Fetching from the wire…
01
02
03
04
05
06
07
08
OSS2026-07-28 · source-backed
27,552 stars. Memories, resources and skills stored as a virtual filesystem under a viking:// protocol that agents navigate with ls, tree and find instead of querying an opaque vector store, preserving each query's directory-browsing trajectory for debugging. Three tiers loaded on demand: L0 abstracts (~100 tokens), L1 overviews (~2k), L2 full detail. Across three agent integrations it also cuts latency 58-66%; on tau2-bench, experience memory adds ~7-12 points of success rate. Split licensing: AGPLv3 core, Apache-2.0 CLI and examples. The debuggability argument is the strongest one in agent memory right now. (GitHub)
Each link below shares sources, entities, or timing with this story.
Volcengine's OpenViking (25,259 stars) unifies memory, resources, and skills behind a filesystem paradigm, enabling hierarchical context delivery and self-evolution for agents. Source: GitHub It's climbed sharply this year and it's a major-vendor bet on "context as infrastruct...
ByteDance open-sources a context database that abandons vector storage for a "file system paradigm" — tiered context loading (L0/L1/L2), directory recursive retrieval combining filesystem positioning with semantic search. The "context-database" product category is crystallizin...
github.com/volcengine/OpenViking — Replaces flat vector storage with hierarchical filesystem paradigm. Three-tier loading reduces token consumption. Auto-extracts long-term memory from sessions. A concrete alternative to "everything is a vector."
It exposes memory, resources and skills as one virtual filesystem under a viking:// protocol, so an agent navigates its context with ls, tree and find rather than opaque similarity queries, with content tiered into L0 abstract, L1 overview and L2 detail loaded on demand. v0.4....
hindsight (15.9K stars, memory that learns from past runs), Memori (15.2K, LLM-agnostic agent-native memory), and OpenViking are all fighting over the same ground. Source: GitHub The interesting split is positioning. hindsight sells "learns from experience," Memori sells model...
29. agency-agents — GitHub 30. MiroFish — GitHub 31. Microsoft HVE-Core — GitHub 32. react-grab — GitHub 33. OpenViking — GitHub 34. page-agent — GitHub
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.