choihyunsus/n2-arachne
Optimize AI workflows with Arachne. Automatically assembles the perfect code context (Tree, Target, Deps, Semantic) to fit context windows without noise. Built for efficiency and scale.
Implements a four-layer context assembly algorithm (tree, target, dependencies, semantic) that intelligently orders results to counteract "Lost in the Middle" bias, achieving 333x token compression on real codebases. Built as an MCP server with native performance acceleration through Rust (BM25 1.3x faster) and C++ SIMD (sqlite-vec vector search in 25ms), it integrates with Claude, Gemini, and any MCP-compatible AI provider while maintaining local-only processing via SQLite with optional Ollama semantic search.
Available on npm.
Stars
47
Forks
5
Language
JavaScript
License
—
Category
Last pushed
Mar 27, 2026
Monthly downloads
955
Commits (30d)
0
Dependencies
4
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/choihyunsus/n2-arachne"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Featured in
Related agents
agno-agi/agno
Build, run, manage agentic software at scale.
agentscope-ai/agentscope
Build and run agents you can see, understand and trust.
adaline/gateway
The only fully local production-grade Super SDK that provides a simple, unified, and powerful...
iflytek/astron-agent
Enterprise-grade, commercial-friendly agentic workflow platform for building next-generation SuperAgents.
agentuse/agentuse
🤖 AI agents on autopilot. Any model. Runs local, cron, CI/CD, or Docker.