This product was not featured by Product Hunt yet. It will not be visible on their landing page and won't be ranked (cannot win product of the day regardless of upvotes).
Ruflo Console
Mission control for your AI agents inside Claude Code
Mission control for AI work inside Claude Code. Plan missions, follow workflows and agent activity, inspect logs and results, and track models, tokens and cost. Bring approvals, questions and failures into one view. Let Claude operate the console within permissions you choose, then take back control at any time. Explore memory, security, project decisions and plugins from the same cockpit. Open source, with optional animated themes.
Ruflo Console is mission control for AI work inside Claude Code: plan missions, follow agents and keep control.
Try it now in Claude Code 2.1.287 or later. Enter these commands in Claude Code, one at a time:
/plugin marketplace add ruvnet/ruflo
/plugin install ruflo-console@ruflo
/reload-plugins
/ruflo
Then ask Claude to create a mission to add dark mode. Approve it and check the mission and action log. Creating a mission does not mean the feature has been built.
Here is what the console brings together:
Plan and follow work. Create missions, set goals and track tasks, workflows, agent activity and swarm topology.
Inspect runs. Open logs and results, search, triage failures, replay and compare. Track models, tokens and cost. Missing measurements show n/a.
See what needs you. The Room brings approvals, questions, failures and finished work across local Claude Code, Codex and Ruflo sessions into a review queue with session previews.
Keep control. Choose read, write, manage or full permissions and ask or auto confirmation. Network, spending and destructive actions still require confirmation. Review the action log or press Take back control.
Keep context close. Explore memory, learning, security, diagnostics, project decisions and plugins. Some features require additional Ruflo components and configured providers.
Ruflo is open source. Model usage costs still apply. See the linked GitHub guide for setup details. Classic, plain and animated themes are optional.
The recorded session shows mission creation, navigation, a refused action and control being taken back. The explainer adds illustrative Seedance graphics. Neither proves completed swarm work or memory recall.
What is hardest to track with several agents: progress, failures, approvals or cost?
I got to test Ruflo Console on macOS before launch. Most of that was reading what the docs promise, trying it myself, and sending fixes back when the two didn't match.
Here's what stood out:
Missions. You create a mission, set goals and follow the tasks, workflows and agent activity as they happen. A mission is a plan, not proof the work is done, and the console is clear about that.
Runs. Logs, results, failures, models, tokens and cost all live in one place. If a measurement is missing, you see n/a instead of a made-up number.
The Room. Approvals, questions, failures and finished work from your Claude Code, Codex and Ruflo sessions land in one review queue, so you know what needs you.
Control. You pick the permission level and whether Claude asks or acts. Network, spending and destructive actions always need your confirmation, and Take back control is one press away.
Mods pair well with it, turning one mission into a full workflow with routing and policy controls.
To try both inside Claude Code (2.1.287 or later):
/plugin marketplace add ruvnet/ruflo
/plugin install ruflo-console@ruflo
/plugin install ruflo-mods@ruflo
/reload-plugins
/ruflo
Ruflo - so many innovations built under the hood and never stops moving. My daily driver
I’m part of the team launching Ruflo Console and Ruflo Mods, and I’ve been using this since the early Claude-Flow days, when Ruv first created it.
It became a core part of the agentic stack I used to develop my open-source platforms, including Agentic QE Fleet. Ruflo is still the main tool in that stack today. When I got early access to Claude-Flow v3, its domain-driven architecture and architectural decisions helped me rethink and rebuild the Fleet.
That’s why Console and Mods matter to me. Console brings workflows, agent activity, logs, token usage, and costs into a more approachable interface alongside Claude Code. Mods add routing and policy controls, making it easier to direct how the tools are used.
As a quality engineer, I still want evidence that the result works. Better visibility helps me ask better questions and decide where to intervene.
I’m glad to be helping bring this next chapter to more people. Try it on a real project and let us know what you discover.
Happy launch day! Congrats on Ruflo Console. Nice to be launching alongside you today. We're launching Benson too: https://www.producthunt.com/products/benson-2. Would appreciate a comment or some support if you've got time. Hope the day goes well!
Hi everyone, Nick here 👋
What excites me about this Ruflo release is how it brings the full engineering workflow together. Writing code is one step. Research, testing, security review and understanding why decisions were made all need to happen too.
Ruflo is the open-source agent orchestration layer for Claude Code and Codex.
A few highlights from this release:
🎯 Mods turn one mission into a workflow that researches, builds, tests, validates, secures, benchmarks and learns.
🖥️ Ruflo Console brings missions, agent activity, logs, token usage and cost into one view beside Claude Code.
🌐 Federation lets Ruflo installations across machines share workloads, with identity verification and policies that gate outbound data.
🧠 Self-learning memory helps agents reuse successful approaches in later tasks.
For me, the combination of coordination, visibility and human control is the big deal. You choose what Claude can access, when it needs approval and when to take back control.
🎨 Orbital also adds an optional animated console theme, with custom palettes, a classic look and reduced motion available.
The native console integrates with Claude Code; Codex and other MCP clients connect through Ruflo’s MCP server. Ruflo is open source, and your model provider’s subscription or usage costs still apply.
What’s the first project you’d put Ruflo Mods to work on?
About Ruflo Console on Product Hunt
“Mission control for your AI agents inside Claude Code”
Ruflo Console was submitted on Product Hunt and earned 20 upvotes and 6 comments, placing #33 on the daily leaderboard. Mission control for AI work inside Claude Code. Plan missions, follow workflows and agent activity, inspect logs and results, and track models, tokens and cost. Bring approvals, questions and failures into one view. Let Claude operate the console within permissions you choose, then take back control at any time. Explore memory, security, project decisions and plugins from the same cockpit. Open source, with optional animated themes.
Ruflo Console was featured in Open Source (68.9k followers), Developer Tools (521.3k followers), Artificial Intelligence (481.3k followers) and GitHub (41.4k followers) on Product Hunt. Together, these topics include over 266.9k products, making this a competitive space to launch in.
Who hunted Ruflo Console?
Ruflo Console was hunted by Reuven Cohen. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
Want to see how Ruflo Console stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
Reuven Cohen
Hey Product Hunt, rUv here.
Ruflo Console is mission control for AI work inside Claude Code: plan missions, follow agents and keep control.
Try it now in Claude Code 2.1.287 or later. Enter these commands in Claude Code, one at a time:
/plugin marketplace add ruvnet/ruflo
/plugin install ruflo-console@ruflo
/reload-plugins
/ruflo
Then ask Claude to create a mission to add dark mode. Approve it and check the mission and action log. Creating a mission does not mean the feature has been built.
Here is what the console brings together:
Plan and follow work. Create missions, set goals and track tasks, workflows, agent activity and swarm topology.
Inspect runs. Open logs and results, search, triage failures, replay and compare. Track models, tokens and cost. Missing measurements show n/a.
See what needs you. The Room brings approvals, questions, failures and finished work across local Claude Code, Codex and Ruflo sessions into a review queue with session previews.
Keep control. Choose read, write, manage or full permissions and ask or auto confirmation. Network, spending and destructive actions still require confirmation. Review the action log or press Take back control.
Keep context close. Explore memory, learning, security, diagnostics, project decisions and plugins. Some features require additional Ruflo components and configured providers.
Ruflo is open source. Model usage costs still apply. See the linked GitHub guide for setup details. Classic, plain and animated themes are optional.
The recorded session shows mission creation, navigation, a refused action and control being taken back. The explainer adds illustrative Seedance graphics. Neither proves completed swarm work or memory recall.
What is hardest to track with several agents: progress, failures, approvals or cost?