vera-ai

Code search for AI agents. Vera indexes your codebase using tree-sitter parsing and hybrid search (BM25 + vector similarity + cross-encoder reranking), then returns ranked code snippets as structured JSON.

This package downloads and wraps the native Vera binary for your platform. On musl-based Linux (Alpine, NixOS), the correct static binary is selected automatically. Set VERA_TARGET to override target detection (e.g., VERA_TARGET=x86_64-unknown-linux-musl uvx vera-ai install).

Current benchmark snapshot: on Vera's local 21-task, 4-repo release benchmark, v0.7.0 reaches 0.78 Recall@5, 0.83 Recall@10, 0.91 MRR@10, and 0.84 nDCG@10 with the local Jina CUDA ONNX stack. Full details live in the main repo docs.

Install

pip install vera-ai

Quick Start

vera-ai setup --potion-code
vera-ai index .
vera-ai search "authentication logic"

vera-ai setup with no flags runs an interactive wizard. vera-ai setup --api prompts for an OpenAI-compatible endpoint and key; use --yes with EMBEDDING_MODEL_* variables for non-interactive setup. vera-ai agent install manages skill files for your coding agents and can update AGENTS.md / CLAUDE.md style project instructions.

Common Tasks

Task	Command
Use the interactive setup wizard	`vera-ai setup`
Use CPU-only local mode	`vera-ai setup --potion-code`
Configure API mode	`vera-ai setup --api`
Use a local NVIDIA backend	`vera-ai setup --onnx-jina-cuda`
Search semantically	`vera-ai search "authentication middleware"`
Search only changed files	`vera-ai search "authentication middleware" --changed`
Common structural tasks	`vera-ai structural routes` / `vera-ai structural env DATABASE_URL` / `vera-ai structural impls Loader`
Find callers or callees	`vera-ai references foo` / `vera-ai references foo --callees`
Explain why a file is missing	`vera-ai explain-path path/to/file`
Inspect index health	`vera-ai stats --json`
Keep the index up to date	`vera-ai update .`
Watch for file changes	`vera-ai watch .`
Run local HTTP inference server	`vera-ai serve`
Diagnose setup issues	`vera-ai doctor`
Run the deeper local probe	`vera-ai doctor --probe`
Repair missing local assets	`vera-ai repair`
Inspect binary upgrades	`vera-ai upgrade`
Install agent skills	`vera-ai agent install`

For the full backend matrix, model options, Docker setup, and troubleshooting, see the main README and Installation Guide.

What you get

61+ languages via tree-sitter AST parsing
Hybrid search: BM25 keyword + vector similarity, fused with Reciprocal Rank Fusion
Cross-encoder reranking for precision
Git-aware scopes and index debugging: --changed / --since / --base, explain-path, and index health in vera-ai stats
Markdown codeblock output by default with file paths, line ranges, and optional symbol info (use --json for compact JSON; --raw works with vera-ai search, vera-ai grep, and vera-ai references; --timing works with vera-ai search and vera-ai grep, before or after the subcommand)

For full documentation, including local model options and manual install steps, see the GitHub repo.

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

vera_ai-1.0.1.tar.gz (5.9 kB view details)

Uploaded Aug 19, 2026 Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

The dropdown lists show the available interpreters, ABIs, and platforms. Enable javascript to be able to filter the list of wheel files.

vera_ai-1.0.1-py3-none-any.whl (6.4 kB view details)

Uploaded Aug 19, 2026 Python 3

File details

Details for the file vera_ai-1.0.1.tar.gz.

File metadata

Download URL: vera_ai-1.0.1.tar.gz
Upload date: Aug 19, 2026
Size: 5.9 kB
Tags: Source
Uploaded using Trusted Publishing? No
Uploaded via: twine/7.0.0 CPython/3.11.14

File hashes

Hashes for vera_ai-1.0.1.tar.gz
Algorithm	Hash digest
SHA256	`f58348fafcd5bc8f28e765c75e188c2063d110b8bb730735112ca34105edc096`
MD5	`56d76d0425e6445b84a613df644bab91`
BLAKE2b-256	`65ca3efe80d369ec0620c2648c66d93bb0a22ea86ec95a150c95c127b812d509`

See more details on using hashes here.

File details

Details for the file vera_ai-1.0.1-py3-none-any.whl.

File metadata

Download URL: vera_ai-1.0.1-py3-none-any.whl
Upload date: Aug 19, 2026
Size: 6.4 kB
Tags: Python 3
Uploaded using Trusted Publishing? No
Uploaded via: twine/7.0.0 CPython/3.11.14

File hashes

Hashes for vera_ai-1.0.1-py3-none-any.whl
Algorithm	Hash digest
SHA256	`01baec513e7ad21de129b84977bd79495bb5f4f994f5444bacd799afb0abbf21`
MD5	`4a9676b1669ac6b6bd5a667ee8594a27`
BLAKE2b-256	`3d108a1c3bad29f6b388ff573e669440360198a806d69c81d955f353b1283311`