convez.ai
MCP ServerDevOps & InfraestruturaIntermediário
cognis-digital

TokenMeter

cognis-digital/tokenmeter

Controle de custos de LLM com análise de tokens e orçamento CI-ready

Ver no GitHub
BomPluginScore · de 0 a 100

Contador e orçador de tokens para aplicações LLM, pronto para CI/CD e MCP-nativo. Escaneia projetos, estima custos de API, aplica limites de orçamento e integra em pipelines de automação com saídas em tabela, JSON ou SARIF.

Instalação

$npx convez-ai cognis-digital/tokenmeter

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
1
Forks
0
Acompanhando
0
Saúde
100%
Último commit
há 3 meses
Versão
walkthrough-v1
Issues abertas
5
Contribuidores
1

Casos de uso

  • Monitorar custos de tokens em aplicações que usam APIs de IA
  • Implementar gates de orçamento em pipelines CI/CD
  • Auditar e priorizar achados de consumo de tokens em projetos
  • Integrar análise de custos em agentes IA via MCP

Veredito

Ferramenta sólida e focada para equipes que precisam controlar custos de LLM em produção. Integração MCP nativa e suporte a CI/CD a tornam prática para automação; documentação clara e funcionalidades bem-definidas (scan, budget, aggregate) sem overhead.

README

A tradução para o português deste README ainda está na fila.

TOKENMETER

Token and cost counter / budgeter for LLM apps, CI-ready

PyPI CI License: COCL 1.0 Suite

Developer Tools — fast, single-purpose, CI- and agent-friendly.

pip install cognis-tokenmeter
tokenmeter scan .            # → prioritized findings in seconds

Contents

Why tokenmeter?

AI cost control

tokenmeter is single-purpose, scriptable, and self-hostable: point it at a target, get prioritized results in the format your workflow already speaks (table · JSON · SARIF), gate CI on it, and let agents drive it over MCP.

Features

  • ✅ Add Model
  • ✅ Get Pricing
  • ✅ List Models
  • ✅ Count Tokens
  • ✅ Estimate
  • ✅ Check Budget
  • ✅ Aggregate
  • ✅ Runs on Linux/macOS/Windows · Docker · devcontainer
  • ✅ Ports in Python, JavaScript, Go, and Rust (ports/)

Quick start

pip install cognis-tokenmeter
tokenmeter --version
tokenmeter scan .                       # scan current project
tokenmeter scan . --format json         # machine-readable
tokenmeter scan . --fail-on high        # CI gate (non-zero exit)

Example

$ tokenmeter scan .
  [HIGH    ] TOK-001  example finding             (./src/app.py)
  [MEDIUM  ] TOK-002  another signal              (./config.yaml)

  2 findings · risk score 5 · 38ms

Architecture

flowchart LR
  A[Input: file / dir / API] --> B[Collectors]
  B --> C[Rules / Analyzers]
  C --> D[Scorer]
  D --> E{Reporters}
  E --> F[Table]
  E --> G[JSON / SARIF]
  E --> H[MCP tool -. drives .-> AI agents]

Use it from any AI stack

tokenmeter is interoperable with every popular way of using AI:

  • MCP server — tokenmeter mcp (Claude Desktop, Cursor, Cognis.Studio, uncensored-fleet)
  • OpenAI-compatible / JSON — pipe tokenmeter scan . --format json into any agent or LLM
  • LangChain · CrewAI · AutoGen · LlamaIndex — wrap the CLI/JSON as a tool in one line
  • CI / scripts — exit codes + SARIF for non-AI pipelines

How it compares

Cognis tokenmetertiktoken
Self-hostable, no account✅varies
Single command, zero config✅⚠️
JSON + SARIF for CI✅varies
MCP-native (AI agents)✅❌
Polyglot ports (JS/Go/Rust)✅❌
Open license✅ COCLvaries

Built in the spirit of tiktoken, re-framed the Cognis way. Missing a credit? Open a PR.

Integrations

Pipes into your stack: SARIF for code-scanning, JSON for anything, an MCP server (tokenmeter mcp) for AI agents, and a webhook forwarder for SIEM/Slack/Jira. See docs/INTEGRATIONS.md.

Install — every way, every platform

pip install "git+https://github.com/cognis-digital/tokenmeter.git"    # pip (works today)
pipx install "git+https://github.com/cognis-digital/tokenmeter.git"   # isolated CLI
uv tool install "git+https://github.com/cognis-digital/tokenmeter.git" # uv
pip install cognis-tokenmeter                                          # PyPI (when published)
docker run --rm ghcr.io/cognis-digital/tokenmeter:latest --help        # Docker
brew install cognis-digital/tap/tokenmeter                             # Homebrew tap
curl -fsSL https://raw.githubusercontent.com/cognis-digital/tokenmeter/main/install.sh | sh
LinuxmacOSWindowsDockerCloud
scripts/setup-linux.shscripts/setup-macos.shscripts/setup-windows.ps1docker run ghcr.io/cognis-digital/tokenmeterDEPLOY.md (AWS/Azure/GCP/k8s)

Related Cognis tools

  • mcpforge — Scaffold, test, and publish MCP servers in minutes
  • promptlint — Lint, version, and test prompts as code with a CI gate
  • envdoctor — .env validator, secret-presence and config-drift checker
  • apidiff — Breaking-change detector for OpenAPI / GraphQL across commits
  • codeglance — Repo onboarding map — architecture + hotspots for humans and agents
  • flakefinder — Flaky-test detector from CI history with quarantine suggestions

Explore the suite → 🗂️ all 170+ tools · ⭐ awesome-cognis · 🔗 cognis-sources · 🤖 uncensored-fleet · 🧠 hermes

Contributing

PRs, new rules, and demo scenarios are welcome under the collaboration-pull model — see CONTRIBUTING.md and SECURITY.md.

⭐ If tokenmeter saved you time, star it — it genuinely helps others find it.

License

Source-available under the Cognis Open Collaboration License (COCL) v1.0 — free for personal, internal-evaluation, research, and educational use; commercial / production use requires a license (licensing@cognis.digital). See LICENSE.


Ver o original no GitHub

Bom para

Relacionados