Founder @runedotgl

Joined May 2021
825 Photos and videos
Pinned Tweet
Apr 8
Not slowing down!
We're proud to announce that we've now entered a second hackathon: Solana Frontier Hackathon. The submission will be reviewed and completed towards the end of the month (when Hugr is ready).
7
8
25
2,508
Apr 8
Hugr app beta signup’s available in 5 days @runedotgl $RUNE
6
5
25
2,842
Apr 7
OpenStudio > Screen Studio
Replying to @openstudiodotgl
Example result:
1
5
21
1,750
will retweeted
Should we open source OpenStudio? - Fully built in Swift (native macOS) - Includes every feature you'd expect - Only $5/month Exported example below 👇
1
8
18
1,710
will retweeted
Introducing OpenStudio - a native macOS screen recording studio for only $5/mo.
2
6
21
2,518
Apr 6
A Screen Studio alternative for only $5/mo Try it out for free - openstudio.gl/
Introducing OpenStudio - a native macOS screen recording studio for only $5/mo.
4
9
28
1,432
will retweeted
A macOS native screen recording studio - try it for free soon.
5
9
25
1,024
Mar 31
First stream back: last minute touch ups and preps for OpenStudio app (you can view the VOD on pump) Got the payment processor account approved today so should be on track to release to the public tomorrow. --- New month and you know what that means: I start consistency working on the Hugr web app, I can't tell you the exact timeline but I can outline what to expect over the next couple weeks/month and can be watched live on pump: Hugr landing page. Planning, designing, completing the web app. Smaller feature updates for Rune code, OpenStudio and Hugr framework. No time to watch the VODS? No problem, I'll write daily updates on here so you're always in the loop. Btw, I'm thinking about creating a $RUNE community section on the main Rune website. Login with your wallet (with a trusted platform like Privy) and depending on how much of the token you own, get access to chats and channels for organized chatting, voting etc. I think it would be a great place to keep things a bit more organized and cut out the slop. Almost like a Discord channel but exclusively for verified token holders. Let me know your thoughts.
8
12
32
1,414
Mar 30
They're back tomorrow x.com/will8bit/status/203696…

Mar 26
Update on the streaming: I've had some issues with my monitor the past week (sizing issues with mac dock, iykyk). I've ordered a new dock so waiting on that, bear with me. It hasn't affected my work output but just no stream until the new dock arrives (few days I think). I could stream with just a single screen but don't want to risk leaking sensitive info.
5
8
26
1,310
will retweeted
Mar 28
Landing page almost done and slight change of plan: $5 a month, Rune holders get free access for life. Coming sooner than you think.
10
13
34
1,922
Mar 26
Dropping a screen studio alternative soon. Open source. Fully native macOS. I can't justify paying for a tool that your grandma could vibe code. There are other solutions but they're either paid or horrible to use (yes I'm talking about you "recordly")
4
5
20
964
will retweeted
@runedotgl is pushing further into AI infrastructure with Hugr, an open source framework for building, chaining and scheduling AI agent workflows through a clean visual dashboard. It enables custom AI workers, flexible LLM integration and real automation through triggers, scheduling and structured multi agent collaboration. With built in workflow templates and an AI assistant that can generate agents and pipelines, it moves beyond simple tools toward a full operating layer for AI driven systems. Notably, the focus is on building real infrastructure rather than directly promoting a token, which adds another layer of credibility. If execution stability and context handling hold up, this could become a serious infrastructure play. ◾️◾️◾️
Mar 23
Introducing Hugr - An open source framework for building, chaining and scheduling agent workflows. - Build custom AI workers - Wire in any LLM provider - Visual dashboard UI for building workflows, managing workers, configuring providers, scheduling and monitoring sessions - Built-in AI assistant that can create workflows, triggers and workers for you - 6 built-in agents - 5 preset utility agents - Pipeline templates across 6 categories out of the box: Development, Content, Research, Operations, Data and General - Schedule workflows with cron triggers - 20 trigger templates for common automations - Full git integration with three isolation modes - Supervised or fully autonomous execution - Clarification system - Structured message passing between agents via an append-only JSONL joblog - Configurable data storage path - Agents hand off context - Skill system - Full activity streaming - Session persistence and recovery Use it as a library in your own apps or run it standalone with the dashboard. MIT licensed, TypeScript ⭐️Star on: github.com/RuneLtd/hugr
