The real catalog of tools for AI agents

Priority-weighted context window token pruner and FIFO eviction engine protecting LLM prompt boundar

Context window token analysis and budget management

Context-window optimization: caching, compression & smart file tools that cut tokens 60-90%.

Adaptive multi-tier TPM/RPM rate limiter with smooth leaky bucket queuing and burst wait estimation

Strips 85-97% of HTML/DOM bloat into clean Markdown or JSON with cryptographic ROI proof.

Inspect OpenAPI 3.0 specs and synthesize schema-compliant Model Context Protocol tool declarations w

Same functionality, consuming only 1/20 of the context window tokens.

Premium agentic endpoint for context-window-optimizer-mcp.

Prunes 85% of HTML/DOM/JSON token bloat into semantic Markdown for LLM agents via x402 & MPP on agentdiet.dev.

Multi-model LLM token cost budget ledger and burn rate forecaster enforcing spending limits and earl

Bidirectional in-memory sensitive vault and surrogate token masker protecting credentials in LLM pro

Premium agentic endpoint for context-window-overflow-router-mcp.

Local Windows ambient context (presence, foreground app, battery) as privacy-gated MCP tools.

Token entropy and n-gram perplexity analyzer auditing LLM outputs for degenerate repetition loops an

Adaptive sliding window query debouncing and micro-batch coalescing engine optimizing LLM throughput

Semantic Versioning 2.0.0 range matcher and dependency tree resolver for multi-agent toolkits and pl

In-memory distributed lease lock with monotonically increasing fencing tokens preventing multi-agent

Regex and Luhn heuristic PII redaction and tokenization engine sanitizing sensitive emails, phones,

Codebase Q&A for Claude Code through Gemini's 1M-token window, with workspace scans and caching.

Semantic boundary preserving text chunker maintaining markdown headers, code fences, and paragraphs