Havuz

Teknik kitapları ve diğer dokümanları, agent’ların ihtiyaç anında kullanabileceği bölümlere ayrılmış Agent Skills formatına dönüştüren Python aracıdır.

Neden yükseliyor · Agent Skills ve context engineering’e yönelik ilginin arttığı bir dönemde, farklı kaynakları birden çok agent host’unda kullanılabilecek skill’lere dönüştürme vaadi dikkat çekiyor. 150 günde 32.594 yıldız ve son 28 günde 23 commit ile 12 farklı yazar kayda değer ilgi ve güncel aktivite gösteriyor; bunlar kaliteyi tek başına kanıtlamaz.

SenseNova-Skills, uyumlu agent runtime’larında ofis ve üretkenlik iş akışlarını yürüten modüler beceriler sunar.

Neden yükseliyor · 166 günde 5711 yıldıza ulaşması ve son 28 günde 13 commit ile 8 farklı yazarın katkı vermesi görünürlük ve yakın dönem aktivitesine işaret ediyor; ancak yıldızlar gerçek kullanımın veya benimsemenin kanıtı değil.

Open-source toolkit for reliable RAG pipelines: convert PDFs to Markdown, clean documents, inspect chunks, compare chunking strategies, and

Local official-document review, formatting repair, and compliant export desktop assistant.

Python CLI to replace visible PDF text with font-aware fallback and cleaner word spacing.

Rust-native MCP server for Office document processing (Excel, Word, PowerPoint). Sub-millisecond, local-first, open source.

Local-first AI knowledge app and Agent Skill with evidence-backed Wiki, an interactive knowledge universe, Viki Q&A, and shareable knowledge

本地运行的 DOCX/TXT 长文档改写与审阅工具，支持段内分块、多轮流式处理、Diff 审阅与 DOCX 原位回填。

ffprobe for documents — probe PDF, Microsoft Office, and Apple iWork files without opening them. Rust CLI + browser WASM SDK returning struc

校园知识服务 Agent 智能体平台：基于 FastAPI、Qwen3 与 RAG，贯通公开资料解析、时间范围检索、证据溯源及人工审核。

Lightweight Doc-to-agent-ready knowledge pipeline. Three-stage Bronze→Silver→Gold architecture extracts structured elements, page content, a

Local-first, governed documentation for humans and AI agents—mirror Office, PDF, and GitHub sources into linked Markdown knowledge workspace

Lemmary turns scans, PDFs, and office files into an organized library you can search, review, and research in plain language.

面向招投标场景的本地化 RAG 标书解析、资质匹配与红线提醒助手

Self-hosted, traceable document-to-knowledge workspace with deterministic workflows, optional AI, search, RAG, and an editable knowledge gra

Schema-first structured extraction from LLMs — validated JSON from one call or a 150-page document.

Turn documents into structured JSON with local-first document AI. Run 100% locally by default, with API, CLI, and Web UI.

Agent skills for LandingAI's Agentic Document Extraction (ADE) — production-ready document AI for agentic coding assistants

Local-first CLI + MCP server: Any file → AI-ready Markdown + JSON

CPU-friendly sidecar that OCRs paperless-ngx documents with PaddleOCR PP-OCRv6 and writes text back via the API.

Wenshu（文枢）— 面向人文社科研究的 AI 知识处理工作流：本地知识库 / RAG / 中文引文 / 理论谱系。AI knowledge workflow for humanities & social sciences: local knowledge base, RAG

Document intelligence that ingests any file and returns clean, spreadsheet-grade structured data plus narrative insight — no black boxes, no

Fully local document intelligence for DeepSeek Harness. Parse PDF, Office files, images, and scanned documents with offline OCR. | DeepSeek