AntonG87

AntonG87/codearia-sieve

Parses a web page into the exact format a decision model needs: dates as dates, numbers with units, chunks that fit the model's window. MCP server + TypeScript library, no model or API key required.

5 good first / help-wanted issues · TypeScript · last activity Sep 22, 2026

5 stars 1 forks 5 watchers TypeScript MIT License
ai-agents claude-code content-extraction context-engineering html-to-markdown llm-agents mcp mcp-server typescript web-scraping
View on GitHub Website
5 Open Issues Need Help Last updated: Sep 22, 2026

Open Issues Need Help

View All on GitHub
Title suffixes like `… | Blog` and `… | Site Name` end up in state.title about 1 month ago
good first issue
AntonG87/codearia-sieve
5

Parses a web page into the exact format a decision model needs: dates as dates, numbers with units, chunks that fit the model's window. MCP server + TypeScript library, no model or API key required.

TypeScript
#ai-agents#claude-code#content-extraction#context-engineering#html-to-markdown#llm-agents#mcp#mcp-server#typescript#web-scraping
Japanese kitchen units: 大さじ, 小さじ, 分, 個 are not facts about 1 month ago
good first issue
AntonG87/codearia-sieve
5

Parses a web page into the exact format a decision model needs: dates as dates, numbers with units, chunks that fit the model's window. MCP server + TypeScript library, no model or API key required.

TypeScript
#ai-agents#claude-code#content-extraction#context-engineering#html-to-markdown#llm-agents#mcp#mcp-server#typescript#web-scraping
Empty list or table container inside a full page gives no signal (script-rendered ingredients, fee tables) about 1 month ago
good first issue
AntonG87/codearia-sieve
5

Parses a web page into the exact format a decision model needs: dates as dates, numbers with units, chunks that fit the model's window. MCP server + TypeScript library, no model or API key required.

TypeScript
#ai-agents#claude-code#content-extraction#context-engineering#html-to-markdown#llm-agents#mcp#mcp-server#typescript#web-scraping
`state.meta` for SEO audits: html title, h1, meta description, canonical, schema.org types about 1 month ago
good first issue
AntonG87/codearia-sieve
5

Parses a web page into the exact format a decision model needs: dates as dates, numbers with units, chunks that fit the model's window. MCP server + TypeScript library, no model or API key required.

TypeScript
#ai-agents#claude-code#content-extraction#context-engineering#html-to-markdown#llm-agents#mcp#mcp-server#typescript#web-scraping
Korean and Japanese compound numbers read only their last group (1조 8000억 → 8000억) about 1 month ago
good first issue
AntonG87/codearia-sieve
5

Parses a web page into the exact format a decision model needs: dates as dates, numbers with units, chunks that fit the model's window. MCP server + TypeScript library, no model or API key required.

TypeScript
#ai-agents#claude-code#content-extraction#context-engineering#html-to-markdown#llm-agents#mcp#mcp-server#typescript#web-scraping