context-mode vs leviathan
Local plugin for 10 coding agents that runs tool calls in a sandbox, indexes full output in SQLite FTS5 and returns only what the agent asks for — ~99% fewer bytes in context, zero telemetry. — versus — Single Rust binary that turns JSONL, CSV, SQLite or any DB export into a ranked full-text index, giving agents short cited answer cards (~450 tokens) at any dataset size.
Both index big text into a local store so the agent fetches small relevant slices. context-mode indexes tool output; Leviathan indexes your datasets.
| context-mode | leviathan | |
|---|---|---|
| Stars | 34k | 879 |
| Forks | 2.3k | 53 |
| Language | JavaScript | Rust |
| License | NOASSERTION | Apache-2.0 |
| Last activity | yesterday | 4 days ago |
| Topics | coding, local | memory, data |
| Curated connections | 6 | 3 |
context-mode — the curator's take
Use it when long sessions die from tool-output bloat (logs, test runs, fetched pages) and you want the agent to search output rather than read it, across Claude Code, Codex, OpenCode and more. Skip it if you need an OSI license (it's ELv2, source-available) or your agent rarely produces large outputs; the hosted Gateway is a separate paid product, not needed for the plugin.
leviathan — the curator's take
Use it when an agent has to answer questions over large record dumps, like tickets, logs or CRM exports, and grep is flooding the context. The benchmark claims 245x fewer tokens than the best grep strategy. Skip it if you need semantic or vector recall: it is lexical full-text search. It is not a memory system that learns from conversations; you re-index when the data changes.