[GitHub Trending] volcengine/OpenViking

7 relevance

Self-evolving context database for AI agents from Volcengine, directly relevant to agent memory and RAG systems.

AI/ML github.com

Answer the board on AI readiness

Arrive with evidence, not opinion. See how your foundation benchmarks against your peers, get a clear read, and leave with a ranked place to start.

Why It Matters

For engineers building AI agents, OpenViking offers a deterministic, observable alternative to opaque vector stores, cutting token costs and improving task success rates by over 10 percentage points in multi-turn agent scenarios.

Key Takeaways

Evaluate OpenViking as your agent's context layer to replace vector stores with a debuggable filesystem that reduces token consumption by up to 91% and boosts accuracy by over 30 percentage points.

Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills. - volcengine/OpenViking

Summary

OpenViking is an open-source context database for AI agents that organizes memories, resources, and skills into a virtual filesystem under the `viking://` protocol, enabling agents to browse context with `ls`, `tree`, and `find` instead of querying a black-box vector store. Content is processed into three tiers—L0 abstract, L1 overview, L2 details—and loaded on demand, with every retrieval leaving a debuggable trajectory. Benchmarks on LoCoMo and tau2-bench show accuracy gains from 24–57% to 80–83% while reducing input tokens by up to 91% and query latency by up to 66%.

Author

volcengine