Quoracle actually does something interesting: it queries a pool of models and only executes actions they agree on, while letting agents spawn children and persist full state to Postgres — all visible in a LiveView dashboard. The per-model conversation history, recursive hierarchy, and explicit consensus pipeline are clever touches; it’s clearly aimed at experimentation rather than drop-in production use (the README even flags security and deployment caveats).

WizardryNiche Gem

shelvick

214mo ago

AI/ML●●Solid

Forage – MCP server that lets AI agents find and install their own MCPs

Forage proxies MCP capability discovery so an agent can search registries, install a package as a child process, emit list_changed so the agent picks the tool up immediately, and even write usage notes to CLAUDE.md for future sessions. That operational pattern — dynamic install + instant availability + persisted learnings — is a clever, pragmatic fix for brittle agent setups, though the project is clearly early and raises real security/trust questions around auto-installing third-party MCPs (user approval is noted but sandboxing/attestation will matter).

Big BrainShip It

DoomedWheel1027

114mo ago