All activity
Kevin Arhagbaleft a comment
I built TokenFence after a coding agent hit a retry loop overnight and kept calling GPT-4o until I noticed the bill. The problem: there's no native way to say "this workflow should cost no more than $2." Account-level limits exist, but nothing per-agent or per-workflow. TokenFence wraps your LLM calls with a hard dollar cap. When it's hit, you choose: kill the run or auto-downgrade to a cheaper...
TokenFencePer-workflow budget caps and kill switch for AI agents
LLM providers give you account-level limits. TokenFence gives you per-workflow limits. Set a dollar cap, pick what happens when it's hit (kill or downgrade model), add two lines of code. Works with OpenAI, Anthropic, and any provider.
TokenFencePer-workflow budget caps and kill switch for AI agents