ByteDance's OpenViking Turns Agent Memory Into a Browsable Filesystem — LoCoMo Accuracy 24–57% → 80–83% With 34–91% Fewer Input Tokens

GitHub·high signalXBlueskyLinkedInCopy link

volcengine/OpenViking (27,552 stars, v0.3.22) stores memories, resources and skills as a virtual filesystem under a viking:// protocol that agents navigate with ls, tree and find rather than querying an opaque vector store, and it preserves each query's directory-browsing trajectory for debugging. Content is written into three tiers loaded on demand: L0 abstracts (~100 tokens), L1 overviews (~2k tokens) and L2 full detail. Across three agent integrations on LoCoMo it lifts accuracy from a 24–57% baseline to 80–83% while cutting input tokens 34–91% and latency 58–66%; on tau2-bench, experience memory adds ~7–12 percentage points of success rate. Licensing is split: AGPLv3 for the core, Apache-2.0 for CLI and examples.