Havuz

PixelRAG, web sayfaları ve belgeleri screenshot tile’larına dönüştürüp görsel içerik üzerinden arayan bir RAG sistemi sunuyor.

Neden yükseliyor · 121 günde 10.101 yıldıza ulaşması ve 8,28 milyon Wikipedia sayfasını içeren canlı indeks/API sunması dikkat çekiyor. README, Berkeley SkyLab, BAIR ve Berkeley NLP bağlantılı araştırma çalışmasını resmi kod tabanı olarak tanımlıyor. Son 28 günde 5 commit ve 4 farklı yazar görünmesi katkı çeşitliliğine işaret etse de aktiviteyi çok yüksek göstermiyor.

Win顺：免费开源的 Windows 快速搜索启动器。双击 Ctrl，拼音秒搜文件、全文搜索 Word/Excel/PDF、剪贴板历史（代替 Win+V）、对话框搜索、任务栏搜索、插件、AI 助手 MCP。Free Windows search launcher: pinyin

wigolo, AI agent’lara yerel çalışan bir MCP ve REST arayüzü üzerinden web search, fetch, crawl ve research araçları sunuyor.

Neden yükseliyor · AI agent’lar için web erişimi güncel ve yaygın bir ihtiyaç; API key ve sorgu ücreti olmadan yerel kullanım vaadi bu ilgiyle örtüşüyor. 168 günde 5.410 yıldız dikkat çekici, ancak nedeni yalnızca verilen verilerden belirlenemiyor; son 28 günde 8 commit ve 1 farklı yazar sürdürülebilirlik hakkında sınırlı kanıt sunuyor.

search every screenshot you've ever taken by the text inside it. native linux, offline, PaddleOCR + sqlite + gpui

Local-first, no-API-key MCP server for web search, fetch, and document reading. Multi-engine (DuckDuckGo, Mojeek, Startpage), smart Playwrig

Fast, stateless CLI for web search and scrape. Built for AI agents.

Index, search, and reason about your entire digital life.

terminal CLI for Kagi that gives you command-line access to search, lenses, assistant, summarization, feeds, and paid API commands.

PDF gibi uzun dokümanlarda sorunun yanıtını içeren sayfayı, PageIndex’in belge ağacı ve Jev’in seçim mekanizmasını kullanarak bulur.

Neden yükseliyor · Repo yalnızca 3 günlük ve 83 yıldız almış; bu erken görünürlük ilgiye işaret ediyor, ancak neden yükseldiğini doğrulayacak bağımsız kanıt yok. Son 28 gündeki 21 commit ve 2 farklı yazar aktivite gösterse de kısa geçmiş, kalıcı benimseme hakkında sonuç çıkarmaya yetmiyor.

A unified agent memory workspace for human and agent | 一个统一的agent记忆工作空间

A prior-art search for your code ideas — has this dev tool already been shipped?

Spotlight-style local search for everything you saved and forgot: GitHub stars, local files, images, and bookmarks. Privacy-first, no full-d

Hybrid search for Obsidian vaults via plugin, CLI, and MCP server

DSH 插件：基于知乎开放平台官方 API 创建的站内搜索、全网索引搜索与直答三个工具。搜索不幻觉，引用有出处。（原生嵌入“设置-插件-插件配置”）

On-policy distillation for agents without the environment: replay teacher prefixes instead of live rollouts.

Local, full Windows search replacement, clipboard manager, and launcher: files, apps, settings and semantic media search with Google's Embed

Generic markdown vault MCP with hybrid search

A local-first, long-term memory for anything you'd otherwise forget.

All Jina AI APIs as Unix CLI commands. Search, read, embed, rerank - with pipes.

Unified search MCP, proxy console, and skill for Tavily, Firecrawl, and Social / X.

🔍 The hardest search benchmark in the wild — vague, multi-turn, proactive. 200 long-horizon tasks with persona-driven progressive disclosure

Perplexity AI search, reasoning, research, and compute - MCP server, dashboard, and multi-IDE auto-config for VS Code.

Effect building blocks for agentic ai

观澜 / Guanlan：AI Agent 的中文互联网研究、阅读与信源路由工具。

From Pipeline to Council — A lightweight agentic framework for search & recommendation. 五个 Agent 重构搜广推管线。

Web browsing superpowers for AI agents - one MCP server to scrape, crawl, extract, map, search, batch, research & monitor the web. Self-host

Search your Claude Code conversation history by content (not just titles), then resume any session. grep + fzf, no index.

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

Manage Claude Code Sessions with AI Sessioner 2026

Personal Intelligence Engine — aggregates communication streams into a searchable local index

Retrieval tools for coding agents, no model in the loop: SOTA-competitive files, search, read, code_pack and write_note over the folder your

The implementation for SIGIR 2026: Learning to Retrieve from Agent Trajectories.

Git-backed wiki engine with MCP server — build knowledge that compounds

Пробив Емайл, поиск информации по электронной почте и инструменты для Email-разведки.

Search over 45M Hacker News posts and comments, and see how any term trends over time, powered by Upstash Redis Search

Fast recursive command search CLI tool built for developers.

Free Kagi Search MCP server — access search and summarizer via session tokens, no API key needed. Works with Claude Desktop, Cursor, Windsur

NEEDLE. A live search and retrieval benchmark from Keenable.ai

Fast CJK-aware fuzzy finder with Japanese romaji and Chinese pinyin search.

A better search engine for your github starred collection.

Opencode-Raven keeps noisy tool work behind a focused Raven agent, so your main model gets compact answers instead of raw search results, do

No-login web access layer for AI agents — 7 zero-config platforms

Unified search, crawling, and archiving toolbox for AI agents and automation scripts.

An open-source browser extension—a gateway with two-sided reach into search, with locally managed credentials—for humans and local AI agents

Search knowledge by what documents mean and how they look — not one or the other.

Federated, local-first search for an AI — one query across transcripts, files, knowledge graph, vector store, and the web, fused by trust-we

Local-first AI bookmark manager with semantic search, cleanup review, Chrome sync-back, and MCP support.

Self-hosted full-text search for Azure Blob Storage. Search inside PDFs/DOCX across containers. One docker compose up, $0/month

Real-time search for real files. No index. No daemon. No stale results.

Web search tool for the pi coding agent — batch queries, ranked readable markdown results ready to fetch. Pairs with pi-smart-fetch.