Free
Free
MIT-licensed source; no subscription, account or telemetry documented.
- Access
- MIT-licensed source; no subscription, account or telemetry documented.
AI usage observability · Official sources reviewed 2026-10-07
drip is a local Python tool that reads Claude Code and Codex CLI token logs and estimates associated water use from published coefficients. It shows low, midpoint and high estimates in a status line, live terminal meter or breakdown, with references to the assumptions behind each number.
Developers seeking an inspectable environmental estimate for their own coding-agent usage logs.
These are model-based estimates, not measured water consumption for a particular request. Provider, location and infrastructure uncertainty affect results. Python 3.11+ is required and logging support depends on the agent.
Read the repository methodology, install the local tool and confirm it finds the correct agent logs. Compare token totals with your agent history and inspect the cited coefficient range. Use the breakdown as an approximate reporting aid and state the assumptions when sharing a figure.
The project is MIT licensed, runs locally with Python standard-library dependencies and advertises no subscription. It uses existing agent logs rather than sending requests itself. Keep low/high ranges with any report and do not present the midpoint as metered environmental impact.
What it can do
Unknown is different from unavailable. Each fact carries its own evidence.
| Capability | Value | Evidence | Checked |
|---|---|---|---|
| Local logs | Reads real token counts from local coding-agent logs. | Facts sourced | 2026-10-07 |
| Estimate range | Shows low, midpoint and high estimates with research sources. | Facts sourced | 2026-10-07 |
Understand the total cost
Free
Free
MIT-licensed source; no subscription, account or telemetry documented.
cmux is a free, open-source macOS terminal built on Ghostty for multitasking with AI coding agents. It adds vertical tabs, split panes, notification rings, an in-app browser, and optional cloud VMs on paid plans for remote agent sandboxes.
Explore toolCodebuff is a terminal-native AI coding agent that indexes entire repositories in seconds and edits code or runs commands from natural-language instructions. It emphasizes deep project awareness, surgical multi-file edits, and optional pay-as-you-go credits alongside STRONG usage subscriptions.
Explore toolpre.dev is a long-horizon coding agent that plans, builds, and verifies software over extended runs in the browser or terminal. It connects to many SaaS tools, publishes previews, and sells separate RL coding tasks to AI labs through pre.dev Labs.
Explore toolThe practical questions
No. It applies published coefficients to local token counts and reports estimates with uncertainty, not per-request meter readings.
drip is a local Python tool that reads Claude Code and Codex CLI token logs and estimates associated water use from published coefficients. It shows low, midpoint and high estimates in a status line, live terminal meter or breakdown, with references to the assumptions behind each number.
MIT-licensed source; no subscription, account or telemetry documented.. This record lists ongoing free access; check the plan limits before starting.
No paid monthly price is listed; this record treats the product as free to start. See the plan cards for entitlements, billing commitments and seat minimums.
Unknown; no separately documented public product API was verified.. API access and subscription access may have different terms; consult the linked sources.
These are model-based estimates, not measured water consumption for a particular request. Provider, location and infrastructure uncertainty affect results. Python 3.11+ is required and logging support depends on the agent.
No retained pricing changes yet. A current price alone does not establish a historical trend.
Official page retrieved and editorially reviewed; no hands-on vendor application test.
Read original source ↗Facts apply to the named version and check date. Send a sourced correction if something changed.