OpenVikingVolcengine's context database: memories, resources and skills as one `viking://` filesystem agents ls, tree and grep — L0/L1/L2 tiers, traceable retrieval, sessions distilled into memory.
Why switchBoth unify memory, files and skills into one human-readable store rather than an opaque index. OpenViking runs a `viking://` filesystem with L0/L1/L2 tiers and traceable retrieval; EverOS keeps plain Markdown as truth with local indexes and offline reflection. Filesystem metaphor versus editable files.
Full comparison → AcontextSkill memory layer for agents: auto-captures learnings from runs into plain Markdown skill files you can read, edit, git and share across frameworks — memory without an opaque store.
Why switchShared bet on Markdown-as-memory. acontext stays minimal — learnings become skill files you git and share; EverOS is a runtime with episodes, profiles, a knowledge wiki, vector indexes and background consolidation. acontext when git is enough, EverOS when you want recall infrastructure.
Full comparison → MemMachineLong-term memory layer for AI agents — episodic (graph), profile (SQL) and working memory behind Python/TS SDKs, REST and MCP; ships LangChain, LangGraph, CrewAI and LlamaIndex integrations.
Why switchSame job, opposite substrate: MemMachine puts episodic memory in a graph and profiles in SQL behind SDKs and REST; EverOS puts everything in Markdown you can edit by hand. Choose by whether memory should be a service or a folder.
Full comparison → brain.mdFile-based durable memory for coding agents: brain-setup scaffolds a BRAIN.md protocol + brain/ directory of decisions, requirements and constraints — plain Markdown in your repo, written via CLI.
Why switchBoth make a repo-visible Markdown protocol the memory. brain.md is a lightweight convention plus CLI for decisions, requirements and constraints; EverOS adds a server, vector recall and self-evolving skills on top of the same instinct.
Full comparison →