Token Usage: open-source projects on GitHub
22 repositories on Token Usage, picked by the REDDYX AI agent. Each has a summary, key features and a breakdown. Sorted by stars.
// RELATED TOPICS
AI Code Cost Tracker
Interactive TUI panel for tracking token expenses of AI code generation. Supports Claude Code, Codex, and Cursor.
★ 6,499 · TypeScriptToken Monitor: Real-Time Tracking
Widget for tracking tokens, costs, and limits of AI tools in real time with cross-device synchronization.
★ 3,701 · JavaScriptClaude Tools
A visual toolset for debugging Claude Code: view session logs, tool calls, token usage, subagents, and the context window. Free and open source.
★ 3,331 · TypeScriptAI Token Tracking
🛰️ CLI utility for monitoring token usage in OpenCode, Claude Code, Cursor, Gemini, and other AI tools. 🏅Global leaderboard + 2D/3D chart.
★ 2,995 · RustCPA-USAGE-KEEPER: Usage Tracker
Standalone CLI‑proxy usage tracker with SQLite storage and built‑in dashboard.
★ 1,315 · GoCOORDINATION OF CLAUDE CODEX CURSOR
squadra synchronously manages windows of Claude, Codex and Cursor: tasks, prechecks, parallel tests. Built-in skills recall lessons, simplify code and forecast work.
★ 1,279 · PythonLOCAL GATEWAY CLAUDE
ThinkWatch-Lite — local gateway for Claude Code, Codex and other AI clients on macOS, Windows and Linux. Switches upstreams without touching clients, keeps API keys from
★ 1,070 · TypeScriptToken Optimizer
Identifies and removes redundant tokens. Improves context quality during compression and prevents data degradation.
★ 1,034 · PythonAGENTACC: Agent Report
The panel shows AI agent actions: tools, modified files, launched tests, time and tokens. Works locally, without registration or telemetry.
★ 759 · PythonDSH-COST-METER: TRACKING EXPENSES
The dsh-cost-meter plugin for DeepSeek Harness tracks the session and daily cost, budget, and history of DeepSeek Harness. Includes the token map,peak/off-peak pricing
★ 699 · JavaScriptACCELERATING CODE REFACTORING
Tura reduces the number of code rewrite steps by 83.1% and increases DeepSWE pass rate by 16.7 percentage points compared to Codex CLI.
★ 667 · RustPOKETOKENBAR - COLLECT ALL POKÉMON
PokeTokenBar lets you spend tokens to raise, evolve and collect Pokémon in a Swift-based app.
★ 567 · SwiftHUD FOR 25+ CODING AGENTS
agent-hud-open shows quotas, tokens and sessions for Claude Code, Codex and 25+ agents in one view. Answer requests and jump back to coding in one click. Works on Mac, Wi
★ 473 · RustTokentelemetry: AI Agent Dashboard
Local token telemetry dashboard for AI agents: tracks usage, sessions, tool calls, and reasoning chains in Hermes and Claude Code.
★ 388 · PythonCODEXU WIDGET FOR OPENAI CODEX
macOS widget for working with OpenAI Codex: tracking quotas, tokens and today's task board.
★ 359 · SwiftLOCAL TELEMETRY AI PILOT
loongsuite-pilot collects telemetry from AI coders in local mode, unifying OpenTelemetry events from Claude Code, Codex, Cursor and agents. It tracks token usage, cost, t
★ 253 · TypeScriptTOKENSCOPE — CLAUDE MENU BAR
Shows Claude CLI token usage, cost, and details by model, MCP, and skill directly in the macOS menu bar.
★ 248 · RustCLAUDE PULSE: TOKEN CONTROL
Local panel for Claude Code without dependencies: real-time tokens and context, session restoration, and tool call approval from your phone.
★ 247 · JavaScriptLLM TOKENOMICS: TOOLS TO SAVE
Curated list on AI token economics: costs, waste, and how to cut bills. Tools, benchmarks, papers, and ready configs for LLMs and coding agents. 206 stars on GitHub.
★ 219 · PythonVERIFY AI AGENTS BILLS
Verovo verifies AI agent charges and confirms delivery results. Local CLI recounts supported billings, while Buyer Ledger catalogs 26 tool billing models.
★ 219 · PythonEMPEROR-AGENT: LOCAL AI WITH WEBUI
Emperor-agent is a local Emperor-style AI agent with Vue WebUI. Supports multi-provider LLMs, streaming chat, tools, skills, memory, and token telemetry. 203 stars on Git
★ 218 · TypeScriptSmith Adaptive Model Router
Agent Smith routes model calls adaptively, monitors Codex token usage in real time, and generates reproducible benchmark reports with verification receipts.
★ 9 · PythonNew projects on this topic in Telegram
Telegram →