{
  "slug": "track-coding-agent-costs",
  "label": "track and cut coding-agent token costs",
  "blurb": "Local trackers and proxies that show what your coding agents spend on tokens and cut how many they send.",
  "keywords": [
    "token usage",
    "token cost",
    "cost tracking",
    "token reduction",
    "context compression"
  ],
  "categories": [
    "code-devtools",
    "infrastructure"
  ],
  "access": [
    "cli"
  ],
  "count": 12,
  "official": 1,
  "url": "https://agentswitchboard.dev/tasks/track-coding-agent-costs",
  "browseUrl": "https://agentswitchboard.dev/browse?task=track-coding-agent-costs",
  "agentsUrl": "https://agentswitchboard.dev/api/agents?task=track-coding-agent-costs",
  "agents": [
    {
      "name": "CodeBurn",
      "slug": "codeburn",
      "url": "https://agentswitchboard.dev/agents/codeburn",
      "iconUrl": "https://agentswitchboard.dev/icons/codeburn.png?v=43381673",
      "description": "Tracks AI coding token usage and cost across coding agents locally, from a CLI, a menubar app and a web dashboard.",
      "provider": "Agentseal",
      "categories": [
        "code-devtools",
        "infrastructure"
      ],
      "accessMethods": [
        "cli"
      ],
      "verified": true,
      "official": false,
      "featured": false,
      "sponsored": false,
      "authType": "none",
      "why": null
    },
    {
      "name": "Tokscale",
      "slug": "tokscale",
      "url": "https://agentswitchboard.dev/agents/tokscale",
      "iconUrl": "https://agentswitchboard.dev/icons/tokscale.png?v=1712b959",
      "description": "Tracks token usage and cost across AI coding agents from a terminal UI and a web dashboard, with live pricing.",
      "provider": "Junho Yeo",
      "categories": [
        "infrastructure",
        "code-devtools"
      ],
      "accessMethods": [
        "cli"
      ],
      "verified": true,
      "official": false,
      "featured": false,
      "sponsored": false,
      "authType": "none",
      "why": null
    },
    {
      "name": "agentsview",
      "slug": "agentsview",
      "url": "https://agentswitchboard.dev/agents/agentsview",
      "iconUrl": "https://agentswitchboard.dev/icons/agentsview.png?v=51af0a92",
      "description": "Searches coding-agent sessions and tracks their token cost locally, from a CLI, a local web UI and a desktop app.",
      "provider": "Kenn Software",
      "categories": [
        "code-devtools",
        "data-analytics"
      ],
      "accessMethods": [
        "cli",
        "mcp"
      ],
      "verified": true,
      "official": false,
      "featured": false,
      "sponsored": false,
      "authType": "none",
      "why": "Cost breakdown: Calculates token cost per model with prompt-caching-aware pricing, filtered by date or agent."
    },
    {
      "name": "Claw Compactor",
      "slug": "claw-compactor",
      "url": "https://agentswitchboard.dev/agents/claw-compactor",
      "iconUrl": "https://agentswitchboard.dev/icons/claw-compactor.png?v=36789b42",
      "description": "Compresses LLM context such as code, JSON, logs, and chat history through a reversible 14-stage pipeline with no LLM calls, via a Python API and CLI, for agent developers.",
      "provider": "OpenCompress",
      "categories": [
        "infrastructure",
        "memory-state"
      ],
      "accessMethods": [
        "api",
        "cli"
      ],
      "verified": true,
      "official": false,
      "featured": false,
      "sponsored": false,
      "authType": "none",
      "why": null
    },
    {
      "name": "LiteLLM",
      "slug": "litellm",
      "url": "https://agentswitchboard.dev/agents/litellm",
      "iconUrl": "https://agentswitchboard.dev/icons/litellm.png?v=b12006fd",
      "description": "AI gateway unifying 100+ LLM providers under one OpenAI-compatible API. Cost tracking, guardrails, load balancing. pip install litellm. 47k GitHub stars.",
      "provider": "BerriAI",
      "categories": [
        "infrastructure"
      ],
      "accessMethods": [
        "api",
        "cli"
      ],
      "verified": true,
      "official": false,
      "featured": false,
      "sponsored": false,
      "authType": "apiKey",
      "why": null
    },
    {
      "name": "billion-context",
      "slug": "billion-context",
      "url": "https://agentswitchboard.dev/agents/billion-context",
      "iconUrl": null,
      "description": "Compresses context in a local proxy between an agent and its model API, so very long sessions keep going, with a Claude Code plugin.",
      "provider": "ranxianglei",
      "categories": [
