AI Engineering

Distill Memory saves key decisions, procedures, learnings, preferences, and plans as durable memories. Use it when something non-obvious is discovered or a significant choice is made so future sessions can find it again.

Distill Memory recognizes durable decisions, lessons, and breakthrough insights during conversations and suggests saving them at the right moment. Use it when a resolution, preference, or procedure is worth preserving for future reference.

Dueling Autoresearch runs two different approaches against the same metric in parallel and keeps a shared scoreboard. Use it when you want an analysis-first head-to-head between lanes such as classical versus learned methods.

Exploratory Autoresearch runs an autonomous ML research loop that alternates analysis with scheduled swings, merges, and exploits. It is used for open-ended experiments where you want broad exploration first and a stagnation guard to prevent getting stuck in small-step tuning.

Hypothesis Generation Loop generates candidate research hypotheses and vets them against retrieved literature. Use it when you need a ranked pool of novel, testable hypotheses rather than a single research question or a proposal review.

Karpathy Autoresearch runs a fully autonomous loop that edits training code, executes the run, and keeps changes only when a single scalar metric improves. Use it for hands-off ML experimentation where the agent loops until interrupted.

Literature Search provides a shared CLI for discovering papers, checking novelty, searching full text, and walking citation graphs. Use it when a loop needs scholarly literature or experimental-result extraction and should fall back cleanly to web search if needed.

ML Autoresearch Loop runs an autonomous machine learning research cycle where each experiment is analyzed before the next change is made. Use it for open-ended model improvement with one change per run, optionally grounded in literature.

Nowledge Mem provides external memory for Alma, including startup context, broad and focused recall, thread history lookup, and durable memory saves. Use it when a conversation depends on prior decisions, preferences, or stored project facts.

Nowledge Mem manages cross-tool session memory for Amp. Use it to load context at startup, search prior decisions and threads, and save durable insights or session summaries.

Nowledge Mem helps you resume work with startup context, search past threads and memories, and save durable knowledge. Use it when you need exact prior decisions, preferences, or CodeBuddy transcript imports.

Nowledge Mem For OpenClaw guides installing and configuring the OpenClaw plugin so it can use shared memory from local or remote Nowledge Mem backends. Use it to verify access, set plugin options, and confirm the memory slot is wired correctly.