Havuz

Wordcell keeps decisions, plans, and sources as Markdown beside your code, so coding agents can find them from the file they are about to ch

The TUI-styled documentation template for your Obsidian vault. Built on Fumadocs + Next.js. Styled like a terminal. Read by AI agents.

The local-first AI knowledge workspace — an infinite canvas for research, learning, and creation (Tauri 2 + Vue 3)

Local-first personal knowledge base CLI — hybrid FTS + pgvector search, a GraphRAG entity graph, and LLM enrichment over your notes, transcr

MCP server for Agent Wikis — maintained, agent-readable knowledge bases. Read-only, no API key.

Save UI inspiration from any app; a vision model curates it into a private wiki and turns your taste into a DESIGN.md your coding agent buil

Stop reading AI replies. Your LLM places typed widgets (charts, kanbans, code, live timers) on an infinite canvas. Any model incl. local Oll

Zero-LLM incremental index + lazy semantic layer for knowledge vaults (markdown, HTML, PDF, images). One file, no dependencies, sub-second u

Open-source, self-hosted work database for people and AI agents, and an alternative to Airtable, Fibery, Notion databases and ClickUp. Conne

针对 [`deepseek-harness`](https://github.com/deepseek-ai/deepseek-harness) 仓库的交互式学习地图：架构分层、依赖脉络、核心流程、模块深读（含**关键源码片段**）、**双源文档库**（官方文档中文优先 + Cl

Knowledge engineering for AI agents: distill corpora too big for any context window into small, verified, git-native knowledge bundles

把微信公众号文章批量抓取并导入 IMA 知识库的自动化技能 (WeChat official-account article crawler → IMA knowledge base, MIT)

Claude Code Skills, Agents & Plugins — UitKit

Turn long AI conversations into reusable domain knowledge across sessions

Independent evidence-gated second brain for understanding and porting DeepSeek Harness architecture.

Keep your decisions, projects, and context when you switch between Claude Code, Cursor, opencode, and the rest — one plain-markdown bundle i

Ground truth for FiveM / GTA V development: a knowledge tree, offline data layers built from your own game, a searchable snippet database an

Give your coding agent a delivery process you can trust. Spec → Plan → Build → Acceptance → Ship.

A Claude skill that turns a folder into a collaboration knowledge base for you, your AI, and your humans

Knowledge engine for AI agents: your documents become a git-versioned markdown knowledge graph the agent navigates over MCP. Curated summari

Local-first, open-source knowledge base for people and AI agents, with Markdown files as durable truth.

A self-contained guide for an AI agent to bootstrap a personal Open Knowledge Format (OKF) knowledge repo: domains, AGENTS.md, generated ind

7 AKU-architected skills for OpenCode + Obsidian MCP: obsidian-mcp, inbox-triage, connection-review, weekly-synthesis, context-maintenance,

Open-source AI chatbot trained on your data, deployable on Cloudflare Workers for free.

Obsidian Turbocharged — governed, agent-ready Obsidian MCP server. Multi-vault native, pluggable embeddings, OAuth-ready HTTP. TypeScript +

Zeeq is an agent knowledge layer that surfaces telemetry that let's teams build better software with AI

Low-power, offline retrieval (RAG) for disaster and infrastructure-failure guidance.

开源、本地优先、支持自定义知识库与可选 AI 的私人公考学习工作台

Turn your Bilibili favorites and cloud documents into a chat-ready personal knowledge base. Agentic RAG with ASR transcription, Milvus vec

面向 B站视频学习的本地优先助手：边看边问、随手记笔记，用视频 Wiki 沉淀与复用知识；保留观看账单与兴趣再平衡。

Inkstone, Cloudflare Workers üzerinde çalışan, Markdown tabanlı not alma, arama, eşitleme ve yedekleme özellikleri sunan self-hosted bir uygulamadır.

Neden yükseliyor · 59 günde 1.020 yıldıza ulaşması, self-hosted Markdown notebook ve Cloudflare üzerinde çalıştırılabilen uygulamalara yönelik ilgiyi yansıtıyor olabilir. README, çevrimdışı çalışma, arama, yedekleme ve MCP gibi çok sayıda özelliği tek üründe topluyor; ancak yıldız ve özellik listesi tek başına benimsenme ya da kalite kanıtı değil. Son 28 günde 22 commit var, fakat bunlar yalnızca 2 farklı yazardan gelmiş; katkı tabanı dar görünüyor.

⚡ DocsAgent — give your AI agents instant, private access to your personal knowledge base (Zotero, Obsidian, Apple Notes supported now, loca

OKF-powered knowledge context for Claude Code — injects your project's knowledge base at every session

SparkWork is a local-first desktop Agent workbench for professional development and complex work. Orchestrate workflows, collaborate across

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

Self-hosted AI-платформа с расширенными возможностями: RAG, агенты, веб-поиск, исследования, коннекторы, любые LLM и гибкие настройки

Open-source, web-based knowledge base — Obsidian-style linked markdown notes, backlinks and a GPU-rendered knowledge graph. FastAPI + Next.j

Open-source, Local-first AI (SI) Second Brain.

A minimal, extensible, agent-native knowledge repository that keeps shared context current and inspectable

Re-debugging Solved Failures? No Way. 500+ Evidence-graded fix lessons, One MCP Call-->https://misakanet.org

Forward videos from IM to transcript, Markdown, and your knowledge base — with raw and skill-updated outputs.

OpenTag, Slack üzerinden gelen yazılım işlerini kullanıcının kendi makinesindeki ACP coding agent'lara yönlendirip sonuçları aynı konuşma başlığında raporlar.

Neden yükseliyor · 95 günlük yaşına karşılık 1.379 yıldız ve son 28 günde 133 commit dikkat çekiyor; Slack içinden yerel coding agent çalıştırma fikri güncel bir ihtiyaca hitap ediyor. Ancak commit'lerin tek yazardan gelmesi, ilginin bağımsız katkı ve sürdürülebilirlik kanıtıyla henüz desteklenmediğini gösteriyor.

Cambium, LLM agent’larıyla sürdürülen bilgi depolarındaki işleri kurallar, durum kayıtları ve doğrulanabilir kanıtlarla yöneten bir governance standardı ve Python araç setidir.

Neden yükseliyor · 55 günde 457 yıldız ve son 28 günde 81 commit ilgi ve yoğun geliştirme sinyali veriyor; ancak farklı yazar sayısının 1 olması katkı tabanının dar olduğunu gösteriyor. Yıldızların ne zaman kazanıldığı verilmediği için yükselişin hızını veya nedenini doğrulayamıyorum; LLM agent’ları, auditability ve MCP kesişiminin ilgi çekmesi olası bir açıklama.

Mint 是本地优先的 AI 知识工作台：将文档、网页与对话沉淀为可持续积累的 LLM Wiki，借助 Agent 与记忆 理解和复用个人知识。采用 SDD 规格驱动开发，以自动化验收闭环交付。

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。