Cost Monitoring
Tracking token usage and spend. As of 2026-11-21, 152 indexed products offer it (58 with full profiles), in 9 forms: 106 MCP servers, 27 Infrastructure, 12 Plugins, 2 IDE extensions. 53 were published in the last 90 days, against 48 in the 90 days before. CodeBurn has the most GitHub stars, 21% of the total across 130 products with their own repository.
CapabilitySegment label: Lagging the catalogue DER
Available as
All in the directoryProfiled products grouped by product form. Within each form: own-repository products by GitHub stars, then products in a subfolder of a larger repository (they show that repository's stars), up to 10 each.
MCP servers 106 indexed · 19 profiled
Protocol-level reach: 36 of the 45 active platforms AgentSidekick tracks document support for MCP. DER Which platforms
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | CodeBurnAI coding spend, tokens and plan quotas across Claude Code, Codex, Cursor and 40+ more tools | getagentseal | 12k | 1d ago | ||
| 2 | gortexHigh-performance code-intelligence engine for AI agents and IDE, supports 257 languages, multi repositories, based on graph, with access via CLI, MCP Server, and API. AI coding agents teammate - expose only needed information, cutting token usage up to 50x. 100% local. Discord: https://discord.gg/39MFHu3J5d | zzet | 2.1k | today | ||
| 3 | squadraCoordinate Claude, Codex and Cursor windows with shared tasks, acknowledgements, prechecks, parallel tests, source-bound proofs and independent review. Built-in skills recall lessons, simplify code and forecast work. Track progress, decisions and evidence in a bilingual local dashboard, with MCP plugins. Browse skills and verified security audits. | dagoSte | 984 | 2d ago | ||
| 4 | android-remote-control-mcpAn MCP Server for Android running on the phone, optmized for token usage, supports also files downloads, camera, a privacy mode (to anonymize/pseudononymize your PII) and support various tunnelling (included a free E2E HTTPS tunnel out of the box in addition to cloudflare and ngrok). | danielealbano | 857 | today | ||
| 5 | llmtrimMCP server and proxy that compresses LLM prompts, tool output, and replies to cut token cost. | fkiene | 276 | 9d ago | ||
| 6 | agentburnLocal profiler: which usage window took you out, and where your agent's money goes | Socialpranker | 81 | 5d ago | ||
| 7 | Cloud FinOps Skill & MCPCloud cost + FinOps knowledge for AI agents: AWS/Azure/GCP optimisation, AI spend, waste playbooks. | OptimNow | 75 | 1d ago | ||
| 8 | preflightNew Relic MCP server for observing AI coding assistants (Claude Code, Cursor, Copilot, etc.) | newrelic-experimental | 67 | today | ||
| 9 | mcpspendQuery your MCPSpend usage: cost today, top tools, recent sessions, budget projections. | andreisirbu91-lab | 58 | 2mo ago | ||
| 10 | ai-memoryPersistent memory for any AI — zero token cost until recall | alphaonedev | 57 | today |
Infrastructure 27 indexed · 25 profiled
No compatibility evidence is collected for this form.
