StackMap
Subscribe

claude-mem vs EverOS

Cross-harness session memory: hooks capture what the agent does, an LLM compresses it into observations, and the next session gets the relevant ones back via progressive-disclosure MCP tools. — versus — One portable memory layer for every agent: conversations, files and trajectories kept as canonical Markdown, indexed locally by SQLite and LanceDB, with offline reflection that refines them.

The curated verdict

Everos keeps memory as canonical Markdown you can read, edit and git across any agent; claude-mem keeps it in SQLite + Chroma behind a worker API and web viewer. Portability and auditability versus search quality and automation.

claude-memEverOS
Stars93k12k
Forks8.1k903
LanguageJavaScriptPython
LicenseApache-2.0Apache-2.0
Last activity2 days ago2 days ago
Topicsmemory, codingmemory, skills
Curated connections78

claude-mem — the curator's take

The most widely installed of the capture-and-reinject memory plugins, and the one with the most product around it: 5 lifecycle hooks, a Bun worker with an HTTP API and live web viewer, SQLite plus FTS5 plus Chroma for hybrid search, and a 3-layer MCP search pattern (index → timeline → full detail) that keeps recall at ~50-100 tokens per hit until you actually want the body. Installs into Claude Code, OpenCode, Antigravity, OpenClaw and more, with `<private>` tags to keep things out of the store and optional cloud sync. The tradeoffs: it spends model tokens summarizing every session, it drags in Bun and uv, and what you get back is a generated observation rather than the raw transcript — if you want auditable, greppable memory you can edit by hand, look at the Markdown-first options instead.

EverOS — the curator's take

Pick it if you want memory you can open in an editor: `.md` files are the source of truth, edited directly and picked up by a cascade watcher, with SQLite plus LanceDB as disposable indexes and no MongoDB, Elasticsearch or Redis in the stack. User episodes and profile sit apart from agent cases and skills as first-class tracks, retrieval scopes orthogonally by user, agent, app, project and session, and reflection consolidates episode clusters between sessions instead of only recalling. Trade-offs: it runs as a server with its own TOML config, full capability needs embedding and rerank models configured beyond the one-key start, Markdown-as-truth means large vaults get large, and `/api/v1` is already a legacy alias.