vestige connector for Codex

Name: vestige
Author: samvallad33

CommunityConnectorSecurity

Think before doing, prove before saving. Vestige is a local, deterministic safety kernel for AI agents. Every memory write and agent action is recorded in Strata, a signed, append-only log, so you can see exactly what your agent did and why.

How to install vestige in Codex

Add it to Codex as an MCP server:

codex mcp add vestige -- vestige-mcp

Command copied from the repo README (Codex's `codex mcp add` adds an MCP server to Codex). Check the README for any API key or setup it needs. Source: repo README.

What it contains

Component list not published in a manifest we can read. See the repo README.

About this listing

vestige is a community connector on GitHub by samvallad33. Its README documents a Codex install and the repo documents a codex mcp add command. It passed the CodexStacks quality filter for repos found this way (at least 500 stars, pushed in the last 90 days, not a fork or a list). OpenAI hasn't reviewed it and we haven't tested it. It's one of 13 listings in the Security category (category assigned by CodexStacks from the repo's topics and description). It also appears in best Codex plugins for security.

vestige FAQ

How do I install vestige in Codex?

Add it as an MCP server with codex mcp add vestige -- vestige-mcp (copied from the repo README; check it for any API key or setup the server needs).

Is vestige an official Codex connector?

No. vestige is a community repo on GitHub by samvallad33. It passed the CodexStacks quality filter, but OpenAI hasn't reviewed it and we haven't tested it, so read the code before you install it.

What does vestige include?

Component list not published in a manifest we can read. See the repo README.

Details

Type: Connector
Category: Security (assigned by us)
Source: Community
Author: samvallad33
License: AGPL-3.0
GitHub stars: 650 (at last sync)
Last push: 2026-10-11
GitHub topics: agent-security, agentic-security, ai-agents, anthropic, audit-log, causal-proof-engine, claude-code, cursor, developer-tools, llm-security, local-first, mcp-security
Source: https://github.com/samvallad33/vestige
Listed via: GitHub search: README documents a Codex install
Tested by CodexStacks: Not yet

Something wrong or missing? Submit or improve this listing. Listings also refresh automatically every night.

For maintainers: badge and embeds

Maintain vestige? Add the badge; it links to this page.

Markdown

[![Listed on CodexStacks](https://codexstacks.com/badge.svg)](https://codexstacks.com/p/vestige/)

HTML

<a href="https://codexstacks.com/p/vestige/"><img src="https://codexstacks.com/badge.svg" alt="Listed on CodexStacks" width="172" height="28"></a>

Embed card (static HTML and inline CSS, no JavaScript). Preview:

vestigeCommunity Codex connectorThink before doing, prove before saving. Vestige is a local, deterministic safety kernel for AI agents. Every memory…View on CodexStacks →

<a href="https://codexstacks.com/p/vestige/" style="display:block;max-width:380px;box-sizing:border-box;padding:14px 16px;border:1px solid #3a2c26;border-radius:12px;background:#0d0b0a;color:#f3ece6;font:14px/1.45 -apple-system,Segoe UI,Roboto,Helvetica,Arial,sans-serif;text-decoration:none"><span style="display:block;font-size:16px;font-weight:700;color:#f3ece6">vestige</span><span style="display:block;margin:2px 0 8px;font-size:12px;color:#b5a9a1">Community Codex connector</span><span style="display:block;margin:0 0 10px;color:#ddd3cc">Think before doing, prove before saving. Vestige is a local, deterministic safety kernel for AI agents. Every memory…</span><span style="font-size:12px;font-weight:600;color:#ffb347">View on CodexStacks →</span></a>

Markdown summary

**[vestige on CodexStacks](https://codexstacks.com/p/vestige/)**: Community Codex connector.

More on badges, embeds and keeping your listing up to date: CodexStacks for plugin authors.

Also in Security

iFixAi

Independent Auditing of AI Agents. Run by human or the agent itself, to answer the most crucial question in the AI Agent Economy. Is the agent doing what is supposed to do? With iFixAi you can have this answer in less than 120 seconds.

CommunityPluginSecurity

Decepticon

Autonomous Hacking Agent for Red Team

CommunityConnectorSecurity

megalinter

Set up, run and fix MegaLinter on any repository: 100+ linters for 69+ languages, 23+ formats and 21+ tooling formats, from CI or locally.

CommunityPluginSecurity

maestro-orchestrate

Multi-agent orchestration platform for Gemini CLI, Claude Code, Codex, and Qwen Code — 39 specialists, parallel subagents, persistent sessions, and built-in code review, debugging, security, SEO, accessibility, and compliance tools

CommunityPluginSecurity