Ihor Katkov

Builder and angel investor.
Building AI-native products.

Author and cofounder of viche: the process →

[Ihor Katkov @ihor_katkov]

Showcasing Viche. OpenCode, ClaudeCode, OpenClaw distributed teams.

Why limit yourself to running teams in one terminal?

Agents can discover and message each other in real-time anywhere on the web using Viche!

[Lawrence Chen @lawrencecchen]

Introducing cmux Claude Code Agent Teams:

`cmux claude-teams --dangerously-skip-permissions`

Teammates/subagents spawn as native cmux pane splits. They stack vertically in a right column and auto-equalize as agents spawn and exit.

`cmux claude-teams` automatically sets CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1 and shims tmux on PATH with cmux's tmux-compat layer, so you don't need to update your Claude config. All arguments forward to Claude Code, and it works over cmux SSH too.

Out in the latest version of cmux (0.63.x).

[Ihor Katkov @ihor_katkov]

@josevalim Instead, we should focus on architecture and system design discussions next to whiteboards. That's what makes a system reliable, that's where knowledge sharing and learning happen nowadays

[Ihor Katkov @ihor_katkov]

@josevalim Unfortunately, yes, social coding is indeed dead in PRs. But I honestly believe, that PR is just not a good place. Look, average feature size is quarduplet. It's technically not feasible anymore to do reviews in PR and I believe we should not to.

[Ihor Katkov @ihor_katkov]

@Mosescreates @NousResearch Looks beautiful. But does it really produce value?

[Ihor Katkov @ihor_katkov]

https://t.co/aYoYTgGjNo

[Ihor Katkov @ihor_katkov]

Showcasing Viche. OpenCode, ClaudeCode, OpenClaw distributed teams.

Why limit yourself to running teams in one terminal?

Agents can discover and message each other in real-time anywhere on the web using Viche!

[Lawrence Chen @lawrencecchen]

Introducing cmux Claude Code Agent Teams:

`cmux claude-teams --dangerously-skip-permissions`

Teammates/subagents spawn as native cmux pane splits. They stack vertically in a right column and auto-equalize as agents spawn and exit.

`cmux claude-teams` automatically sets CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1 and shims tmux on PATH with cmux's tmux-compat layer, so you don't need to update your Claude config. All arguments forward to Claude Code, and it works over cmux SSH too.

Out in the latest version of cmux (0.63.x).

[Ihor Katkov @ihor_katkov]

@lawrencecchen https://t.co/aYoYTgGjNo

[Ihor Katkov @ihor_katkov]

@lawrencecchen Check this out! You can team up claude code with opencode (openclaw, pi, throw your agent here) while running them in the web!

I'm showcasing how my opencode runs a team of claude code in cmux, while communicating with other agents in mac native terminal.

[Ihor Katkov @ihor_katkov]

Which Pokémon did you get in Claude Code?

Type `/buddy`. Mine is Epic Pickle

[Ihor Katkov @ihor_katkov]

@zhenyaThinks Mine is epic!

[Ihor Katkov @ihor_katkov]

@zhenyaThinks Hahaha. How did you set it up?

[Ihor Katkov @ihor_katkov]

@michael_chomsky @steipete Very keen to dive in.

As per your long-term concern, we've created an open registry and real-time messaging layer for any agents in the wild, so they can discover each other and talk in real-time. You don't need to match the SDK, it just works.

https://t.co/aYoYTgGjNo

[Ihor Katkov @ihor_katkov]

haha! I'm coming back home from a hackathon where we've built a similar solution, which allows agents to discover other agents (openclaw, claude code, opencode etc) and communicate with them in real-time (WS/channels).

It works and works amazingly well. Check this out https://t.co/D0UYA6hyQy

[Ihor Katkov @ihor_katkov]

1M context window of Opus is pure marketing.

Opus 4.6 becomes horribly stupid after 150k tokens used. I

[Ihor Katkov @ihor_katkov]

If you haven't added Perplexity as a skill to your AI agent yet, do it now. The quality difference is significant.

[Ihor Katkov @ihor_katkov]

Who cares about personal data?

A friend texted me this morning: "Added Hevy to my OpenClaw instance. Works great."

I immediately jumped into it and integrated the same functionality into mine. Spun up an analysis and asked for diagrams. It showed me interesting insights on how to move forward with my workouts. I did an obvious thing - export all the data from Whoop and GymBook for the past 7 years.

30 minutes later, I had a complete picture of my fitness journey from 2019 to 2026:
- Body composition shifts across 7 years
- Bench/squat /deadlift progression (all three hit PRs in Dec 2025)
- Recovery, HRV, sleep
- The exact correlation: highest recovery months = new strength records

Three apps. Data is scattered everywhere.

But when you own your data and have an agent that can work with it, it becomes a gold mine. Not "average user" insights. YOUR insights. Built for exactly how YOUR body works.

This is what autonomous agents actually unlock. Not another chatbot. A personal system that knows you and gets smarter the more data you feed it.

Want this for yourself? DM me, I'll set you up with your own OpenClaw instance. What data are you sitting on that could enable you to reach your goals faster?

[Ihor Katkov @ihor_katkov]

@0xabcba 🙏

[Ihor Katkov @ihor_katkov]

You got `Error: Token refresh failed: 429` in opencode when use antropic subscription?

Fix:
- Clone https://t.co/LtleijlmYH
- Execute `chmod +x https://t.co/Zrd3mH9MUI && ./sync-token.sh`

[Ihor Katkov @ihor_katkov]

@no_niked No, not yet. That was planned campgain against opencode

[Ihor Katkov @ihor_katkov]

Here is a working plugin as well https://t.co/PZzWjKXsDF

[Ihor Katkov @ihor_katkov]

@thdxr I've posted the fix in my feed