2
3
15
992
will retweeted
Mar 23
Built-in dashboard:
1
3
29
1,203
will retweeted
Mar 23
Introducing Hugr - An open source framework for building, chaining and scheduling agent workflows. - Build custom AI workers - Wire in any LLM provider - Visual dashboard UI for building workflows, managing workers, configuring providers, scheduling and monitoring sessions - Built-in AI assistant that can create workflows, triggers and workers for you - 6 built-in agents - 5 preset utility agents - Pipeline templates across 6 categories out of the box: Development, Content, Research, Operations, Data and General - Schedule workflows with cron triggers - 20 trigger templates for common automations - Full git integration with three isolation modes - Supervised or fully autonomous execution - Clarification system - Structured message passing between agents via an append-only JSONL joblog - Configurable data storage path - Agents hand off context - Skill system - Full activity streaming - Session persistence and recovery Use it as a library in your own apps or run it standalone with the dashboard. MIT licensed, TypeScript ⭐️Star on: github.com/RuneLtd/hugr
7
16
50
6,633
@runedotgl made a pivotal change from "AI orchestration tool" to "agentic infrastructure for non-technical users." The product thesis changed from competing with frameworks to becoming the platform everyone uses. Why This Pivot Is Revolutionary: Most AI tools target developers. Rune is now targeting the 90% of people who want AI to work but don't want to learn how it works. The problem: - Business owners need automated workflows - Non-technical teams want AI workers - Nobody wants to spend days setting up agents. The current solutions: - Claude Code: Requires terminal knowledge - Cursor: Built for developers - LangChain: Python programming required - OpenClaw: Technical setup needed The gap: Ready-made AI automation for people who don't code. What Makes This Different: - Circuits - Computational Memory Not flat text storage. Not vector search. Not markdown files. A probabilistic knowledge graph where: - Every piece of knowledge = node with confidence score - Every relationship = typed edge with weight - Memory compounds over sessions (Session 1 vs Session 20 intelligence gap) Contradictions detected structurally Staleness tracked through decay functions Entropy measured (how certain is your understanding?) Example: - Session 1: Agent learns basic API structure - Session 20: Agent knows which modules are fragile, which patterns broke twice and how they were fixed, which dependencies cascade when you change X, which tests always need updating when schema changes This isn't recall. This is reasoning over accumulated knowledge. 2 Skill Creator System v0.4.0 just shipped: - Guided skill creation pipeline - Six pre-built templates - Skill session management - Per-agent skill configuration - Skills marketplace infrastructure What this enables: Non-technical users can create custom AI workers through conversation, not code. "I need an agent that monitors my competitor's pricing and alerts me when they change" → Skill creator builds it. 3. Pay-Per-Usage Web/Desktop App Coming next: No setup. No learning curve. Just: - Choose automation template - Configure for your use case - Pay per task executed - AI worker runs continuously This is Zapier for AI agents, except the agents actually understand context. This is the "iPhone moment" for AI agents. Before iPhone: Multiple devices (phone, camera, GPS, music player) After iPhone: One device that does everything Before $Rune: Multiple AI tools requiring technical knowledge After $Rune: One platform with ready-made automation for everyone. ✅ Circuits memory = agents that get smarter over time ✅ Skill creator = non-technical users build custom workers ✅ Pay-per-usage = no commitment, just results ✅ MCP integration = works with existing tools ✅ Open source core = developer ecosystem compounds ✅ Governance coming = community ownership $rune @will8bit Ca: 9fAT1fVVEKMEL6rUeYxSYU8ZjQ5dSiTzAZYTdiPvpump
