Acontext vs EverOS
Skill 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. — 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.
Shared 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.
| Acontext | EverOS | |
|---|---|---|
| Stars | 3.7k | 12k |
| Forks | 334 | 901 |
| Language | JavaScript | Python |
| License | Apache-2.0 | Apache-2.0 |
| Last activity | 1 months ago | 6 days ago |
| Topics | memory, skills | memory, skills |
| Curated connections | 8 | 4 |
Acontext — the curator's take
The "memory should be legible" bet: instead of embeddings in a vector store, learnings from agent runs become Markdown skill files you can read, diff, git and mount into any framework — debuggable memory users can inspect and correct, the exact thing opaque memory layers get wrong. It can also adopt and evolve skills you wrote or downloaded. Trade-off: no semantic recall over thousands of entries; it lives or dies on distilling runs into a curated, manageable skill set. Want scale-out retrieval memory instead? That's memmachine or hindsight territory.
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.