Maestro is a cross-platform desktop app for orchestrating your fleet of AI agents and projects. It's a high-velocity solution for multitasking keyboard hackers.
Austin, TX
Joined February 2026
- Tweets647
- Following117
- Followers246
- Likes104
Pinned Tweet
Maestro is a desktop AI orchestrator built by hackers for hackers. We're only scratching the surface here, but check out this fun introduction video.
Big thanks to Ricky from Macbook Orchestra (@thepunchisfree) for putting this together for us! Appreciate the support 💜
Check out our battle cards, we feel very confident about our capabilities and are expanding every week:
runmaestro.ai/battle-cards/
Conductor is dead. Here are 69 alternatives. What are you using?
1. @orca_build · 115k★
2. T3 Code (@t3dotgg) · 47k★
3. Paseo (@moboudra) · 23k★
4. @useOrchestrator · 14k★
5. @paradevai · 16k★
6. cmux (@manaflowai) · 29k★
7. @emdashcom · 6.2k★
8. @RunMaestroAI · 3.5k★
9. @nimbalyst · 2k★
10. Zeron · 3.5k★
11. Jean (@heyandras) · 1.4k★
12. Xum (@codermux) · 2.1k★
13. @TraycerAI · 1.7k★
14. @get_bb_app · 4.9k★
15. Ghostex (@maddada) · 1.6k★
16. Kandev · 1.1k★
17. Parallel Code · 1.1k★
18. Supacode (@khoiracle) · 2.4k★
19. Termio · 752★
20. Pane (@parsakhaz) · 602★
21. Agent Teams AI · 2.4k★
22. wmux · 449★
23. OpenHarness (@autonomous_labs) · 1.4k★
24. Hive · 474★
25. Cate · 2.2k★
26. diri (@cristicrtu) · 483★
27. @NuphosAI · 351★
28. PandaCode · 1.1k★
29. @verdent_ai · 39k installs
30. Alethe · 1.1k★
31. agentglass · 347★
32. Waku (@localhost_5173) · 1.6k★
33. Kangentic · 139★
34. @vicoaai · 531★
35. ADE · 133★
36. Termic · 326★
37. Sculptor (@imbue_ai) · 245★
38. Poracode · 121★
39. DevThrottle · 107★
40. @zuse_sh · 243★
41. CCC · 215★
42. Agentbox · 345★
43. Hermes IDE · 346★
44. Maestri (@evertjr)
45. Termany (@idoubicc) · 498★
46. Frame (@jiuv__jiuv) · 455★
47. dev-3.0 · 324★
48. @usetempest · 196★
49. Kander (@dualface) · 171★
50. Prometeu · 65★
51. Frink · 183★
52. @superdoteng · 695 Discord
53. Lanes · 277★
54. Polyscope (@marcelpociot)
55. Agetor (@alamops) · 116★
56. Antumi · 94★
57. Ouijit · 177★
58. @agentastic
59. @glueprint_ai
60. @aidorothy1 · 357★
61. ManyAgents (@stulogy)
62. MAO (@miguerdotcom)
63. KanVibe · 149★
64. @veflowai
65. CodeAgentSwarm (@Art0xDev)
66. Tegment
67. Hyperlane
68. Jaade · 1.3k downloads
69. Muster
Your docs, laid out by when they last changed.
Maestro's Document Graph adds a Timeline layout: one column per last-modified date, links drawn across time. Point it at your agent's memories to see what it learned, and when.
Preview: Off shows names only.
A group chat moderator handing work to an agent that is already busy means two processes writing in one repo.
Maestro group chats now only work with agents that are free, on by default. Busy agents get skipped, and the chat says so.
Know what you are doing? Turn it off.
Your agent hits its session limit at midnight. The work stops until you notice.
Maestro now keeps retrying until the quota comes back, with a countdown to the next attempt. