CalibratedDecisions.

Repo · Context & memory

Jev Lucid Memory

Research prototype of wake–sleep memory for AI agents: an LLM drafts lessons from task records, a decision model (TypeSafe Jev via the official SDK…

Open github.com ↗

From the repository

Wake–sleep memory for AI agents. Decision models such as Jev judge which lessons to retain and reuse. Research prototype with local evaluation.

agent-memoryai-agentsdecision-modelsjevllmlocal-inferencememory-consolidationpythonresearch-prototypewake-sleep

How builders describe it

Research prototype of wake–sleep memory for AI agents: an LLM drafts lessons from task records, a decision model (TypeSafe Jev via the official SDK or OpenRouter, or local Clef-Flash) judges whether each lesson is supported enough to keep and whether its conditions fit a new task, and code enforces…

The decision Jev makes

Keep or discard a tool result, or answer whether a stopping condition is met.

Where it fits

Agents drown in their own context. These projects use Jev to decide what to keep, what to drop and when a loop is actually finished. All 117 context & memory projects →

Related projects