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | BifrostGo-based LLM gateway exposing many providers through one OpenAI-compatible API with failover, load balancing, governance and an MCP gateway. | Maxim AI | 9.9k | today | ||
| 2 | llm-gatewayOpen Source LLM Gateway 🦚 | mnfst | 7.7k | 4d ago | ||
| 3 | otariOpen-source AI gateway you run yourself. One endpoint for 40+ providers, with virtual keys, budgets, and usage tracking. | mozilla-ai | 959 | today | ||
| 4 | ThinkWatch-LiteLocal gateway for Claude Code, Codex and other AI clients on macOS, Windows and Linux: switch upstreams without touching clients, keep API keys from relays, cut off malicious tool calls, trace every request. | ThinkWatchProject | 946 | 1d ago | ||
| 5 | ThinkWatchSelf-hosted AI API and MCP gateway for organizations: SSO and RBAC, per-user identity for MCP tool calls, PII redaction and tool-call guards, rate limits, budgets, cost accounting and audit logs. | ThinkWatchProject | 817 | today | ||
| 6 | agentacctSee what your coding agents did and what it cost. Breaks each task down into work steps — tools used, files changed, tests run, time and tokens spent. Local-first dashboard for Claude Code, Codex, OpenCode, and more. No login, no telemetry. | mikehasa | 757 | 1mo ago | ||
| 7 | ANOLISAANOLISA (Agentic Nexus Operating Layer & Interface System Architecture) | Agentic OS with runtime, security, observability, and Tokenless response compression for lower token usage and cost. | agentic-os-org | 685 | today | ||
| 8 | clawmetrySee your agent think. Zero-config observability & governance for 30 AI agent runtimes: Claude Code, OpenAI Codex, Hermes, OpenClaw & 26 more. Live token costs, sessions, tool calls, crons. | vivekchand | 437 | today | ||
| 9 | loongsuite-pilotLocal-first telemetry collector for AI coding agents — unified OpenTelemetry events for Claude Code, Codex, Cursor and more. Token usage, cost, traces and security audit, exported anywhere. | alibaba | 265 | today | ||
| 10 | awesome-ai-tokenomicsA curated list on AI token economics: what tokens cost, where they get wasted, and how to cut the bill. Tools, benchmarks, papers, and copy-paste configs for the token economy of LLMs and coding agents. | QuesmaOrg | 221 | 8d ago |
Plugins 12 indexed · 7 profiled
7 of these are Claude plugins, which Claude Code documents (protocol-level). DER
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | claude-flightdeckA Claude Code mod that puts a live agent dashboard in your terminal: context and cost, advisor timeline, every permission check, subagent cards and swimlanes. | scasella | 333 | 2d ago | ||
| 2 | tokendoctortokendoctor: the same Claude Code for up to 38% less. Replays your own past sessions to show what each change would have saved, then changes only what you pick | localixai | 171 | 1d ago | ||
| 3 | token-saverContent-aware output compression for AI coding assistants. 36 specialized processors cut CLI output tokens by 60-99% (git, pytest, npm, terraform, kubectl, docker, and more) without losing errors, diffs, or stack traces. | ppgranger | 167 | 16d ago | ||
| 4 | claude-context-optimizerClaude Code plugin that tracks token usage, identifies wasted context, and saves 30-50% on API costs. Heatmaps, ROI reports, budget alerts, efficiency scores, git-aware suggestions — all local, zero config. | egorfedorov | 134 | 11d ago | ||
| 5 | claude-modsClaude Code mod: context in tokens, 5-hour and weekly limits vs. the clock, prompt cache countdown, session cost and running agents, in one band above the prompt. | augiefra | 31 | 7d ago | ||
| 6 | conciseSay more with less. Claude Code skill/plugin that cuts ~60-70% of output tokens while keeping natural, readable English. | o4f6bgpac3 | 21 | 7mo ago | ||
| 7 | dash0OpenTelemetry observability for Claude Code sessions. Captures tool calls, LLM invocations, token usage, and errors as OTel traces. Send telemetry to Dash0 or any OpenTelemetry-compatible backend. | dash0hq | 6 | 2d ago |
IDE extensions 2 indexed · 2 profiled
No compatibility evidence is collected for this form.
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | Claude Code UsageLocal Claude Code and OpenAI Codex token usage, cache, and quota tracker in the VS Code status bar | GrowthJack | 76 | 23d ago | ||
| 2 | SuperBasedLocal-first AI coding observability in your editor: Claude Code token usage, Codex cost and Cursor spend across 50 adapters, provider-exact via a local proxy. Works with no account; sign in to see all your machines online and join your team. | superbased | 63 | 2d ago |
Agent projects 1 indexed · 1 profiled
No compatibility evidence is collected for this form.
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | tokscale🛰️ Track token usage across AI coding agents from your terminal. 🏅 Global leaderboard with trillions of tokens tracked. | junhoyeo | 5.9k | 3d ago |
Agent skills 1 indexed · 1 profiled
Protocol-level reach: 26 of the 45 active platforms AgentSidekick tracks document support for the Agent Skills format. DER Which platforms
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | ham(HAM) Memory system for AI coding agents. Cut token usage by 80% by scoping context to directories. | kromahlusenii-ops | 72 | 8mo ago |
Developer tools 1 indexed · 1 profiled
No compatibility evidence is collected for this form.
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | HeliconeProxy-based LLM observability that logs requests, costs and latency with one-line integration, plus an AI gateway. | Mintlify (Helicone) | 6.3k | 4d ago |
SaaS products 1 indexed · 1 profiled
No compatibility evidence is collected for this form.
