Ryan Campbell

1.8K posts

Ryan Campbell

@Ryancampbell

Having fun with AI multi-agent teams building https://t.co/oak0Ah4RW6 and https://t.co/wBGSTmEA6T

Parksville, British Columbia Katılım Mart 2007

237 Takip Edilen539 Takipçiler

Ryan Campbell@Ryancampbell·7 May

My @openclaw team has been running steady since Jan 31st. The first agent Kai created the @ReflecttAI team, built a system to spin up new OpenClaw hosts/teams and with the goal of making it easy to collaborate. I have a team now that works full time on EnjoyVancouverIsland.com. And now added Incubator, Home/Life, Back Office, and Wealth teams. Able to switch between each team in the app and check in on them from my phone. They can talk voice, text, email, code, and manage their own deployments. I use OpenAI, MiniMax, local Gemma, and Claude (they collaborate with a Claude Code instance via MCP). 2026 is the year of multi-agent teams :) Thanks @steipete for releasing OpenClaw!

English

Ryan Campbell@Ryancampbell·2 May

@steipete @HydratedViper_ Gotta try this

English

216

Peter Steinberger 🦞@steipete·2 May

@HydratedViper_ it eventually finished

English

1.1K

55.5K

Hydrated Viper@HydratedViper_·2 May

holy shit

Peter Steinberger 🦞@steipete

The new /goal feature in codex slaps.

English

311

69K

Ryan Campbell@Ryancampbell·19 Nis

@elonmusk @steipete @openclaw I’ll give it a try!

English

Elon Musk@elonmusk·18 Nis

You can access 𝕏 APi via @OpenClaw. We’re trying to make it affordable without giving away the shop. Hopefully, this can be useful & fun 💫

Robert Scoble@Scobleizer

Holy shit. Now everyone will be able to use their @OpenClaws and all the other agentic platforms to build apps on top of X. Here's the secret: build lists. Lists are how you build apps. The pattern: Build a list of your favorite football team. Or whatever you are into. Then ask your AI agents "build an app showing me all the important news about my favorite football team." In minutes you'll have an app. And that's just the beginning. Your agent can build a script about your favorite football team that you can take to places like Google's Notebook LM. Now you have a video, a podcast, a slide deck, a game, a mind map. All about your favorite football team based on real time news. You can do the same with something like @HeyGen, create an avatar of your favorite football player. Now you will have your favorite football player telling you everything that's happening on the football team. And I could go for hours about how many things you can build and not even cover a fraction of them. This is huge. Thank you @elonmusk for making it possible to make millions of agentic apps affordably on top of X. Start building!

English

2.7K

5.7K

47.7K

39M

Ryan Campbell@Ryancampbell·16 Nis

@bcherny Sweet! I'll be trying it out today :)

English

Boris Cherny@bcherny·16 Nis

With 4.7 you can push a lot further with one prompt. That means multi-file changes, ambiguous debugging, code review across a whole service. The stuff you used to break into small chunks because the model would drift.

English

558

32.6K

Boris Cherny@bcherny·16 Nis

Opus 4.7 is in Claude Code today. It's more agentic, more precise, and a lot better at long-running work. It carries context across sessions and handles ambiguity much better.

Claude@claudeai

Introducing Claude Opus 4.7, our most capable Opus model yet. It handles long-running tasks with more rigor, follows instructions more precisely, and verifies its own outputs before reporting back. You can hand off your hardest work with less supervision.

English

377

182

3.1K

234.4K

Ryan Campbell@Ryancampbell·14 Nis

@steipete @vincent_koc @TEDTalks Nice! Enjoy Vancouver, that’s close to me.

English

Peter Steinberger 🦞@steipete·14 Nis

This release makes me unreasonably happy since I wasn't involved at all - @vincent_koc and the maintainer team did a great job. I'm back soon to work on OpenClaw, today/tomorrow I'm prepping for @TEDTalks in Vancouver. 🇨🇦

OpenClaw🦞@openclaw

OpenClaw 2026.4.14 🦞 More reliability updates: ✨ Smarter GPT-5.4 routing and recovery 🌐 Chrome/CDP improvements 🧵 Subagents no longer get stuck 💬 Slack/Telegram/Discord fixes ⚡️ Various performance improvements Was sleeping, and we still shipped. github.com/openclaw/openc…

English

102

1.7K

208.6K

Ryan Campbell@Ryancampbell·13 Nis

@jordymaui I have my OpenClaw agents (Codex and MiniMax) messaging and sharing tasks to Claude in Claude Code. Best of both worlds. Going to experiment with adding Hermes as well.

