trending

1d ago

Conduit - Fix the tool-list bloat slowing your AI agent

Your agent got slower the more MCP servers you added, and it's not the model. Every server dumps its whole tool list into context on every request: 3 servers cost ~24k tokens before you even say hi. Conduit puts them behind one local gateway that exposes 3 meta-tools the agent searches on demand. Measured: 97% less tool overhead per request, ~90% fewer tokens, same task success. Cloud or local, one tool or five. Keys in your OS keychain. Free and open source.