From 5935164622146cb8e6b12879a025777de05c969d Mon Sep 17 00:00:00 2001 From: Tobias Perelstein <5562156+tobocop2@users.noreply.github.com> Date: Sun, 14 Jun 2026 15:18:05 -0400 Subject: [PATCH 1/5] Add lilbee to Search & Data Extraction --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index 242010380..94bca52e5 100644 --- a/README.md +++ b/README.md @@ -2361,6 +2361,7 @@ Tools for conducting research, surveys, interviews, and data collection. - [leehanchung/bing-search-mcp](https://github.com/leehanchung/bing-search-mcp) πŸ“‡ ☁️ - Web search capabilities using Microsoft Bing Search API - [leadbrain/korean-data-mcp](https://github.com/leadbrain/korean-data-mcp) [![leadbrain/korean-data-mcp MCP server](https://glama.ai/mcp/servers/leadbrain/korean-data-mcp/badges/score.svg)](https://glama.ai/mcp/servers/leadbrain/korean-data-mcp) 🐍 ☁️ - Real-time Korean web data β€” Naver place reviews, Melon music chart, Daangn/Bunjang marketplace listings, Naver news, Musinsa fashion rankings. 7 tools powered by Apify actors. Requires APIFY_TOKEN. - [lfnovo/content-core](https://github.com/lfnovo/content-core) 🐍 🏠 - Extract content from URLs, documents, videos, and audio files using intelligent auto-engine selection. Supports web pages, PDFs, Word docs, YouTube transcripts, and more with structured JSON responses. +- [lilbee](https://github.com/tobocop2/lilbee) 🐍 🏠 🍎 πŸͺŸ 🐧 - Local-first search engine over your files, code, and crawled web pages. It runs and manages the models itself and answers with citations back to the source. - [Linked-API/linkedapi-mcp](https://github.com/Linked-API/linkedapi-mcp) πŸŽ–οΈ πŸ“‡ ☁️ - MCP server that lets AI assistants control LinkedIn accounts and retrieve real-time data. - [linxule/mineru-mcp](https://github.com/linxule/mineru-mcp) πŸ“‡ ☁️ - MCP server for MinerU document parsing API. Parse PDFs, images, DOCX, and PPTX with OCR (109 languages), batch processing (200 docs), page ranges, and local file upload. 73% token reduction with structured output. - [luminati-io/brightdata-mcp](https://github.com/luminati-io/brightdata-mcp) πŸ“‡ ☁️ -Β Discover, extract, and interact with the web - one interface powering automated access across the public internet. From acbcb258e745202798d9a5d5bf77c9c10cff7fce Mon Sep 17 00:00:00 2001 From: Tobias Perelstein <5562156+tobocop2@users.noreply.github.com> Date: Sun, 14 Jun 2026 15:25:41 -0400 Subject: [PATCH 2/5] Shorten lilbee description and make crawling explicit --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 94bca52e5..b425c75cb 100644 --- a/README.md +++ b/README.md @@ -2361,7 +2361,7 @@ Tools for conducting research, surveys, interviews, and data collection. - [leehanchung/bing-search-mcp](https://github.com/leehanchung/bing-search-mcp) πŸ“‡ ☁️ - Web search capabilities using Microsoft Bing Search API - [leadbrain/korean-data-mcp](https://github.com/leadbrain/korean-data-mcp) [![leadbrain/korean-data-mcp MCP server](https://glama.ai/mcp/servers/leadbrain/korean-data-mcp/badges/score.svg)](https://glama.ai/mcp/servers/leadbrain/korean-data-mcp) 🐍 ☁️ - Real-time Korean web data β€” Naver place reviews, Melon music chart, Daangn/Bunjang marketplace listings, Naver news, Musinsa fashion rankings. 7 tools powered by Apify actors. Requires APIFY_TOKEN. - [lfnovo/content-core](https://github.com/lfnovo/content-core) 🐍 🏠 - Extract content from URLs, documents, videos, and audio files using intelligent auto-engine selection. Supports web pages, PDFs, Word docs, YouTube transcripts, and more with structured JSON responses. -- [lilbee](https://github.com/tobocop2/lilbee) 🐍 🏠 🍎 πŸͺŸ 🐧 - Local-first search engine over your files, code, and crawled web pages. It runs and manages the models itself and answers with citations back to the source. +- [lilbee](https://github.com/tobocop2/lilbee) 🐍 🏠 🍎 πŸͺŸ 🐧 - Runs and manages local models, indexes your files and code, crawls the websites you point it at, and answers with citations back to the source. - [Linked-API/linkedapi-mcp](https://github.com/Linked-API/linkedapi-mcp) πŸŽ–οΈ πŸ“‡ ☁️ - MCP server that lets AI assistants control LinkedIn accounts and retrieve real-time data. - [linxule/mineru-mcp](https://github.com/linxule/mineru-mcp) πŸ“‡ ☁️ - MCP server for MinerU document parsing API. Parse PDFs, images, DOCX, and PPTX with OCR (109 languages), batch processing (200 docs), page ranges, and local file upload. 