AI Decision System
Replayable, offline-verifiable records for AI-assisted go/no-go decisions: experiment promotions, typed model answers and human-approved actions.
A RETE rules engine that enforces project conventions from disk, outside the LLM context window. Trajectory predicates use a durable journal, while advisory confidence rules ground Git mutations in co
Developer toolsRust · HTMLGitHub @awatermaOnlineOwner unconfirmed
Have you tried it? One tap is enough. No sign-in needed.
A RETE rules engine for durable enforcement of project conventions in LLM-assisted work.
Translation pending
Taken from the repository README
Loading the full README. The saved excerpt is shown below.
Practical wisdom for LLM-assisted work. Phronesis (φρόνησις) is a domain-neutral RETE rules engine designed to provide durable, deterministic governance for non-deterministic AI agents. It addresses the "contextual drift" that occurs in long-running LLM sessions, where project-specific guidance (like CLAUDE.md) slowly fades as the context window fills and auto-compaction triggers. Rules in Phronesis live on disk, are evaluated by lightweight hooks at the moment of action, and fire the same in token nine hundred thousand as they do in token eight hundred.Read the full README ↗
The full README is unavailable right now. Read it at the original link. The saved excerpt is shown below.
Practical wisdom for LLM-assisted work. Phronesis (φρόνησις) is a domain-neutral RETE rules engine designed to provide durable, deterministic governance for non-deterministic AI agents. It addresses the "contextual drift" that occurs in long-running LLM sessions, where project-specific guidance (like CLAUDE.md) slowly fades as the context window fills and auto-compaction triggers. Rules in Phronesis live on disk, are evaluated by lightweight hooks at the moment of action, and fire the same in token nine hundred thousand as they do in token eight hundred.Read the full README ↗