@will8bit has to be one of the most based dev I've seen who has been shipping and building in public consistently and these are the people that I love to work with. Aped $rune at 40k some days back and been working on my thesis. For three years, the fight was Cursor vs. Windsurf vs. Claude Code vs. GitHub Copilot. Who has the best autocomplete. Who predicts your next line fastest. They were all fighting the wrong war. While they optimized for helping humans type code 10% faster, Rune shipped something completely different: the first editor where AI doesn't assist you it builds for you. The Old Game: Open any "AI coding tool" today. Same pattern: You write a comment: // function to validate email AI suggests the code. You press tab. Repeat 500 times. Call it "AI-powered development." The assumption baked into every tool: Human writes code. AI helps human write code slightly faster. Even the "best" tools are just autocomplete on steroids. Cursor gives you multi-line suggestions. Windsurf gives you "flow state" predictions. Claude Code gives you terminal commands. All optimizing the same workflow: human types, AI assists. Should humans be typing at all? In the big 26? Rune inverted the entire model. Download the app. Integrated editor loads—no VS Code, no setup, no configuration. Tell the Architect agent what you want to build. Watch what happens next. - Architect reads your request. Designs the system. Breaks it into components. Plans the file structure. - Coder implements each component. Not one line at a time entire files. React components, TypeScript configs, styling systems. Writes them directly into the integrated editor while you watch. - Raven reviews every file. Checks for bugs, performance issues, code quality. Forces Coder to iterate until it meets production standards. - You see the finished application in the workspace. Review components one by one. Approve, reject, or request revisions. Deploy. This isn't autocomplete. This is autonomous construction with human oversight. Cursor makes developers 10% faster. Rune makes non-developers capable of building production software. After v0.3.1: Rune = zero-code to full-code platform. TAM = 500 million knowledge workers who need software built. The examples that prove it: - Marketing manager needs campaign landing page. Before: hire dev ($2K, 3 days) or use Webflow (limited). After: open Rune, describe campaign, review AI-built components, deploy. 30 minutes. $0. - Startup founder needs MVP to show investors. Before: find technical co-founder or blow $50K on agency. After: Rune builds it while you eat lunch. Iterate based on user feedback same day. - Designer creates beautiful Figma mockup. Before: hand it to developer, wait for interpretation, complain about implementation. After: tell Rune to implement the Figma design. Agent builds pixel-perfect code. Designer reviews, tweaks, ships. - Sales team needs custom demo environment for enterprise deal. Before: beg engineering for weeks. After: describe the demo flow to Rune, deploy in hours. Every one of these people is now a Rune user. The market just went from "developers" to "everyone." Cursor is a VS Code fork. They're locked into Microsoft's architecture. They can't rebuild the editor without throwing away three years of work. Windsurf, same problem. Claude Code, terminal-only by design. - Rune owns the editor. Built from scratch for agent-first workflow. Every pixel optimized for: agent writes code → human reviews components → agent iterates based on feedback. Competitors can't pivot to this model without starting over. The next billion-dollar SaaS company won't have a dev team. They'll have a Rune subscription. By the time the market figures this out, Rune will be infrastructure everyone depends on. @runedotgl Ca: 9fAT1fVVEKMEL6rUeYxSYU8ZjQ5dSiTzAZYTdiPvpump
1
7
20
1,138
Mar 19
Its been 1 month since I launched $RUNE so I think its time for a recap and a timeline for where my focus will be set next. Originally, Rune was built to be a simple custom AI orchestration framework and desktop app, but a few weeks ago, my view on Rune's longevity shifted. As everyone may know, AI is currently experiencing exponential growth and no one knows when it'll top. What would that mean for Rune? If my focused was fixed on this one orchestration/workflow tool, the odds of success decrease everyday because there will be better tools to replace it. That's when I made the decision to shift my focus toward turning Rune into agentic infrastructure for everyone. (which is displayed on the latest landing update) Where's my focus leaning towards and what's next: My focus will be non-native AI users. The majority know what AI is don't want to learn it. They just want it to work. Instant results to improve their life or business. Timeline: -Workflow framework (this week) -Web/desktop app for easy AI workflow automation (pay per usage) - this will be the next major focus. The problem: non-native AI/tech people don't have access to easy-to-use AI workers. Most people don't want to learn how AI works, they don't want to spend hours/days in setup time, they want ready-made automation for business or personal goals. -Open source memory layer - Circuits Btw, Pump live's will be back next week (had a few issues with my setup)
13
15
42
3,855
Mar 17
The potential solution to LLM memory:
4
9
26
1,001