Vera
Active·★ 120·MIT·Updated 2026-10-14
Vera is a local-first code search tool that uses BM25, vector search, and cross-encoder reranking. It indexes over 60 languages with tree-sitter and returns structured JSON results. It runs as a single static binary with no external dependencies.
#bm25#cli#code-search#code-search-engine#cross-encoder#embeddings#local#mcp
01
Features
01Model-agnostic, local-first
02Tree-sitter structural parsing
03Structured, code-aware results
04Cross-encoder reranking
05Zero-dependency, single binary
02
Compatibility
Linux x86_64
Linux x86_64
Verified via docs
Linux aarch64
Linux ARM64
Verified via docs
macOS x86_64
macOS x86_64
Verified via docs
macOS aarch64
macOS ARM64
Verified via docs
Windows x86_64
Windows x86_64
Verified via docs
Docker
Docker
Verified via docs
03
Quick start
1
$ bunx @vera-ai/cli install
2
$ vera setup
04
Use cases
↳Semantic code search in large codebases
↳AI agent integration for automated code retrieval
↳Codebase analysis and refactoring support
05
Alternatives
coco-search★ 37
Local-first hybrid semantic code search tool. Indexes codebases into PostgreSQL with pgvector embeddings via Ollama, combines vector similarity + keyword search with RRF fusion. Supports 30+ languages. Features CLI, MCP server, WEB dashboard and interactive REPL.
codesearch★ 93
Fast, local semantic code search as MCP server for OpenCode and Claude Code. Rust-powered, fully offline.
subcog★ 29
Persistent memory system for AI coding assistants. Captures decisions, learnings, and context from coding sessions. Features hybrid search (semantic + BM25), MCP server integration, SQLite persistence with knowledge graph, and proactive memory surfacing. Written in Rust.
knowledge-rag★ 300
Drop docs, search instantly from Claude Code — 12 MCP tools, 20 format parsers, hybrid search + reranking. Zero servers, zero API keys, 100% local.
Comments
Log in to leave a comment
No comments yet. Be the first!