Daily LLM token pricing data with automatic updates

MANA - LLM Token Optimization

OpenCode plugin for RTK (Rust Token Killer) - reduces LLM token consumption by 60-90% on dev commands

Vue/Nuxt streaming Markdown renderer for AI chat, LLM token streams, SSE/WebSocket output, incomplete Markdown, long documents, Mermaid, KaTeX, and stream-diffs powered code blocks.

Provider-neutral LLM token accounting and cost. Zero deps, isomorphic.

CLI for tokenmaxxing — sync your LLM token usage to the leaderboard.

OpenCode plugin that prefixes shell commands with snip to reduce LLM token consumption

Pure TypeScript sampling algorithms for LLM token generation with exact llama.cpp parity

High-performance CLI proxy that minimizes LLM token consumption (fork of rtk).

Framework-agnostic LLM token counter — GLM/GPT/Qwen/DeepSeek exact, Claude/Gemini approx

Local dashboard for monitoring LLM token usage across Cursor, Claude Code, and Codex

Compact, language-agnostic codebase mapper for LLM token efficiency.

MCP server that compresses, summarizes, and filters context to minimize LLM token usage

TypeScript primitives for LLM token usage, billing integrity, cost, reliability, and failure receipt measurement.

Token-Less — LLM token optimization toolkit (schema/response compression, command rewriting, tool readiness)

Real-time, local-only web dashboard that visualizes LLM token usage and costs from standard OpenTelemetry data

Calculate LLM token costs from litellm pricing data

Trimly CLI — track and optimize your LLM token spend

OpenCode TUI sidebar plugin for real-time LLM token metrics

Track input and output LLM token usage per call with pluggable storage (memory, file, MongoDB)