ANKIT AGARWAL

ANKIT AGARWAL

Senior DevOps Leader & AI Tool Builder
All activity
Building LLM agents with 100+ tools? Context bloat kills performance and costs. Agent-Corex intelligently selects only the relevant tools your model actually needs. ⚔50-75% fewer tokens → massive cost savings šŸš€ 3-5x faster inference → better user experience šŸŽÆ 95%+ accurate tool selection → production-ready Hybrid Ranking Engine: • Keyword matching (<1ms) + semantic embeddings (50-100ms) • Works with any MCP server Use cases: autonomous agents, multi-step reasoning, cost optimization.
Agent-Corex – Intelligent Tool Selection
Agent-Corex – Intelligent Tool SelectionIntelligent tool selection for LLMs – 50-75% cost reduction
ANKIT AGARWALstarted a discussion

We built Agent-Corex after hitting 'context bloat hell' with 200+ tools

Hey everyone! šŸ‘‹ We just shipped Agent-Corex, and I want to share the story of why we built it. The Problem We Faced: Six months ago, we were building an LLM agent system that had access to ~200 different tools. We did what seemed logical: we dumped all of them into the system prompt. It was a disaster. Our API costs exploded (30K tokens per request 😱) Inference was slow (2.3 seconds per...

Contribute to ankitpro/cursor-rules-generator development by creating an account on GitHub. Instead of manually writing rules for AI coding assistants, this tool analyzes your repository and generates structured rules. Perfect for: • AI coding workflows • Large repositories with complex context Key features: • Automatic rule generation • Open-source and extensible Install: npm install cursor-rules-generator-mcp Try it with your repo and see how it improves AI-assisted coding.
GitHub
GitHubGenerate Cursor IDE rules automatically from your codebase