Token-Oriented Object Notation for Go โ JSON for LLMs at half the token cost
-
Updated
Nov 24, 2025 - Go
Token-Oriented Object Notation for Go โ JSON for LLMs at half the token cost
Token burn reducer and focus keeper for Claude Code, Codex, Copilot, Gemini CLI, and more: surgical read hints, PDF/Office/CSV/markdown file interception, 160+ filter & interception rules, compact manifest injection, image shrinking, cache and compact skills, cache MCP calls, prompt injection protections, and much more.
Codex usage tracker for live quota, token analytics & session insights. Local-first desktop app for macOS & Windows.
Local dashboard for visualizing usage across seven AI coding agents - sessions, token costs, cache performance, tool calls, and daily breakdowns
Static cost analyzer for multi-agent context graphs: explain what agents load and estimate tokens per fire and per day.
Time estimation MCP server for AI agents: PERT, COCOMO II, Monte Carlo, sprint forecasting, token-to-time mapping, cost estimation, and schedule risk tools.
A searchable, sortable model picker for the DeepSeek Harness Web UI โ provider groups, favorites, models.dev prices, context windows, live per-task token cost and a local-model filter. One-command install: dsh plugin add dsh-model-garden.
Open your AI agents' black box. The waste is between your agents, not inside them. Four deterministic detectors over one trace file, priced from real usage fields. Hosted at boxdawn.com.
Cost-aware multi-model orchestration for Codex CLI: route hard work to strong agents, replay proven paths with cheaper agents, and track cost, memory, and project evolution.
Evidence-first token cost ledger and budget checks for DeepSeek Harness
Local hooks that catch vague AI-agent prompts before they burn tokens.
Build a private evaluation dataset to optimize your organization's token costs.
Community plugins for DeepSeek Harness (DSH) Web GUI: session token cost meter with official dynamic pricing, DeepSeek & Volcengine billing balance, and update checker. Plain JavaScript, no build required.
MCP server: token cost math for LLM API calls, 69 models across 17 providers, prices verified by ComparEdge
Compare LLM API pricing from your terminal. Supports 300+ models across all major providers. https://x.com/saqibameen
Local-first observability, cost analysis and project memory for Codex, Claude Code and AI coding agents.
See what your AI coding agent cost, itemized on every pull request. Token & dollar tracking for Claude Code, Cursor, Copilot, Aider & any OpenAI/Anthropic tool. Local ledger, sticky PR comment, GitHub Action, and dashboard.
Measure what your MCP servers actually cost: per-server tool-schema weight in bytes and tokens, for AI coding agents.
Read-only lens over a running OxideGate proxy: shows how many bytes each MCP server costs on every request.
OpenLLM Monitor ๐ is a plug-and-play, real-time observability dashboard ๐ for monitoring and debugging LLM API calls across OpenAI ๐ค, Ollama ๐ฆ, OpenRouter ๐, and more. It tracks tokens ๐งฎ, latency โฑ๏ธ, cost ๐ธ, retries ๐, and lets you replay prompts ๐. Fully open-source ๐ and self-hostable ๐ ๏ธ.
To associate your repository with the token-cost topic, visit your repo's landing page and select "manage topics."