别SDK

SnapX is a free, open-source, cross-platform tool that lets you capture or record any area of your screen and instantly share it with a single keypress. Upload images, videos, text, and more to multiple supported destinations—all with ease. ShareX fork

A minimalist SOTA LaTeX OCR model with only 20M parameters, running in browser. Full training pipeline available for self-reproduction. | 超轻量SOTA LaTeX公式识别模型，仅20M参数量，可在浏览器中运行。训练全流程代码开源，以便自学复现。

CnSTD: 基于 PyTorch/MXNet 的 中文/英文 场景文字检测（Scene Text Detection）、数学公式检测（Mathematical Formula Detection, MFD）、篇章分析（Layout Analysis）的Python3 包

Web interface for recognizing text, proofreading OCR, and creating fully-digitized documents.

Magic Context cache-aware infinite context, cross-session memory, and background history compression

Dedoc is a library (service) for automate documents parsing and bringing to a uniform format. It automatically extracts content, logical structure, tables, and meta information from textual electronic documents. (Parse document; Document content extraction; Logical structure extraction; PDF parser; Scanned document parser; DOCX parser; HTML parser

Multi-modal OCR pipeline optimized for ML training (text, figure, math, tables, diagrams)

PowerMem: Your AI-Powered Long-Term Memory — Accurate, Agile, Affordable. Also friendly support for the OpenClaw Memory Plugin.

The definitive resource for Agent Skills - modular capabilities revolutionizing AI agent architecture

Control Figma from the command line. Full read/write access for AI agents — create shapes, text, components, set styles, export images. 100+ commands.

A packaged and flexible version of the CRAFT text detector and Keras CRNN recognition model.

A Python library for solving reCAPTCHA v2 and v3 with Playwright

translate scientific papers in latex, especially arxiv papers

(eBook，PDFs Translation) A multilingual eBook processing tool supporting all eBook formats. Features online and offline translation while preserving original layouts. Compatible with both scanned and digital PDFs. Elegant user interface. The world's highest-performing open-source layout-preserving eBook translator.

Interact with your SQL database, Natural Language to SQL using LLMs

WebAI2API: 基于 Camoufox 的网页 AI 转 API 工具，支持 LMArena/Gemini等，多窗口并发与账号隔离。 | Web AI to OpenAI API via Camoufox. Supports LMArena/Gemini and more, multi-window concurrency & account isolation.

AIRecon is an autonomous cybersecurity agent that combines a self-hosted Large Language Model (Ollama) with a Kali Linux Docker sandbox and a Textual TUI. It is designed to automate security assessments, penetration testing, and bug bounty reconnaissance — without any API keys or cloud dependency.

Kolo is a text-based Python debugger for AI agents. Capture every executed function call, return value, local variable, HTTP request, and more in greppable trace files.

🧠 Context Engineering Research - Not just another agent collection, but using research and context engineering to function as a collective. Hub-and-spoke coordination through Claude Code.

Text-To-Speech, RAG, and LLMs. All local!

Open Source Virtual (Network) Printer for Windows that allows you to create PDFs, OCR text, and print images, with advanced features usually available only in enterprise solutions.

Converts PDF, DOC, DOCX, XML, HTML, RTF, etc to plain text

Python tool for grabbing text via screenshot

MixTeX multimodal LaTeX, ZhEn, and, Table OCR. It performs efficient CPU-based inference in a local offline on Windows.

Converts a pdf file into a text file while keeping the layout of the original pdf. Useful to extract the content from a table in a pdf file for instance. This is a subclass of PDFTextStripper class (from the Apache PDFBox library).

a "Proof of Concept or GTFO" mirror with an extensive index with also whole issues or individual articles as clean PDFs.