Bootstrap installer and wrapper for the Vera CLI
Project description
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.
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
vera-ai setup only configures the backend. Run vera-ai agent install to set up skill files for your agents (interactive by default, or pass --client and --scope for non-interactive use).
Usage
# Optional: install skill files for your agents
vera-ai agent install
# Index a project
vera-ai index .
# Search
vera-ai search "authentication middleware"
# Local ONNX inference (no API keys needed. downloads models automatically)
vera-ai index . --onnx-jina-cpu
vera-ai search "error handling" --onnx-jina-cpu
# Optional local CodeRankEmbed preset
vera-ai setup --code-rank-embed --onnx-jina-cuda
# GPU acceleration (NVIDIA/AMD/DirectML/CoreML/OpenVINO)
vera-ai index . --onnx-jina-cuda
# Diagnose or repair local setup issues
vera-ai doctor
vera-ai doctor --probe
vera-ai repair
vera-ai upgrade
vera-ai doctor --probe runs a deeper read-only ONNX session check. vera-ai upgrade shows the binary update plan and can apply it when the install method is known.
What you get
- 60+ languages via tree-sitter AST parsing
- Hybrid search: BM25 keyword + vector similarity, fused with Reciprocal Rank Fusion
- Cross-encoder reranking for precision
- Markdown codeblock output by default with file paths, line ranges, and optional symbol info (use
--jsonfor compact JSON,--rawfor verbose output,--timingfor step durations)
For full documentation, including custom local ONNX embedding models and manual install steps, see the GitHub repo.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file vera_ai-0.9.16.tar.gz.
File metadata
- Download URL: vera_ai-0.9.16.tar.gz
- Upload date:
- Size: 5.2 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.11.15
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
d7a9664931312b739bfd9c91344b03814b588b1a781ce26efe54f8363c8aa602
|
|
| MD5 |
2f6eb6c5e6c107d2f5d3f1aa5f665b0f
|
|
| BLAKE2b-256 |
62b50b8fabca8b6ebd16fd0d6727780f287c9221017bac1029c8ea19a58e39e3
|
File details
Details for the file vera_ai-0.9.16-py3-none-any.whl.
File metadata
- Download URL: vera_ai-0.9.16-py3-none-any.whl
- Upload date:
- Size: 5.6 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.11.15
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
5b67f71250ae72491be52e56fda946c2a91d508bc59f3e86352630710c1169c5
|
|
| MD5 |
63ed592acb44df84a06065a7ed5d45c2
|
|
| BLAKE2b-256 |
6496557c52dd3db84668a7e42606fa8d0336a2a32b02ecdaf3fd8a11bf979adc
|