73% token reduction with structured output. - [luminati-io/brightdata-mcp](https://github.com/luminati-io/brightdata-mcp) πŸ“‡ ☁️ -Β Discover, extract, and interact with the web - one interface powering automated access across the public internet. From 6c002ea41b9d73c81e1c42dff7d1ac1612d9f9ab Mon Sep 17 00:00:00 2001 From: Tobias Perelstein <5562156+tobocop2@users.noreply.github.com> Date: Sun, 14 Jun 2026 15:38:00 -0400 Subject: [PATCH 3/5] Clarify Ollama and LM Studio support alongside the native model manager --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index b425c75cb..5c7031d47 100644 --- a/README.md +++ b/README.md @@ -2361,7 +2361,7 @@ Tools for conducting research, surveys, interviews, and data collection. - [leehanchung/bing-search-mcp](https://github.com/leehanchung/bing-search-mcp) πŸ“‡ ☁️ - Web search capabilities using Microsoft Bing Search API - [leadbrain/korean-data-mcp](https://github.com/leadbrain/korean-data-mcp) [![leadbrain/korean-data-mcp MCP server](https://glama.ai/mcp/servers/leadbrain/korean-data-mcp/badges/score.svg)](https://glama.ai/mcp/servers/leadbrain/korean-data-mcp) 🐍 ☁️ - Real-time Korean web data β€” Naver place reviews, Melon music chart, Daangn/Bunjang marketplace listings, Naver news, Musinsa fashion rankings. 7 tools powered by Apify actors. Requires APIFY_TOKEN. - [lfnovo/content-core](https://github.com/lfnovo/content-core) 🐍 🏠 - Extract content from URLs, documents, videos, and audio files using intelligent auto-engine selection. Supports web pages, PDFs, Word docs, YouTube transcripts, and more with structured JSON responses. -- [lilbee](https://github.com/tobocop2/lilbee) 🐍 🏠 🍎 πŸͺŸ 🐧 - Runs and manages local models, indexes your files and code, crawls the websites you point it at, and answers with citations back to the source. +- [lilbee](https://github.com/tobocop2/lilbee) 🐍 🏠 🍎 πŸͺŸ 🐧 - Runs and manages its own local models, or uses your existing Ollama or LM Studio if you prefer. Indexes your files and code, crawls the websites you point it at, and answers with citations to the source. - [Linked-API/linkedapi-mcp](https://github.com/Linked-API/linkedapi-mcp) πŸŽ–οΈ πŸ“‡ ☁️ - MCP server that lets AI assistants control LinkedIn accounts and retrieve real-time data. - [linxule/mineru-mcp](https://github.com/linxule/mineru-mcp) πŸ“‡ ☁️ - MCP server for MinerU document parsing API. Parse PDFs, images, DOCX, and PPTX with OCR (109 languages), batch processing (200 docs), page ranges, and local file upload. 73% token reduction with structured output. - [luminati-io/brightdata-mcp](https://github.com/luminati-io/brightdata-mcp) πŸ“‡ ☁️ -Β Discover, extract, and interact with the web - one interface powering automated access across the public internet. From ba2780ae4c021f302e7f5deb4da28b93e277a242 Mon Sep 17 00:00:00 2001 From: Tobias Perelstein <5562156+tobocop2@users.noreply.github.com> Date: Sun, 14 Jun 2026 16:49:51 -0400 Subject: [PATCH 4/5] Use full owner/repo name (tobocop2/lilbee) per the name-check rule --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 5c7031d47..162e15f39 100644 --- a/README.md +++ b/README.md @@ -2361,7 +2361,7 @@ Tools for conducting research, surveys, interviews, and data collection. - [leehanchung/bing-search-mcp](https://github.com/leehanchung/bing-search-mcp) πŸ“‡ ☁️ - Web search capabilities using Microsoft Bing Search API - [leadbrain/korean-data-mcp](https://github.com/leadbrain/korean-data-mcp) [![leadbrain/korean-data-mcp MCP server](https://glama.ai/mcp/servers/leadbrain/korean-data-mcp/badges/score.svg)](https://glama.ai/mcp/servers/leadbrain/korean-data-mcp) 🐍 ☁️ - Real-time Korean web data β€” Naver place reviews, Melon music chart, Daangn/Bunjang marketplace listings, Naver news, Musinsa fashion rankings. 