Run your agent's non-urgent LLM tasks at the cleanest grid hour.
US data centers are projected to reach 6.7–12 % of national grid load by 2028 (DOE 2024), driven primarily by AI compute. Tidegap is an open-source MCP scheduler that defers non-urgent LLM tasks to off-peak hours — 50 % cheaper via Anthropic/OpenAI Batch APIs, and lower carbon. Per-task receipts to a local SQLite ledger. Apache-2.0.
50% cheaper: projected, Batch-API list price. Lower carbon: the saving depends on region and day. See docs/claims.md.
Built by Vitalii Borovyk, independent and open source. See the GitHub repo or read more about the project.
install — 30 seconds
One line. Any host.
Paste the prompt below into your agent. It detects the host (Claude Code, Cursor, Claude Desktop, Windsurf, Continue, Cline, Zed, Goose, OpenClaw, or any generic MCP host) and runs the right install path for you.
Please install Tidegap — open-source carbon-aware MCP scheduler, Apache-2.0.
Instructions: https://www.tidegap.com/install.md
Read that file, then run the install path for whichever host
you're in and confirm it worked.install it yourself
Pick your host below and copy the command. Default is the universal MCP install; switch the dropdown for host-specific configs or to use the library directly.
Universal — add tidegap-mcp to any host that speaks Model Context Protocol.
npx -y @tidegap/mcpthen Wire this into your host's MCP config (the snippets for specific hosts are in the dropdown).
Once installed, your assistant can call /tidegap:defer "summarize this" --by tomorrow 6pm and the task lands at the cleanest grid hour inside the deadline. See all commands →
how it works
One scheduled task, four parallel wins.
A task arrives while the grid is at peak — dirty, strained, expensive. Tidegap rides it down the carbon curve and dispatches it at the clean off-peak trough. From that one dispatch, four wins flow out at once — carbon, cost, latency and grid load — because they all track the same thing: grid demand.
Carbon
Lower
vs dispatching at peak
Cost
−50%
Batch window (projected)
Latency
Faster
off-peak capacity
Grid load
−84%
time-shifted (simulated)
Illustrative — the loop shows the mechanism, not live data. A deferrable task waits through the dirty, strained peak and is dispatched at the off-peak trough inside its deadline. Carbon, cost and latency move together because they all track grid demand; exact figures vary per region per day. Cost and grid-load figures are labelled projected/simulated above; sources in docs/claims.md.
dashboard
Live data + tools.
Live carbon map
Grid regions across North America, Europe and Asia-Pacific, real-time data. Click any region for the 72-hour forecast.
Plan a task
Pick a region + deadline. See the cleanest hour and the carbon you'd save vs running now.
My impact
Personal carbon-receipt summary from your local Tidegap queue. CLI-parity in the browser.
Docs & commands
All 8 /tidegap:* slash commands, 10 MCP tools, install matrix for every host. Architecture deep-dive.
- grid regions
- 31
- live carbon feeds
- 5
- carbon forecast
- 72h
- intensity bands
- 5
Measured directly from the code — see docs/claims.md.