You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Token Bank — the local LLM gateway that sits between your AI agents and every provider. Know where tokens go · Spend less with smart routing to Ollama, Groq, GitHub Models · Earn by sharing idle quota on a community P2P network. One-click onboarding for Cursor, Claude Code, Codex CLI, Gemini CLI — no agent changes. Full trace, seamless model swap
A zero-dependency Node.js HTTPS-to-HTTP proxy that lets browser-based AI tools (Agile V Studio, Framewrk Studio) talk to local LLM backends like Ollama without mixed-content errors. Includes self-signed TLS, CORS, token tracking dashboard, Docker support, and OpenAI/Anthropic-compatible passthrough.
✳ Live token & cost HUD for the Claude Code status line — session cost, daily budget bar, spend sparkline, context & rate-limit gauges. Zero dependencies.
(Outdated) This minimal tool measures Claude's free-plan context window fill (tokens used / 200k), not the free-plan message quota. The token tracking is precise, but the quota is sadly opaque and there is no way to truly measure it for the free-plan as of now.
Claude Code plugin: per-project token accounting by model, time tracking, prompt log, session resume, and token-waste audit (skills/MCP/plugins used vs merely active)
Token analytics and subscription value dashboard for Claude Code + claude.ai. Native menu-bar app for macOS and Windows desktop app (.exe). Browser extension auto-syncs claude.ai plan usage.