Agent infrastructure · Local guardrails

Elytra

Local guardrails for coding agents. Elytra checks what Claude Code, Codex, Grok and Antigravity try to do and holds consequential actions for a person's decision before they run.

Status
Early access · Published as elytra-mcp
My role
Designed and built the agent hooks, MCP proxy, loopback runtime with its SQLite decision ledger, and the React console.
Stack
PythonMCPSQLiteReact
A coding agent reaches the Elytra runtime through hooks and an MCP proxy. The local runtime decides allow, ask, hold or block, and reports to a console and desktop notification. The MCP server keeps its own credentials.coding agentClaude Code · CodexGrok · Antigravityelytra hookelytra proxylocal runtimeSQLite ledger · permitsyour MCP serverunchanged credentialsallowaskholdblockconsole + notificationhookMCPloopback only

The problem

Coding agents run shell commands, edit files, read the web and call MCP tools on a developer's machine. Some of those actions are consequential, and an agent that has read untrusted content can be steered toward them.

Approach

  1. 1

    Classify every tool call

    Agent hooks run one short-lived process per tool call. Shell commands, file edits and web access are classified into fixed actions such as reads, installs, pushes, sends, deletes and history rewrites.

  2. 2

    Decide on the developer's machine

    A loopback-only runtime decides each call against a guardrail preset and the developer's rules: allow, ask, hold or block. An allowed call receives a single-use permit bound to its exact arguments.

  3. 3

    Remember what the session has read

    Content from outside, such as an issue, a page or an email, marks the session as untrusted for what follows. In every preset, sending data out after untrusted reads, or sending secrets, is blocked.

Results

  • Open source under Apache-2.0 and installable from PyPI as elytra-mcp, with hooks for Claude Code, Codex, Grok and Antigravity.
  • elytra explain shows how any command would be decided, and elytra uninstall restores every agent configuration exactly.
  • Documented limits: shell classification and content inspection are heuristics, and self-protection is best-effort.