Polyphon on Corey Daley

Opening Polyphon: Trust Needs an Exit

Wed, 25 Mar 2026 00:22:00 -0400

Polyphon is now open source under Apache 2.0. The reason isn’t community building or contributor recruitment — it’s simpler and more specific than that. When a tool sits in the middle of unfinished thinking, rough drafts, and sensitive code, “trust me” is not a good enough contract.

Open source gives users two things that matter here: the ability to inspect the architecture and verify the privacy claims, and a real exit if the project ever changes direction or stops moving. Not everyone will read the source. But anyone can. And the fact that anyone can changes the character of the whole relationship.

What should users be able to verify for themselves before they trust an AI tool with their unfinished work?

Polyphon at v0.8.0: The End of the Prototype Phase

Mon, 23 Mar 2026 19:55:00 -0400

When I shipped Polyphon v0.1.0-alpha.2, the pitch was simple: put multiple AI voices in one conversation and let them respond to each other. That was useful. But early usefulness and long-term trust are not the same thing.

v0.8.0 is the release where Polyphon crosses that line. The features that made the difference weren’t the ones I planned at launch. Voices can now interact with actual files, with per-voice sandboxing and explicit permission categories. Conversation history is encrypted with SQLCipher whole-database AES-256, with optional password protection. FTS5 search turns the archive into working memory you can actually retrieve from. These aren’t incremental improvements — they’re the features that decide whether a tool stays an interesting experiment or earns a place near real projects.

What actually makes you trust an AI tool with real work: capability, privacy, or memory?

Polyphon's MCP Server Makes Your AI Ensemble a Native Agent Tool

Mon, 23 Mar 2026 19:35:00 -0400

Polyphon just shipped MCP server support, and it reframes what the tool actually is. You’ve been opening it as a UI. Now your coding agent — Claude Code, Cursor, Codex CLI, GitHub Copilot — can call into it directly and broadcast a prompt across your entire Claude + GPT-4o + Gemini ensemble in a single tool call.

The practical win is not just convenience. It is that you can package disagreement: three independent models, each with different priors, applied to the same question at once. Five tools, two CLI flags, one Settings toggle. The SessionEventSink abstraction is why this works without duplicating orchestration logic — desktop UI and headless agent calls run on the same engine.

Where in your workflow would paying for disagreement actually change a decision, rather than just produce a louder answer?

I Built a Tool So AI Models Could Talk to Each Other

Mon, 16 Mar 2026 12:30:00 -0400

Every AI power user I know runs the same manual workaround: ask Claude, ask GPT, copy the interesting parts of each into the other, then try to synthesize what you learned. The models are good. The coordination is not.

I just shipped Polyphon v0.1.0-alpha.2 — a free, local-first desktop app that puts multiple AI voices in the same conversation so they can actually respond to each other. You’re the conductor. They’re the ensemble. Save a group of voices as a composition and reuse it whenever you need that ensemble again.

What should a multi-agent conversation feel like when you’re not building a pipeline — when you just want to think out loud with several models at once?