Codex Symphony – bootstrap OpenAI Symphony and Linear in any repo
Convenience wrapper around Symphony and Linear—useful if you're already using both.
A minimal TypeScript orchestrator connecting Linear, Symphony, and YSA — picks up issues, runs Claude agents in sandboxed Podman containers, and shows blocked network requests in real time.
Example repo for YSA sandboxing when the main YSA product would be the actual submission.
Developers building AI agent systems requiring network isolation and security
E2B · Modal · Replicate
This example repo shows how to connect it to Symphony (OpenAI's agent orchestrator) — the entire integration is one new file, runner/ysa.ts.
The demo shows an agent attempting to POST data to an external URL and getting blocked by the network proxy.
Demo Repo: https://github.com/ysa-ai/ysa-symphony-example YSA: https://github.com/ysa-ai/ysa
Convenience wrapper around Symphony and Linear—useful if you're already using both.
Go reimplementation of OpenAI Symphony with multi-agent team coordination, but the market is brand new.
Defense-in-depth sandboxing for Claude agents: Podman + MITM proxy + seccomp + iptables.
Five-component architecture adds output enforcement to standard RAG pipelines.
Solid security research, but it's a case study—not a tool you can actually use.
Linear becomes the UI for autonomous AI dev agents running in local bubblewrap sandboxes.