7 tools powered by Apify actors. Requires APIFY_TOKEN. - [lfnovo/content-core](https://github.com/lfnovo/content-core) 🐍 🏠 - Extract content from URLs, documents, videos, and audio files using intelligent auto-engine selection. Supports web pages, PDFs, Word docs, YouTube transcripts, and more with structured JSON responses. -- [lilbee](https://github.com/tobocop2/lilbee) 🐍 🏠 🍎 πŸͺŸ 🐧 - Runs and manages its own local models, or uses your existing Ollama or LM Studio if you prefer. Indexes your files and code, crawls the websites you point it at, and answers with citations to the source. +- [tobocop2/lilbee](https://github.com/tobocop2/lilbee) 🐍 🏠 🍎 πŸͺŸ 🐧 - Runs and manages its own local models, or uses your existing Ollama or LM Studio if you prefer. Indexes your files and code, crawls the websites you point it at, and answers with citations to the source. - [Linked-API/linkedapi-mcp](https://github.com/Linked-API/linkedapi-mcp) πŸŽ–οΈ πŸ“‡ ☁️ - MCP server that lets AI assistants control LinkedIn accounts and retrieve real-time data. - [linxule/mineru-mcp](https://github.com/linxule/mineru-mcp) πŸ“‡ ☁️ - MCP server for MinerU document parsing API. Parse PDFs, images, DOCX, and PPTX with OCR (109 languages), batch processing (200 docs), page ranges, and local file upload. 73% token reduction with structured output. - [luminati-io/brightdata-mcp](https://github.com/luminati-io/brightdata-mcp) πŸ“‡ ☁️ -Β Discover, extract, and interact with the web - one interface powering automated access across the public internet. From 03968e894893ca07acdb90a7b65dc47630b7064e Mon Sep 17 00:00:00 2001 From: Tobias Perelstein <5562156+tobocop2@users.noreply.github.com> Date: Sun, 14 Jun 2026 20:49:18 -0400 Subject: [PATCH 5/5] Add Glama score badge to the lilbee entry --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 162e15f39..57bb7f880 100644 --- a/README.md +++ b/README.md @@ -2361,7 +2361,7 @@ Tools for conducting research, surveys, interviews, and data collection. - [leehanchung/bing-search-mcp](https://github.com/leehanchung/bing-search-mcp) πŸ“‡ ☁️ - Web search capabilities using Microsoft Bing Search API - [leadbrain/korean-data-mcp](https://github.com/leadbrain/korean-data-mcp) [![leadbrain/korean-data-mcp MCP server](https://glama.ai/mcp/servers/leadbrain/korean-data-mcp/badges/score.svg)](https://glama.ai/mcp/servers/leadbrain/korean-data-mcp) 🐍 ☁️ - Real-time Korean web data β€” Naver place reviews, Melon music chart, Daangn/Bunjang marketplace listings, Naver news, Musinsa fashion rankings. 7 tools powered by Apify actors. Requires APIFY_TOKEN. - [lfnovo/content-core](https://github.com/lfnovo/content-core) 🐍 🏠 - Extract content from URLs, documents, videos, and audio files using intelligent auto-engine selection. Supports web pages, PDFs, Word docs, YouTube transcripts, and more with structured JSON responses. -- [tobocop2/lilbee](https://github.com/tobocop2/lilbee) 🐍 🏠 🍎 πŸͺŸ 🐧 - Runs and manages its own local models, or uses your existing Ollama or LM Studio if you prefer. Indexes your files and code, crawls the websites you point it at, and answers with citations to the source. +- [tobocop2/lilbee](https://github.com/tobocop2/lilbee) [![tobocop2/lilbee MCP server](https://glama.ai/mcp/servers/tobocop2/lilbee/badges/score.svg)](https://glama.ai/mcp/servers/tobocop2/lilbee) 🐍 🏠 🍎 πŸͺŸ 🐧 - Runs and manages its own local models, or uses your existing Ollama or LM Studio if you prefer. Indexes your files and code, crawls the websites you point it at, and answers with citations to the source. - [Linked-API/linkedapi-mcp](https://github.com/Linked-API/linkedapi-mcp) πŸŽ–οΈ πŸ“‡ ☁️ - MCP server that lets AI assistants control LinkedIn accounts and retrieve real-time data. - [linxule/mineru-mcp](https://github.com/linxule/mineru-mcp) πŸ“‡ ☁️ - MCP server for MinerU document parsing API. Parse PDFs, images, DOCX, and PPTX with OCR (109 languages), batch processing (200 docs), page ranges, and local file upload. 73% token reduction with structured output. - [luminati-io/brightdata-mcp](https://github.com/luminati-io/brightdata-mcp) πŸ“‡ ☁️ -Β Discover, extract, and interact with the web - one interface powering automated access across the public internet.