Cordum

A source-available control plane that enforces policy and requires human approval before an AI agent's risky tool calls, shell commands, workflows or production changes, keeping an auditable record of what was approved.

Visit website github.com

Cordum stands up an API gateway, a scheduler, a safety kernel, a workflow engine, a context engine, a dashboard, NATS and TLS-secured Redis with one command, generating secrets and certificates and running a post-deploy smoke test that exercises a real approval workflow. Cordum Edge is included as a compliance firewall specifically for Claude Code and other local AI-agent actions.

It can be installed from source with a quickstart script, or run from published Docker images with docker compose, and exposes a dashboard and an API gateway, each behind a generated API key, with TLS certificate and key pairs generated for the stack.

It is written in Go and licensed as source-available rather than open source.

More in AI evals

See all 269

Provenance gate
github.com
A deterministic authorization gateway that sits between an AI agent and its tools, tracing where each parameter of a side-effect call came from, and blocking the call or asking a human when the source does not check out.
- Agent skills
- AI evals
JevBench
benchmarkheaven.com
A reproducible benchmark from Benchmark Heaven that ranks Jev-class typed decision models on intelligence, calibration, speed, and cost, with a published harness, scoring rules, and results.
- AI evals
LIFE FORGE - The Autonomous Flight Simulator for AI Agents
github.com
A co-evolutionary adversarial red-teaming tool for AI agents that uses quality-diversity evolutionary search to autonomously breed edge-case scenarios, testing whether an agent with tool access can be made to hallucinate, deadlock or leak funds.
- AI evals
- Security

More in AI evals

Provenance gate

JevBench

LIFE FORGE - The Autonomous Flight Simulator for AI Agents

Cookies