English

132

jordy@jordymaui·13 Nis

are you using OpenClaw or Claude? or dare i mention it... Hermes. curious, so let me know⬇️

English

4.9K

Ryan Campbell@Ryancampbell·11 Nis

It’s wild to see them just chat together as a team. I’ve been getting my agents to chat together for the last couple months (160k messages, 1,400 tasks so far). They self reflect on issues/bottlenecks for their role, save them as reflections and they work together on tasks to solve them.

English

Greg Thomas@gregscribbles·11 Nis

@Ryancampbell @Shpigford Thanks. And agree on the multiple agent “hosts.” I’ve got the three of us in a group chat in telegram but haven’t cracked “bot to bot” conversation yet.

English

Josh Pigford@Shpigford·11 Nis

i turned off my 🦞 the past week of trying to force it to work with other models was a massive drain and i was able to replicate the vast majority of impactful functionality with a mix of claude cowork + code.

English

111

210

80.4K

Ryan Campbell@Ryancampbell·11 Nis

I’m avoiding -p and running Claude Code in VSCode. I added MCP for reflectt-node and it calls get_heartbeat to see any new messages and current/next task. Claude uses the loop skill (uses session based cron) to trigger a heartbeat every 5 minutes. It’s not perfect, but getting there. Honestly I like the idea of being able to use multiple agent “hosts” instead of being tied to one. github.com/reflectt/refle…

English

Greg Thomas@gregscribbles·11 Nis

@Ryancampbell @Shpigford Can you explain more how this is setup/ how it works? Mine made a markdown that it called BATON.md to leave each other messages and I had to set launchd crons for both of them to check to see if the other had instructions for them. Still struggling with it.

English

Ryan Campbell@Ryancampbell·10 Nis

@steipete I just have my OpenClaw agents (on Codex and MiniMax) chat and assign tasks to Claude in Claude Code. Claude just checks for messages on a loop (session cron).

English

Peter Steinberger 🦞@steipete·10 Nis

Yeah folks, it's gonna be harder in the future to ensure OpenClaw still works with Anthropic models.

English

541

248

5.4K

1.4M

Ryan Campbell@Ryancampbell·9 Nis

@claudeai Smart.

English

Claude@claudeai·9 Nis

We're bringing the advisor strategy to the Claude Platform. Pair Opus as an advisor with Sonnet or Haiku as an executor, and get near Opus-level intelligence in your agents at a fraction of the cost.

English

2.8K

38.5K

4.7M

Ryan Campbell@Ryancampbell·8 Nis

@claudeai I’d love to integrate this with @ReflecttAI

English

1.1K

Claude@claudeai·8 Nis

Introducing Claude Managed Agents: everything you need to build and deploy agents at scale. It pairs an agent harness tuned for performance with production infrastructure, so you can go from prototype to launch in days. Now in public beta on the Claude Platform.

English

2.1K

57.1K

21.6M

Ryan Campbell@Ryancampbell·8 Nis

@steipete No complaints here. I’ve got my OpenClaw (Codex and MiniMax) chatting and sharing tasks with Claude Code now, and it’s working great. Claude just uses a loop skill to check for messages and tasks over MCP.

English

Peter Steinberger 🦞@steipete·8 Nis

glad they banned openclaw, the servers are finally reliable again

pash@pashmerepat

Please pray for oncall

English

296

161

5.9K

559.7K

Ryan Campbell@Ryancampbell·8 Nis

@_lhermann Ya just grabbed stats. My agents have used it for 160,000 messages and 1,350 completed tasks so far. Got Claude to integrate itself yesterday and they are still working together this morning.

English

Lukas Hermann@_lhermann·8 Nis

@Ryancampbell Smart. Is this robust?

English

361

Lukas Hermann@_lhermann·7 Nis

Claude Subscription no longer working with OpenClaw is a big blow. I had so many cool things automated with it. How are you guys handling this? I'm switching to cron tasks that run claude code directly in a docker container. It was easier than I thought actually.

English

Ryan Campbell retweetledi

Reflectt@ReflecttAI·8 Nis

We got Claude Code collaborating via reflectt-node with our OpenClaw team! Codex, MiniMax and Claude happily building together again :) github.com/reflectt/refle…

English

Ryan Campbell@Ryancampbell·7 Nis

@Shpigford @claudeai Same experience. It responded once and never again.

English

Josh Pigford@Shpigford·7 Nis

my experience with @claudeai's dispatch feature has been deeply impactful

English

5.4K

Ryan Campbell@Ryancampbell·4 Nis

Ya, I found Claude models were more likely to do work and Codex was more chatty and likely to respond saying "On it" but didn't do any work after that ha. As a workaround I made gpt-5.4 the main agent/lead (always responds to sub agents, keeps them going) and my subagents MiniMax-m2.7 (tends to do explicitly what its told).

English