About this listing
Product and access model reviewed from current official sources; workflow and example are editorial suggestions, not a hands-on test.
Official sourceOpen-source local guardrail that checks AI coding agent tool calls, secret reads, MCP use and package installs before they run.
Best suited to
HOL Guard is for developers who let agents such as Claude Code, Codex or Cursor run commands on their machine.
HOL Guard is for developers who let agents such as Claude Code, Codex or Cursor run commands on their machine. It evaluates supported tool calls before they run and can allow, ask for approval or block them, covering secret access, destructive commands, risky MCP configuration and malicious packages. Receipts record what happened.
This example describes a task, not a tested output. Adjust the source material and settings to your own situation.
Block reads of .env files and unknown package installs, but ask before running shell commands in a new repository.
Result check: Check the coverage matrix for your agent, because enforcement depth varies by agent and event type, and test that a blocked action is really blocked.
Guard Local is free, open source under Apache-2.0 and runs on your machine without a cloud account. Optional Guard Cloud adds synced decision history and shared policy: Solo at $4.99, Pro at $15 and Team at $30, with Enterprise by quote, and the billing period is not stated on the page. The site does not list supported operating systems, so check its install page for yours.
Allow, ask or block decisions before tool calls run
Covers shell commands, secret and .env access, MCP calls and package installs
Works with Codex, Claude Code, Cursor, OpenCode and other agents
Runs locally and offline
Security receipts for each decision
Optional Guard Cloud for shared policy
Guard Local is free, open source under Apache-2.0 and runs on your machine without a cloud account. Optional Guard Cloud adds synced decision history and shared policy: Solo at $4.99, Pro at $15 and Team at $30, with Enterprise by quote, and the billing period is not stated on the page. The site does not list supported operating systems, so check its install page for yours.
Plan information can change. Prices and conditions are set by the provider. Information checked 2026-10-17.
Source for access detailsOne email a week with pricing and feature changes in this category. No per-tool price alerts.
By subscribing you agree to receive this email from Genius Forges and to us storing your address to send it. We may ask you to confirm by email. Every email has an unsubscribe link. See our privacy policy.
HOL Guard is for developers who let agents such as Claude Code, Codex or Cursor run commands on their machine. It evaluates supported tool calls before they run and can allow, ask for approval or block them, covering secret access, destructive commands, risky MCP configuration and malicious packages. Receipts record what happened.
Guard Local is free, open source under Apache-2.0 and runs on your machine without a cloud account. Optional Guard Cloud adds synced decision history and shared policy: Solo at $4.99, Pro at $15 and Team at $30, with Enterprise by quote, and the billing period is not stated on the page. The site does not list supported operating systems, so check its install page for yours.
Install Guard for one agent you already use. Run its risk check on your current setup.
Check the coverage matrix for your agent, because enforcement depth varies by agent and event type, and test that a blocked action is really blocked.
Tell us what needs improving. No account or private output required.
Report incorrect information or a broken linkDocumentation-based review · 2026-10-17
Reviewed from the linked official pages. The workflow and example are editorial suggestions; no account-level product test or measured performance comparison was performed.
Backend for coding agents: model access, user login, Postgres and file storage under one project key, with a $0 starter.
Best for: Vectoree is for developers and teams whose coding agents, such as Cursor, Claude Code or Codex, build apps that need a backend.
Free 14-minute unassisted coding diagnostic for JavaScript, TypeScript and Python, with paid practice drills for debugging and tracing.
Best for: Unrust is for developers who want to measure their own unassisted coding after leaning on AI assistants.
General AI agent for in-depth research, websites, slides and wide multi-item research, with credit-based plans from $20 a month.
Best for: Manus suits people who want to hand a multi-step task to an agent and get a finished piece of work back, such as a research summary, a website or a slide deck.
On Product Hunt
External community signal. Not our editorial ranking.