最快的代理化搜尋基礎架構。支援 S3 原生的 ls/glob/read/grep 功能、 tree-sitter 段落、平行扇出，以及 MCP 伺服器。以 Rust 實作。
CREVIOS/agentic-search 是一個以 Rust 撰寫的高速代理化搜尋基礎架構，專為 AI 代理工具（如 Claude Code、Codex、Gemini 等）設計，提供 S3 原生的檔案系統操作，包括 ls、glob、read 與 grep。它利用 tree-sitter 進行語法感知的程式碼段落擷取，並支援平行扇出（fan-out）架構來加速大規模搜尋與讀取任務。此外，此工具可作為 MCP 伺服器運作，讓 AI 代理能透過標準化協定直接與 S3 儲存桶互動，適用於程式碼探索、日誌分析與自動化工作流程。由於其專注於效能與代理整合，非常適合需要快速檔案檢索與程式碼理解的情境。
npx skills add CREVIOS/agentic-searchInstalled? Explore more 研究與資料分析 skills: obra/superpowers, affaan-m/quarkus-verification, affaan-m/uspto-database · View all 6 →
Fastest agentic search substrate. S3-native ls/glob/read/grep with tree-sitter spans, parallel fan-out, MCP server. Rust.
Source: https://github.com/CREVIOS/agentic-search
Discovered from GitHub repositories pushed in the last 24 hours for agent skills, Claude/Codex/Gemini workflows, MCP tooling, and adjacent AI-agent automation.
Agent skill repository discovered by 10x-chat research.
Verification loop for Quarkus projects: build, static analysis, tests with coverage, security scans, native compilation, and diff review before release or PR.
USPTO patent and trademark data workflow for official record lookup, PatentSearch queries, TSDR checks, assignment data, and reproducible IP research logs.
Structured scholarly-work evaluation for papers, proposals, literature reviews, methods sections, evidence quality, citation support, and research-writing feedback.
Systematic literature-review workflow for academic, biomedical, technical, and scientific topics, including search planning, source screening, synthesis, citation checks, and evidence logging.
Evidence-first current-state research workflow for ECC. Use when the user wants fresh facts, comparisons, enrichment, or a recommendation built from current public evidence and any supplied local context.