⬢github Rust · 652 ★ +21 since we first saw it · pushed 1 d ago · Apache-2.0
elstongun/leviathan
**Deep memory for agents over large datasets.** Leviathan is a single static binary that turns your records (JSONL, JSON, CSV/TSV, SQLite, or anything a database CLI can export) into a ranked full-text index.
Leviathan is a single static Rust binary that turns records — JSONL, JSON, CSV/TSV, SQLite, or database CLI output — into a ranked full-text index. AI agents query it in plain language and get short, cited result cards (~450 tokens per answer), with filtering, date ranges, and group-scoped search. The index is one SQLite file with no runtime dependencies.
Why now: Trending as a new, most-starred repo, driven by benchmark comparisons claiming ~245× fewer tokens per question than grep-based strategies at 1M records.
Who it is for: Developers building LLM agents that need to search large structured datasets without dumping raw records into context.
Stars over our 44 snapshots: 631 to 652, since 10 h ago.
Where people talked about it
- ⬢github new repos, most starred 14 min ago
API: https://socialmediatrends-api.osmike.com/v1/repos/elstongun/leviathan