        "memory-state",
        "infrastructure"
      ],
      "accessMethods": [
        "cli"
      ],
      "verified": true,
      "official": false,
      "featured": false,
      "sponsored": false,
      "authType": "none",
      "why": null
    },
    {
      "name": "Headroom",
      "slug": "headroom",
      "url": "https://agentswitchboard.dev/agents/headroom",
      "iconUrl": "https://agentswitchboard.dev/icons/headroom.png?v=995e9d4d",
      "description": "Compresses tool outputs, logs, RAG chunks, files, and history locally before they reach the model, as a Python or TypeScript library, a drop-in proxy, an agent wrapper, or an MCP server.",
      "provider": "Headroom Labs",
      "categories": [
        "infrastructure",
        "code-devtools"
      ],
      "accessMethods": [
        "api",
        "mcp",
        "cli"
      ],
      "verified": true,
      "official": false,
      "featured": false,
      "sponsored": false,
      "authType": "none",
      "why": null
    },
    {
      "name": "pxpipe",
      "slug": "pxpipe",
      "url": "https://agentswitchboard.dev/agents/pxpipe",
      "iconUrl": null,
      "description": "Cuts coding agents' input tokens by rendering bulky context as images in a local proxy for Claude Code, Gemini CLI and Antigravity.",
      "provider": "teamchong",
      "categories": [
        "infrastructure",
        "code-devtools"
      ],
      "accessMethods": [
        "cli"
      ],
      "verified": true,
      "official": false,
      "featured": false,
      "sponsored": false,
      "authType": "none",
      "why": null
    },
    {
      "name": "RTK",
      "slug": "rtk",
      "url": "https://agentswitchboard.dev/agents/rtk",
      "iconUrl": "https://agentswitchboard.dev/icons/rtk.png?v=97bb38d0",
      "description": "Filters and compresses shell command output such as git, test runs and builds before a coding agent reads it, via hooks for Claude Code, Cursor, Codex and Gemini CLI.",
      "provider": "RTK AI Labs",
      "categories": [
        "code-devtools",
        "infrastructure"
      ],
      "accessMethods": [
        "cli"
      ],
      "verified": true,
      "official": false,
      "featured": false,
      "sponsored": false,
      "authType": "none",
      "why": null
    },
    {
      "name": "AgentOps",
      "slug": "agentops",
      "url": "https://agentswitchboard.dev/agents/agentops",
      "iconUrl": "https://agentswitchboard.dev/icons/agentops.png?v=e2b72d49",
      "description": "Observability platform purpose-built for AI agents. Track agent sessions, LLM calls, tool use, and costs. Integrates with LangChain, CrewAI, AutoGen, and OpenAI.",
      "provider": "AgentOps",
      "categories": [
        "infrastructure"
      ],
      "accessMethods": [
        "api"
      ],
      "verified": true,
      "official": false,
      "featured": false,
      "sponsored": false,
      "authType": "apiKey",
      "why": "Track token usage and costs per agent run across all major LLM providers"
    },
    {
      "name": "Maki",
      "slug": "maki",
      "url": "https://agentswitchboard.dev/agents/maki",
      "iconUrl": "https://agentswitchboard.dev/icons/maki.png?v=5c6872b9",
      "description": "Rust coding agent CLI with tree-sitter code indexing, sandboxed Python execution, and multi-tier subagents. Benchmarks show ~40% token reduction vs competing coding agents.",
      "provider": "Maki",
      "categories": [
        "code-devtools"
      ],
      "accessMethods": [
        "cli"
      ],
      "verified": true,
      "official": false,
      "featured": false,
      "sponsored": false,
      "authType": "apiKey",
      "why": null
    },
    {
      "name": "Langfuse",
      "slug": "langfuse",
      "url": "https://agentswitchboard.dev/agents/langfuse",
      "iconUrl": "https://agentswitchboard.dev/icons/langfuse.png?v=b2abe0af",
      "description": "Open-source LLM observability and analytics. Trace, evaluate, and debug LLM apps with prompt versioning, score tracking, and a full analytics dashboard.",
      "provider": "Langfuse",
      "categories": [
        "infrastructure"
      ],
      "accessMethods": [
        "api",
        "cli"
      ],
      "verified": true,
      "official": true,
      "featured": false,
      "sponsored": false,
      "authType": "apiKey",
      "why": "Analyze user session funnels, latency distributions, and token cost trends"
    }
  ],
  "relatedTasks": [
    "monitor-apps-in-production",
    "run-code-in-a-sandbox",
    "run-ci-cd-pipelines",
    "evaluate-agents"
  ],
  "stacks": []
}