workflowstacks
local-ai

Vigils

A local control plane for AI agents — see what they do, approve what matters, keep secrets out. Rust + Tauri + Chrome MV3.
302 stars18 forksRustUpdated 8/31/2026100% free · open source
What it does

Vigils runs a local control plane that watches AI‑agent actions, lets you approve or block them, and keeps any API keys or secrets off the network.

When to use it
  • •You’re giving internal teams access to LLM‑powered agents and need a safety‑gate before they can call external services.
  • •You want to experiment with AI agents on a laptop without exposing your OpenAI or Anthropic keys to the cloud.
  • •Your product ships a Chrome extension that talks to AI agents and you need a desktop UI to audit those calls in real‑time.
Ready-to-paste prompt
vigils approve --request-id 42   # approves the pending outbound request with ID 42 that the agent just generated
Heads up: The Chrome MV3 extension can only talk to `http://127.0.0.1` on ports that Chrome allows (default is 8080); if you change the server port you must also update the `manifest.json` `host_permissions` field, otherwise the extension will be blocked.
Saves to your device
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/vigils && curl -fsSL https://workflowstacks.com/api/skills/vigils/claude-skill -o ~/.claude/skills/vigils/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How Vigils works
Codeflow
Free to inspect

Vigils is a very large Rust project (~86k lines across 198 code files, plus 82 test files). It is a full software project: use it through its install path rather than reading it end to end. Last commit this month, Apache-2.0 license, has a test suite.

Size
Very large codebase
~86k lines · 198 code files · days to read — use, don't read
Setup
Developer setup
A real software project. Use it via its install path; don't expect to read it all.
Runs on
Rust
No API keys detected
Rust 85%JavaScript 6%Vue 4%Shell 2%TypeScript 2%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    Cargo.toml
    Dependencies and the commands it exposes
What's in each folder
apps/Sub-packages / plugins187 files
extensions/Sub-packages / plugins29 files
docs/Documentation66 files
crates/vigil-redaction/Folder832 files
crates/vigil-audit/Folder25 files
crates/vigil-mcp/Folder20 files
crates/vigil-http-auth/Folder16 files
crates/vigil-types/Folder13 files
READMEHas testsDocumentedCI checksApache-2.0 licenseUpdated this month
Quick Actions
Details
Creator
duncatzat
Language
Rust
Category
local-ai
Published
5/31/2026

Are you the creator of this tool? Claim your listing → and earn 85% of every sale.

Related skills

More local-ai tools founders pair with this one.

local-ai★ 126,617
Run LLMs with llama.cpp
Get fast LLM inference with llama.cpp, for founders using C++.
local-ai★ 91,165
Stirling-PDF: Edit PDFs Anywhere
Edit PDFs on any device with Stirling-PDF, a tool for startup founders
local-ai★ 31,165
Run AI Locally with llmfit
Find compatible AI models for your hardware with llmfit, a tool.
local-ai★ 29,040
koreader: Multi-format eBook Reader
Get a versatile eBook reader for various devices.
local-ai★ 16,018
MNN: Fast On-Device AI
Get high-performance Edge AI with MNN, battle-tested by Alibaba, for startup founders
local-ai★ 10,300
Run AI Locally with runanywhere-sdks
Run AI models on-device with this production-ready toolkit, ideal for startup founders