Ante protects its eval-verified agent engine behind a typed stream, so developers can build custom interfaces, IDE integrations, and team workflows without coupling them to the core.

4 points•ubermon•9 days ago•6 comments•

6 comments

swrrt9 days ago
Interesting, I thought it was something related to Apache Kafka or Apache Flink type of things. I personally working on that type of streaming for a longtime, never considering stream in an 'agentic' context.
swrrt9 days ago
Does this kind of stream involves things like 'dynamic scaling' or 'load balancing' where typical streaming system need to consider about?
ubermon9 days ago
not yet, but will be included in the distributed version
roguelite9 days ago
can you share the repo?
ubermon9 days ago
Hi HN, this Monk from Antigma Labs, a lot of recent agent/harness projects lean toward "everything is a plugin". For the surface, I agree. Our take is that it stops being right at the agent core.

The interface is cheap to verify: you look at it and you know. The agent core (compaction, scheduling, loop heuristics) is not. Whether a change there made the agent a bit worse at multi-file refactors only shows up in eval sweeps across models and seeds. An in-process plugin API over that layer freezes it right where it needs to evolve.

So we borrowed from Unix pipes: plugin the surface, protect the plugged. The engine runs as a daemon (ante serve) and talks over a typed message stream. Clients send operations (prompts, approvals, interrupts); the engine emits events (tokens, diffs, tool progress). The terminal UI you get when you run ante is just one client of that stream.

Some of the examples:

examples/mini-tui: a one-file Rust TUI

ante-acp: Agent Client Protocol adapter for Zed and JetBrains (work in progress; no session resume yet)

ante-gateway: Slack and Discord bot, one isolated session per thread

Love to hear more about your thoughts on the future of agent architecture

Read the full thread on Hacker News →

Related stories