🏆 #3,611 overall#825 of 1,494 in Search & Retrieval

vakovalskii /searcharvester

Self-hosted search + markdown harvester for AI agents. SearXNG (100+ engines) + FastAPI + trafilatura. Tavily-compatible /search plus /extract with size presets and pagination. One-command Docker Compose.

$ git clone https://github.com/vakovalskii/searcharvester.git
GitHub social preview for vakovalskii/searcharvester
Stars
283
283
This week
—
Forks
44
44
Language
Python
License
AGPL-3.0
Created
Sep 11, 2025
1.2 years old
Last push
Sep 30, 2026

Categories

GitHub topics

More in Search & Retrieval

Search & Retrieval

VectifyAI/PageIndex🔥 active

▲ +294 ★ this week

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

PythonMITupdated Nov 13, 2026
GitHub ↗★ 40.4K⑂ 3.5K
Search & Retrieval

Sallyn0225/eidolon-sc🔥 active

和《偶像大师 闪耀色彩》偶像实时语音/文字对话的 AI 分身:日语原声 + 中文字幕、回忆原作剧情、跨角色共享记忆;支持 Google/GitHub 登录与自带密钥,Docker Compose 一键部署(参考 LAPLACE Eidolon)

🎙️ Speech Recognition
PythonAGPL-3.0updated Nov 13, 2026
GitHub ↗★ 426⑂ 90
Search & Retrieval

didilili/deepsearch-agents🔥 active

🔎 深度研搜对话式多智能体 AI Agents,最适合系统学习 DeepAgents 的实战项目|AI Deep Research Agent 实战 · LangGraph + RAGFlow + Tavily + FastAPI + WebSocket 从0到工程化落地。前后端完整代码全栈可跑,Docker 环境一键部署,配套 ai-agents-from-zero 免费教程与章节代码分支。适合系统学习大模型应用、多智能体 Agent 和企业级 AI 工程落地

Pythonno licenseupdated Nov 6, 2026
GitHub ↗★ 321⑂ 84
Search & Retrieval

vstorm-co/agenticos🔥 active

Open-source, self-hosted AI agent platform for your company's AI teammates. Build, run and govern agents on your own servers and models: shared chat, RAG, skills, a real browser, 4,700+ MCP servers, budgets, approvals and an audit trail. An alternative to ChatGPT Enterprise and Grok Bot. Apache-2.0, built on Pydantic AI.

PythonApache-2.0updated Nov 13, 2026
GitHub ↗★ 265⑂ 52
Search & Retrieval

DasDigitaleMomentum/searxNcrawl🔥 active

Open-source MCP server that gives AI agents web search (SearXNG) and clean Markdown crawling of pages, whole sites and logged-in areas. Self-hosted, no API key. Firecrawl-compatible API planned.

PythonMITupdated Nov 11, 2026
GitHub ↗★ 190⑂ 25
Search & Retrieval

apowerb/apowerb🔥 active

The open-source agentic framework to build, orchestrate, and operate production AI agents.

PythonApache-2.0updated Nov 13, 2026
GitHub ↗★ 150⑂ 27

Data from GitHub · snapshot Nov 13, 2026