Agent Switchboard

Tasks

I need to track and cut coding-agent token costs

Local trackers and proxies that show what your coding agents spend on tokens and cut how many they send.

12 tools · 1 official

Picked from listings that mention token usage, token cost, cost tracking, token reduction or context compression in their name, description, tags or skills; those in Code & DevTools or Infrastructure & Ops, or with CLI access, rank higher.

The short answer

The best fits to track and cut coding-agent token costs on Agent Switchboard, as of 20 Nov 2026: CodeBurn, Tokscale and agentsview, of 12 tools that do it.

Which official tools track and cut coding-agent token costs?
Langfuse.
Which have a hosted MCP server?
None of the 12 tools lists a hosted MCP server address.
Which need no API key or sign-in?
CodeBurn, Tokscale and agentsview, among 8 that need none.

Updated with the weekly drop. Featured and Sponsored listings that do the job come first, labeled; the rest are ranked by how well they fit.

Compared · top 6

As of Nov 20, 2026, the last change to any of these listings. Verified means its URLs load and its access answers; we recheck every month.

ToolAccessSign-inMakerCheckedUpdated
CodeBurntoken-usage. Pick it if you want to try it with no sign-up.CLINoneAgentsealVerifiedNov 20, 2026
Tokscaletoken-usage. Pick it if you want to try it with no sign-up.CLINoneJunho YeoVerifiedNov 20, 2026
agentsviewCost breakdown. Pick it if you want to try it with no sign-up.CLI · MCPNoneKenn SoftwareVerifiedNov 20, 2026
Claw Compactortoken-compression. Pick it if you want to try it with no sign-up.API · CLINoneOpenCompressVerifiedOct 10, 2026
LiteLLMllm-gateway. Pick it if you work from a terminal.API · CLIAPI keyBerriAIVerifiedMay 13, 2026
billion-contextcontext-compression. Pick it if you want to try it with no sign-up.CLINoneranxiangleiVerifiedNov 20, 2026

Best fits · 12

Filter these on Browse

Official · 1

The ones published by the company behind the product.

Missing a tool that does this? Suggest a listing.

/tasks/track-coding-agent-costs
I need to track and cut coding-agent token costs · 12 fit · 1 official · keywords: token usage, token cost, cost tracking, token reduction, context compression · categories: code-devtools, infrastructure · access: cli
Local trackers and proxies that show what your coding agents spend on tokens and cut how many they send.
The best fits to track and cut coding-agent token costs on Agent Switchboard, as of 20 Nov 2026: CodeBurn, Tokscale and agentsview, of 12 tools that do it.
Which official tools track and cut coding-agent token costs? Langfuse.
Which have a hosted MCP server? None of the 12 tools lists a hosted MCP server address.
Which need no API key or sign-in? CodeBurn, Tokscale and agentsview, among 8 that need none.
Markdown: /tasks/track-coding-agent-costs.md · updated 2026-11-20
compared · as of 2026-11-20
codeburncli · auth: none · verifiedupdated 2026-11-20tokscalecli · auth: none · verifiedupdated 2026-11-20agentsviewcli+mcp · auth: none · verifiedupdated 2026-11-20claw-compactorapi+cli · auth: none · verifiedupdated 2026-10-10litellmapi+cli · auth: apiKey · verifiedupdated 2026-05-13billion-contextcli · auth: none · verifiedupdated 2026-11-20
best fits
codeburncliTracks AI coding token usage and cost across coding agents locally, from a CLI, a menubar app and a web dashboard.tokscalecliTracks token usage and cost across AI coding agents from a terminal UI and a web dashboard, with live pricing.agentsviewcli+mcpCost breakdown: Calculates token cost per model with prompt-caching-aware pricing, filtered by date or agent.claw-compactorapi+cliCompresses 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.litellmapi+cliAI gateway unifying 100+ LLM providers under one OpenAI-compatible API. Cost tracking, guardrails, load balancing. pip install litellm. 47k GitHub stars.billion-contextcliCompresses context in a local proxy between an agent and its model API, so very long sessions keep going, with a Claude Code plugin.headroomapi+mcp+cliCompresses 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.pxpipecliCuts coding agents' input tokens by rendering bulky context as images in a local proxy for Claude Code, Gemini CLI and Antigravity.rtkcliFilters 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.agentopsapiTrack token usage and costs per agent run across all major LLM providersmakicliRust coding agent CLI with tree-sitter code indexing, sandboxed Python execution, and multi-tier subagents. Benchmarks show ~40% token reduction vs competing coding agents.langfuseapi+cliAnalyze user session funnels, latency distributions, and token cost trends
official
langfuse
related tasks
/tasks/monitor-apps-in-production52 fitmonitor apps in production/tasks/run-code-in-a-sandbox58 fitrun code in a sandbox/tasks/run-ci-cd-pipelines11 fitrun CI/CD pipelines/tasks/evaluate-agents32 fittest and evaluate agents
more
/browse?task=track-coding-agent-costsall 12, with filters/tasksevery task/api/tasks/track-coding-agent-coststhis task as JSONGET · no auth