bilalimamoglu/sift

Turn noisy command output into short, actionable diagnoses for AI coding agents.

36
/ 100
Emerging

Applies local heuristics to parse and group failures from test runners (pytest, vitest, jest), type checkers (tsc), linters (ESLint), and build tools before routing to an LLM—keeping most common cases deterministic and offline. Reduces noisy logs by 62% token usage and 71% tool calls in benchmarked debug loops by surfacing grouped root causes and anchors instead of raw output. Integrates as a CLI wrapper (`sift exec`), pipe consumer, or agent-native skill for Codex, Claude, and Cursor with optional fallback to OpenAI/OpenRouter endpoints for ambiguous cases.

Available on npm.

Maintenance 13 / 25
Adoption 5 / 25
Maturity 18 / 25
Community 0 / 25

How are scores calculated?

Stars

10

Forks

Language

TypeScript

License

MIT

Last pushed

Mar 18, 2026

Commits (30d)

0

Dependencies

5

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/bilalimamoglu/sift"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.