Introducing Kumo ADE, a workbench for agent collaboration and automation.
I was running Claude Code in one terminal and Codex in another, pasting output back and forth between them. So I built the tool I wanted:
→ Bring the agent CLIs you already use: Claude, Codex, Cursor, Gemini, Copilot and 10 more. Keys, models and MCP servers stay with each one.
→ @ an agent to hand it work. Its reply comes back to your thread.
→ Chain agents into Agentflows. A reviewer sends work back until it passes, and one flow takes a new issue all the way to an open PR.
→ Every task gets its own git worktree, so agents never touch each other's files.
→ Pair your phone once and keep going from the couch.
macOS · Apple Silicon
https://t.co/PKCqMjG4JU
Introducing Kumo ADE, a workbench for agent collaboration and automation.
I was running Claude Code in one terminal and Codex in another, pasting output back and forth between them. So I built the tool I wanted:
→ Bring the agent CLIs you already use: Claude, Codex, Cursor, Gemini, Copilot and 10 more. Keys, models and MCP servers stay with each one.
→ @ an agent to hand it work. Its reply comes back to your thread.
→ Chain agents into Agentflows. A reviewer sends work back until it passes, and one flow takes a new issue all the way to an open PR.
→ Every task gets its own git worktree, so agents never touch each other's files.
→ Pair your phone once and keep going from the couch.
macOS · Apple Silicon
https://t.co/PKCqMjG4JU
A new Stanford paper just proved that decentralized multi-agent systems can beat Claude Code and Codex on complex coding tasks, running up to 2.49× faster!
DeLM tackles a key bottleneck in multi-agent systems: time wasted repeating work and waiting on other agents.
DeLM replaces the central coordinating agent with a shared context and task queue. Agents pick up tasks independently, share discoveries as they happen, and build on each other’s progress. When one agent finds a solution or hits a dead end, the others can use that information immediately.
DeLM beats state-of-the-art in both speed and accuracy on long-horizon tasks from Terminal-Bench 4.0, DeepSWE v1.1, and ProgramBench:
- Up to 2.49× faster execution than the vanilla Claude Code and Codex baselines
- Up to +19.2 percentage points in accuracy over the vanilla Claude Code and Codex baselines
- Up to +19.9 points in ProgramBench test pass rate within the same 120-minute budget
Built on Codex and Claude Code. Code and 720 trajectories are available so you can explore how the agents collaborate! An open-source plugin lets you try DeLM directly in Codex and Claude Code.
Kumo ADE v0.27 is out.
→ Setup scripts: every new workspace installs its own deps before the agent starts. Hit Suggest and Kumo reads your repo and writes the script for you.
→ Status lights in the sidebar: see at a glance which workspace is running, which one needs you, and which one hit an error.
→ Reworked unread notifications: they live in the title bar now, color-coded by status. Open the list, jump to an agent, and ‹ takes you back.
→ Multi-select agents with ⇧/⌘ and close or reopen them in one go.
→ Tabs scroll instead of squeezing, and the composer tucks extra options into ⋯ in narrow panes.
→ Pressing Enter to pick a word in a Chinese/Japanese/Korean input method no longer sends the message.
Introducing Kumo ADE, a workbench for agent collaboration and automation.
I was running Claude Code in one terminal and Codex in another, pasting output back and forth between them. So I built the tool I wanted:
→ Bring the agent CLIs you already use: Claude, Codex, Cursor, Gemini, Copilot and 10 more. Keys, models and MCP servers stay with each one.
→ @ an agent to hand it work. Its reply comes back to your thread.
→ Chain agents into Agentflows. A reviewer sends work back until it passes, and one flow takes a new issue all the way to an open PR.
→ Every task gets its own git worktree, so agents never touch each other's files.
→ Pair your phone once and keep going from the couch.
macOS · Apple Silicon
https://t.co/PKCqMjG4JU
We’re rolling out monthly Claude Platform API credits for Max and Team plans:
Max 5x: $100
Max 20x: $200
Team: up to $500, pooled
Works on any model, including Haiku 5.5, in your code or third-party harnesses.
How it works and full terms: https://t.co/qmWL6xVGwr
Introducing Kumo ADE, a workbench for agent collaboration and automation.
I was running Claude Code in one terminal and Codex in another, pasting output back and forth between them. So I built the tool I wanted:
→ Bring the agent CLIs you already use: Claude, Codex, Cursor, Gemini, Copilot and 10 more. Keys, models and MCP servers stay with each one.
→ @ an agent to hand it work. Its reply comes back to your thread.
→ Chain agents into Agentflows. A reviewer sends work back until it passes, and one flow takes a new issue all the way to an open PR.
→ Every task gets its own git worktree, so agents never touch each other's files.
→ Pair your phone once and keep going from the couch.
macOS · Apple Silicon
https://t.co/PKCqMjG4JU
Introducing Kumo ADE, a workbench for agent collaboration and automation.
I was running Claude Code in one terminal and Codex in another, pasting output back and forth between them. So I built the tool I wanted:
→ Bring the agent CLIs you already use: Claude, Codex, Cursor, Gemini, Copilot and 10 more. Keys, models and MCP servers stay with each one.
→ @ an agent to hand it work. Its reply comes back to your thread.
→ Chain agents into Agentflows. A reviewer sends work back until it passes, and one flow takes a new issue all the way to an open PR.
→ Every task gets its own git worktree, so agents never touch each other's files.
→ Pair your phone once and keep going from the couch.
macOS · Apple Silicon
https://t.co/PKCqMjG4JU
1. Oh shit, AI can do my job better than me
2. Software engineering is dead!
3. I can vibe code as much slop as I want!
4. Oh, things are not going well. Fable/Sol/Opus all suuuck
5. But what if I constrain the agent? Put it in a straitjacket?
6. Oh, the results are pretty good now. How do I go deeper?
7. *Orders 12 software engineering books from Amazon*
8. Software engineering is alive!