open_budgetOpen a hard budget for one agent run before it starts: max dollars, tokens, calls and/or wall-clock seconds. Returns a handle.
MCP · live · free 500/day
One runaway loop can eat a day of credits. Cap the run, not the month.
A hard spending cap for one AI agent run, shared by every sub-agent. Your agent checks before each model or tool call and gets a clear STOP when the run hits its dollar, token, call or time limit. Free 500 checks a day, then $9 a month.
Works with ClaudeCodexChatGPTGrok Bot· bring your own model
open
Budget open: $2. Call reserve with this handle before every model or tool call, and pass it to sub-agents.
run cap (USD)2
remaining (USD)2
statusopen
next stepreserve({handle, usd|tokens|calls}) before each call; stop when allowed=false.
checked2026-10-15 13:53 UTC (prerendered; Run for live)
Tools your agent gets
Each result includes understood, job, and a one-line outcome, so your agent can confirm and report back in plain words.
reserveCall BEFORE each model call, tool call or sub-agent spawn with your estimate. Returns allowed=true and deducts it, or allowed=false with the limit that tripped.
recordAfter a call, report the actual usage minus what you reserved (positive if it cost more, negative to give back an overestimate). Keeps the ledger honest without blocking.
budget_statusSee spend vs limits, remaining budget, whether the run is stopped and why, and the last 20 ledger events. Set close=true when the run finishes.
usage_and_upgradeUsage today + upgrade link (not metered).
Free first. Pro when it matters.
The free tier resets every day. It is not a trial. Upgrade when your agents need volume.
01
Just call it
No signup. 500 calls a day per IP over MCP or REST.
$0
02
Free API key
A stable identity for your agent with the same 500/day. One click, no email.
03
Pro
50,000 calls a day. After you pay, you get your key immediately. Cancel anytime.
$9/month
FAQ
What problem does this solve?
Agent loops and sub-agent forks can burn millions of tokens in one run before anyone notices. Provider caps are monthly or org-wide, and SDKs report usage after the run. Run Budget Guard gives one run a hard cap that every sub-agent shares, checked before each call.
How does my agent use it?
Call open_budget at the start with max_usd, max_tokens, max_calls and/or max_seconds. Before every model call, tool call or sub-agent spawn, call reserve with your estimate. If allowed is false, stop and return the partial result. Optionally call record with the actual usage to keep the ledger exact.
Does it work across sub-agents running in parallel?
Yes. Pass the handle to each sub-agent. Every reserve is an atomic check-and-deduct on one ledger row, so eight parallel calls against a cap of five calls allow exactly five.
Who estimates the cost?
Your agent does. Run Budget Guard does not see your prompts or proxy your model traffic; it only counts the numbers you send. Use your provider's published prices for the estimate and record to correct it.
What happens when a limit trips?
The run is marked stopped with the reason (max_usd, max_tokens, max_calls, max_seconds) and every later reserve returns allowed=false, so a looping agent cannot creep past the cap. Open a new budget to continue.
What does it cost?
Free: 500 checks a day, 10 open runs, handles last 24 hours. Pro is $9 a month: 50,000 checks a day, 200 open runs, handles last up to 7 days. You get your Pro key on screen right after paying.
Connect in one line
Remote MCP over streamable HTTP. Claude Code:
claude mcp add --transport http run-budget-guard https://budget.botrecipe.com/mcp
MCP URL https://budget.botrecipe.com/mcp
REST POST https://budget.botrecipe.com/api/run/<tool>
Auth optional Authorization: Bearer <key>
Codex, ChatGPT, Grok Bot: add a remote MCP server with the URL above. Skill file: SKILL.md · catalog entry: tool.json