S
SiftrCode v0.1.1

Cut agent token waste by 90%

Our proprietary synthesis engine strips implementation bloat into clean interfaces before inference.

Demo:
user_service.ts
Step 1: Raw Code |
Context:
2,420 tokens ($72.60)
➔
2,420 tokens ($72.60)

Works with Claude Code & Cursor

Select your coding agent and LLM model to view instant setup commands and real-world token savings.

Model:

Connect to Claude Code

• Guide →

Registers SiftrCode's Stdio MCP server to prune code before Claude reads it.

$ claude mcp add siftrcode -- npx -y siftrcode mcp
Token Economics
Claude 3.7 Sonnet: $3.00/MTok in • $15.00/MTok out
Context -92.2% Evaporated
125,000 tok 9,800 tok
Query Cost Save $0.346 / query
$0.375 $0.029
Monthly Dev Savings Save ~$4,750 / yr
50 turns/day +$396/dev
Based on 50 agent turns/day • 11x faster latency (3.4s vs 38s)
Calculate exact waste:
npx siftrcode audit

Simple Licensing

Free open-source CLI for individuals. Paid caching for teams.

OPEN SOURCE
INDIVIDUAL DEVELOPERS

Community CLI

$0 Free forever (MIT)
  • ✔ Local AST Pruning (TS, Py, Go, Rust)
  • ✔ Codebase Auditor (siftrcode audit)
  • ✔ Context Packer (siftrcode pack)
  • ✔ Stdio MCP Server integration
GitHub Repository →
TEAM PRO
FOR STARTUPS & TEAMS

SiftrCode Pro

$19 / seat / mo
  • ✔ Everything in Community CLI
  • ✔ TypeSafe Jev Cloud Relevance Gate
  • ✔ Team Cross-Repo Context Cache
  • ✔ CI/CD Pull Request Context Auditor