{"categories":[{"label":"Artificial Intelligence","url":"https://skillfed.io/packages/category/scientific-engineering-artificial-intelligence/5"}],"enrichment":{"capability":"OpenViking is a context database for AI agents that organizes memories, resources, and skills as a virtual filesystem under the `viking://` protocol, with tiered content loading (abstract, overview, details) and observable retrieval trajectories.","skillfed_tags":["agent-memory","context-retrieval","filesystem-interface"],"use_cases":["Build AI agents with persistent, searchable memory that survives across sessions and reduces token consumption on long conversations.","Ingest and organize technical documentation, code repositories, and web content as agent-accessible context with semantic search.","Debug agent retrieval behavior by inspecting the directory-browsing trajectory that produced each result.","Integrate OpenViking recall into existing agent frameworks via provided plugins and integrations.","Extract and store agent experience and user preferences as long-term memory after multi-turn sessions."],"what_it_does":"OpenViking is an open-source context database designed for AI agents that replaces traditional vector stores with a filesystem-like interface. Instead of querying a black-box retrieval system, agents browse context using familiar commands (`ls`, `tree`, `find`, `grep`) on a `viking://` protocol namespace. Content is processed into three layers on write\u2014L0 (abstract, ~100 tokens), L1 (overview, ~2k tokens), and L2 (full details)\u2014and loaded on demand to reduce token spend and latency.\n\nThe package includes a server component, a CLI client, and integrations for popular AI agents. It supports ingesting resources from URLs, GitHub repos, and local files, then automatically extracts and commits session memory after agent interactions. Retrieval is observable: each query preserves its directory-browsing trajectory so you can debug why a result was retrieved. The fact sheet shows benchmarks reporting 80\u201383% accuracy on user memory tasks with 34.3\u201391.0% reduction in input tokens and 58.45\u201366.10% latency improvement.","worth_installing":"Yes, with conditions. OpenViking is actively maintained with recent releases and solves a real problem for AI agent developers\u2014observable, token-efficient context retrieval. However, the AGPL-3.0 license requires copyleft compliance in derivative works, and the 58 runtime dependencies create medium install friction. Install if you are building agents that need persistent, debuggable memory and can accept the license terms; avoid if you need a permissive-licensed context store or want minimal dependencies."},"id":"openviking","links":{"html":"https://skillfed.io/packages/openviking","md":"https://skillfed.io/packages/openviking.md","pypi":"https://pypi.org/project/openviking/"},"maintenance":{"status":"active"},"meta":{"latest_release":"2026-08-06","license_spdx":"AGPL-3.0","license_treatment":"agpl","name":"openviking","python_support":"supports_current","summary":"An Agent-native context database"},"popularity":{"monthly_downloads":400754,"position":6935,"tier":"top_15000"},"security":{"n_vulnerabilities":0},"version":"0.4.13"}