DEDUPED Hot AI repos, turned into use cases Get 5 a day

What you can do with Agent Safe Pipeline

AgentSafe is an open-source gateway that sits in front of an AI agent's or API's consequential HTTP requests, checks each one for authorization, and then forwards it once, holds it for a person, or refuses it, leaving chained evidence of each decision.

Trended earlier

decionis/agent-safe-pipeline on GitHub

Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk.

What do you want to do?

4 use cases

  • Test whether an agent can reach a payments API directly

    Compare direct, shadow and enforced requests before any real traffic goes through a gateway.

    View prompt
    Using the decionis/agent-safe-pipeline repository, install AgentSafe and run `agentsafe test`. Report the Exposure line and the Verdict for the boundary test against <your-api-url> if you have one, otherwise against the built-in synthetic target. Confirm the exit code is 0 before you say the boundary holds.

  • Hold high-value API calls until a person approves them

    Route consequential HTTP requests through a gateway that holds the risky ones for approval.

    View prompt
    Using the decionis/agent-safe-pipeline repository, install AgentSafe and start `agentsafe proxy --upstream <your-api-url> --port 8080`. Send one POST request to /payments through the gateway with an amount above the approval threshold, and report the decision and the HTTP status. Verify that the upstream received no request for that call.

  • Keep a chained record of every agent API action

    Print and store the evidence lines for each intent, decision and forward the gateway handles.

    View prompt
    Using the decionis/agent-safe-pipeline repository, install AgentSafe, run `agentsafe doctor`, and start `agentsafe proxy --upstream <your-api-url> --port 8080 --verbose`. Send one allowed request and one blocked request through the gateway, then list the evidence lines and dossier ids for both. Verify that each request has its own evidence line before you report back.

  • Preview what enforcement would change on live agent traffic

    Run the gateway in shadow mode and read the report of what enforcement would have held or refused.

    View prompt
    Using the decionis/agent-safe-pipeline repository, install AgentSafe and run it in shadow mode in front of <your-api-url>. After the agent has run its normal tasks, run `agentsafe status` and summarize what enforcement would have held or refused, by action. Verify that the shadow report reflects requests the agent actually sent before recommending enforcement.

How to use Agent Safe Pipeline

  1. Check you have what it needs: A terminal on macOS or Linux, with Homebrew, a Linux package, Docker or Helm available; An HTTP API or tool endpoint you want the gateway to sit in front of, or the local demo target on localhost:3000; Optional: a Decionis key from `agentsafe login`, if you want decisions from the Decionis control plane instead of the local demo authority.
  2. Open decionis/agent-safe-pipeline on GitHub and read the README and license.
  3. Install AgentSafe with Homebrew: brew tap decionis/agent-safe https://github.com/decionis/agent-safe-pipeline && brew trust decionis/agent-safe && brew install agentsafe
  4. Run the boundary test: agentsafe test
  5. Read the Exposure line and the Verdict; exit code 0 means the boundary holds and 1 means exposure.
  6. Start the gateway in shadow mode against your API, using the next-step line the test prints: agentsafe proxy --upstream <your-api-url> --mode shadow (inferred, check the README)

These steps come from our top use case, Test whether an agent can reach a payments API directly, which also has a copy-paste agent prompt.

Agent Safe Pipeline alternatives · Best AI repos for Security and science

About this repo

Requirements

  • A terminal on macOS or Linux, with Homebrew, a Linux package, Docker or Helm available
  • An HTTP API or tool endpoint you want the gateway to sit in front of, or the local demo target on localhost:3000
  • Optional: a Decionis key from `agentsafe login`, if you want decisions from the Decionis control plane instead of the local demo authority
Maintain Agent Safe Pipeline? Add the Featured on Deduped badge

Paste this into your README:

[![Featured on Deduped](https://dedupedai.com/badge/decionis-agent-safe-pipeline.svg)](https://dedupedai.com/use-cases/decionis-agent-safe-pipeline/?ref=badge)

More badge styles and HTML

Questions about Agent Safe Pipeline

What is Agent Safe Pipeline?

AgentSafe is an open-source gateway that sits in front of an AI agent's or API's consequential HTTP requests, checks each one for authorization, and then forwards it once, holds it for a person, or refuses it, leaving chained evidence of each decision. It is an open-source project on GitHub: https://github.com/decionis/agent-safe-pipeline.

Who is Agent Safe Pipeline for?

Platform, security and operations engineers who let AI agents call APIs that move money, change records or delete data, and need to control and audit those calls.

What can I do with Agent Safe Pipeline?

4 use cases so far, for example: Test whether an agent can reach a payments API directly; Hold high-value API calls until a person approves them; Keep a chained record of every agent API action. Each has steps and a copy-paste agent prompt.

What do I need to run Agent Safe Pipeline?

A terminal on macOS or Linux, with Homebrew, a Linux package, Docker or Helm available; An HTTP API or tool endpoint you want the gateway to sit in front of, or the local demo target on localhost:3000; Optional: a Decionis key from `agentsafe login`, if you want decisions from the Decionis control plane instead of the local demo authority.

What are alternatives to Agent Safe Pipeline?

Other hot AI repos in Security and science: Rea, Reverify, Ablation, Claude AD, Awesome Reverse Engineered.

Is Agent Safe Pipeline safe to run?

Deduped does not own, audit or vouch for it. Read the README and license, run it on your own systems first and review every command before you run it.