veil social preview
agent-framework195Apache 2.0

veil

Local privacy proxy for AI coding agents. Keep PII and secrets out of LLMs with deterministic pseudonymization.

Updated Nov 13, 2026
Platforms
macos, linux, windows
Pricing
free-open-source
Status
active
License
Apache 2.0

What it does

Core capabilities at a glance

  • AI Agents
  • Data Loss Prevention
  • Data Masking
  • Data Privacy
  • Database Security
  • LLM Security
  • Local First
  • MCP

Deep dive

The full breakdown - performance, comparisons, and setup

veilLink to this section

veil is an agent framework - Local privacy proxy for AI coding agents. Keep PII and secrets out of LLMs with deterministic pseudonymization.

OverviewLink to this section

Your AI coding agent reads production-shaped data. veil makes sure the model never sees a real person.

veil is a local privacy proxy for AI coding agents such as Claude Code, Codex CLI, Aider and DeepSeek Harness. It replaces every real name, email, phone number, address, ID number and secret with a consistent pseudonym before the request leaves your machine. When the agent runs a command, queries a database or edits a file locally, veil swaps the real values back in, safely escaped. The model reasons about real bugs; it just never learns who they happened to.

The model still found the bug (invoice 293 was charged twice within the same second). Its answer came back to the developer with the real name, card number and address restored. The provider saw none of them.

veil is published on PyPI as 'veil-proxy'. It installs the 'veil' and 'veil-hook' commands, on macOS, Linux and Windows.

Keys are kept in the OS keychain: macOS Keychain, Linux Secret Service, or Windows Credential Manager. CI or containers can use 'VEIL_VAULT_KEY' / 'VEIL_TOKEN_SECRET' instead.

veil is open-source, written primarily in Python, with 195 GitHub stars under the Apache 2.0 license. It was last updated on 2026-10-31.

Key capabilitiesLink to this section

From the project's documentation:

  • Finds the project's data:
  • database URLs in .env files (DATABASE_URL, REDIS_URL, MONGODB_URI, …);
  • SQLite files and fixture folders;
  • the git history (contributors);
  • personal fields declared in code (Prisma, Django, Rails, SQLAlchemy, OpenAPI, protobuf).
  • Seeds veil with the real values, and remembers the sources (encrypted) so it re-seeds them when

InstallLink to this section

A quick way to get started (always check the official docs for the latest):

pip install veil-proxy # core: httpx, cryptography, pyahocorasick

How it fits a local-AI stackLink to this section

veil runs on your own hardware, so pair it with a model and a GPU sized to your needs. Use the VRAM calculator to pick a model that fits your card, and see what you can run for hardware guidance. Related agent frameworks in the directory:

SourcesLink to this section

Stats from GitHub, 2026-11-13.

Frequently asked

Quick answers to common questions

What is veil?

veil is a agent-framework tool for local AI workloads. Local privacy proxy for AI coding agents. Keep PII and secrets out of LLMs with deterministic pseudonymization.

Is veil free and open source?

Yes, veil has 195 GitHub stars and is licensed under Apache 2.0. You can self-host it for free on macos, linux, windows.

What platforms does veil support?

veil runs on macos, linux, windows.

What hardware do I need for veil?

The hardware requirements depend on which models you run. Check our hardware directory for compatible GPUs and systems. veil has 195 GitHub stars and an active community.

Does veil support GPU acceleration?

veil supports GPU acceleration via CUDA, Metal, or Vulkan depending on your platform. For the best performance, pair it with an NVIDIA RTX 4090 or 5090.

What are the best alternatives to veil?

Popular alternatives include other agent-framework tools in our directory. Browse our full collection at /tool for comparisons, community reviews, and benchmark data to find the right fit for your workflow.

How much does veil cost?

veil is free-open-source. It is completely free and open source to self-host.

Pairs well with

Complementary tools, models, and hardware