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | Datadog LLM ObservabilityModule of Datadog APM that traces LLM chains and agents, tracks token cost and latency, and runs quality and security evaluations. | Datadog | — | — |
Agent SDKs 1 indexed · 1 profiled
No compatibility evidence is collected for this form.
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | Stripe Agent ToolkitLibraries and an MCP server that let agent frameworks call Stripe APIs, plus helpers for metering and billing LLM token usage. | Stripe | 2.1k | today |
Which platforms these forms can reach
All platformsProtocol-level: the platform documents support for the standard. No specific pairing has been tested.
MCP servers 106 indexed here
36 platforms document MCP support CUR.
ContinueOpenCodeClaude CodeCodexGemini CLIZedOpenHandsClineWarpgooseQwen CodeBolt (bolt.new)KiroAmazon Bedrock AgentCoreAmpApps in ChatGPT / Apps SDK (now ChatGPT Plugins)Augment CodeChatGPTClaude (claude.ai apps)Claude DesktopCursorDevinDevin Desktop (formerly Windsurf)Factory (Droid)Gemini (app)Gemini Enterprise Agent Platform (formerly Vertex AI / Vertex AI Agent Builder)GitHub CopilotGitHub Copilot cloud agent (formerly Copilot coding agent)Google AntigravityJetBrains AI AssistantJunieLovableMicrosoft Copilot StudioReplit AgentTabninev0
Agent skills 1 indexed here
26 platforms document Agent Skills support CUR.
OpenClawOpenCodeClaude CodeCodexGemini CLIOpenHandsWarpgooseBolt (bolt.new)KiroAmpApps in ChatGPT / Apps SDK (now ChatGPT Plugins)ChatGPTClaude (claude.ai apps)Claude DesktopCursorDevinDevin Desktop (formerly Windsurf)Factory (Droid)Gemini (app)GitHub CopilotGitHub Copilot cloud agent (formerly Copilot coding agent)Google AntigravityJunieReplit AgentTabnine
Platforms publishers name
| Platform | Profiled products naming it |
|---|---|
| Claude Code | 22 |
| Codex | 15 |
| Cursor | 8 |
| OpenCode | 3 |
| OpenClaw | 2 |
| Kiro | 2 |
| Gemini CLI | 1 |
| Cline | 1 |
Integrations most often paired
Third-party services named by products with this capability, whole catalogue.
| Integration | Products | Share |
|---|---|---|
| Google Cloud | 2 | 1.3% |
| AWS | 1 | 0.7% |
| Android | 1 | 0.7% |
| Azure | 1 | 0.7% |
| Datadog | 1 | 0.7% |
| Discord | 1 | 0.7% |
| Grafana | 1 | 0.7% |
| Kubernetes | 1 | 0.7% |
| Stripe | 1 | 0.7% |
| Terraform | 1 | 0.7% |
Keywords that trigger this capability
Matched as whole words, ignoring case, in a product's name, description and repository topics.
| Keyword | Products matched |
|---|---|
| cost monitoring | 1 |
| token usage | 46 |
| token cost | 22 |
| llm cost | 50 |
| spend tracking | 1 |
| cost tracking | 32 |
| usage dashboard | 0 |
| ccusage | 0 |
Segment statistics
Whole catalogue (152 indexed products). Calculated 2026-11-21.
Lagging the catalogue. Mid-sized among capabilities, with launches growing more slowly than the catalogue’s. Size is ranked against all capabilities; momentum compares launches in the last 90 days with the 90 before, relative to the catalogue’s own ratio (62 or more = faster, 38 or less = slower; under 5 dated launches it is not measured). The HHI of 0.125 means stars are spread as if across about 8 equally popular projects — unconcentrated by the common 0.15 / 0.25 thresholds. Stars measure attention, not usage or quality.
Limits
- Classification is by the keywords above. A product that offers this capability without using one of them is not counted; one that uses a keyword in another sense is counted wrongly. Methodology
- Platform reach is protocol-level: it says a platform documents the standard, not that any product here was tested on it. Platforms named by publishers are their own claims.
- Stars belong to repositories. Products in a subfolder of a large repository show that whole repository’s stars and are excluded from the concentration figures.
- Launch counts use each source’s publication date; for auto-discovered repositories that is the repository’s creation date.
Page data last updated .