Launching today
Questlock
Reuse AI work across agents, with shared token budgets
2 followers
Reuse AI work across agents, with shared token budgets
2 followers
Why pay for the same AI work twice? Questlock helps your agents share completed work and skip another model call when a matching result is still valid. Run agents on one machine or across your own machines, with a shared token budget. Use local or hosted models, with Questlock as an independent companion to OpenRouter. Less repeated work, more room in your budget for something new. AI tool plugins available!
Hey Product Hunt! I'm Shivam, the maker of Questlock.
The problem I wanted to solve: our agents keep doing work we already paid for. Sometimes the next request only needs a checked edit. Sometimes several workers ask for the same result.
Questlock is an experimental, open-source Go library and self-hosted broker. Cooperating agents can claim work, reuse an eligible completed result and share a daily token allowance across machines. Each process bounds admission using its own CPU and memory headroom.
The mission: As teams add more agents, they can end up running the same work twice and spending their model budget on answers they already have. Questlock helps cooperating agents share completed work, reuse an eligible result and work within a shared token allowance, on one machine or across their own machines. The goal is to make the models and hardware developers already have go further.
I'd love feedback from developers running agents on their own machines: where is repeated work costing you the most?
Release and setup: https://github.com/spfuzzylink/q...
AI tool plugins available!