Kōan
See your AI agents think. Reasoning, tool calls & decisions
Start new thread

Kōan - See your AI agents think. Reasoning, tool calls & decisions

by•
AI agents are powerful but invisible. When they fail, you get an error — not a reason. Kōan streams every agent event live — reasoning, tool calls, decisions, errors — tagged and timed. → Anthropic, OpenAI, Gemini + any custom LLM → Add DeepSeek, Mistral, Ollama via custom provider → Per-agent model selection → BYOK — keys never stored → No signup needed Free to start. Just add your API key and run.

Add a comment

Replies

Best
Maker
📌
Hey Product Hunt! 👋 I built Kōan because I kept hitting the same wall — AI agents failing in production with zero visibility into why. The name comes from Zen Buddhism. A kōan is a riddle with no obvious answer — which is exactly what debugging a black-box AI agent feels like. Kōan makes the invisible visible. A few things I'd love your feedback on: 1. Which provider integrations matter most to you? 2. What would make the event stream more useful for debugging? 3. Would team sharing / log export unlock this for your workflow? Try it free at k-an.vercel.app — no signup, just add your API key and hit Run All. Happy to answer any questions below! 🎋
Maker

Update — Day 3 🎋

Shipped a few improvements based on your feedback:

→ Clearer positioning: Kōan is agent observability — not just a log viewer or debugger.

→ JSON + CSV export: download full agent sessions for offline debugging, sharing, or analysis.

→ Session sharing: generate a URL and share exactly what your agent did — reasoning steps, tool calls, and decisions included.

→ Clearer empty state: new users now know exactly what to do when they land.

Kōan works with OpenAI, Anthropic, Gemini, DeepSeek, Mistral, Ollama, and custom endpoints.

Still free. Still BYOK. Still no signup.

👉

What should I ship next?

Maker

Just shipped - v3 update

We've been heads-down building and just pushed a bunch of features based on early feedback:

What's new:

  • Sessions now persist — your API keys and agents survive browser refreshes. No more re-entering everything.

  • Search your agent logs — filter the live event stream by keyword or event type in real time.

  • Test your API keys — one click to verify a provider connection before running agents. Instant ✓ or ✗.

  • Copy any log entry — hover any event and copy the message instantly.

  • Keyboard shortcut — press R to run all agents, Esc to close modals.

  • Agent run counter — see how many times each agent has fired this session.

  • Import / Export agents — back up your agent configs as JSON or share them with your team.

  • Light & dark mode — toggle between themes from the header. Your preference is saved automatically.

Still free, still BYOK (bring your own keys), still works with Anthropic, OpenAI, Gemini, and any OpenAI-compatible API.

More coming soon — would love to hear what you want next. Drop a comment