This product was not featured by Product Hunt yet. It will not be visible on their landing page and won't be ranked (cannot win product of the day regardless of upvotes).
Free, open-source execution control for AI agents. Gate connected tool calls with policy, short-lived leases, one-use approvals and operator revocation. Build in with Rust or bolt on through HTTP/MCP. Includes captioned demos and local evaluation guides.
I built DeadBolt because I wanted a concrete place to enforce permission immediately before an agent's tool call changes something.
The trusted executor checks the gate and starts the protected action only after a fresh explicit allow. Developers can build it in with Rust or bolt on a local HTTP sidecar or trusted stdio MCP proxy. It is free under Apache-2.0.
Stable v1.0.3 is available. The published v1.1.0-rc.1 prerelease adds scoped workload credentials, exact-action approval and an installable Python client with an optional OpenAI Agents SDK integration.
The first evaluation uses harmless temporary files and needs no AI account. I would value reports from developers trying it outside this project: what worked, what failed, and which integration was hard to understand.
It protects the routes you connect to it; it is not a whole-agent sandbox and cannot cancel an action already running. The captioned videos show real Harness tool dispatch using a deterministic local demo provider. Narration is AI-generated.
Built by NextEleven.
No comment highlights available yet. Please check back later!
About DeadBolt on Product Hunt
“Give agents tools. Keep control.”
DeadBolt was submitted on Product Hunt and earned 0 upvotes and 1 comments, placing #6 on the daily leaderboard. Free, open-source execution control for AI agents. Gate connected tool calls with policy, short-lived leases, one-use approvals and operator revocation. Build in with Rust or bolt on through HTTP/MCP. Includes captioned demos and local evaluation guides.
DeadBolt was featured in Developer Tools (521.5k followers), Artificial Intelligence (481.6k followers) and GitHub (41.4k followers) on Product Hunt. Together, these topics include over 252.2k products, making this a competitive space to launch in.
Who hunted DeadBolt?
DeadBolt was hunted by Sean McDonnell. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
Want to see how DeadBolt stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
Sean McDonnell