Arcee open-sources NAC, an agent harness built around 'episodes' instead of one growing transcript

Arcee AI Blog·medium signalXBlueskyLinkedInCopy link

Arcee AI released NAC under Apache-2.0 on Aug 13 (github.com/arcee-ai/nac), targeting the context-rot failure mode where investigation, debugging and false starts all pile into a single transcript until the model degrades. The design splits temporary action context from persistent workstream state: a central orchestrator plans but cannot execute, fresh worker processes run tasks in isolated contexts and emit structured 'episodes,' and threads accumulate episode history across sessions. 'Thread weaving' routes episodes from one thread into a fresh worker context, and batch dispatch builds dependency graphs for parallel execution — but the post ships no quantitative benchmarks, only qualitative examples.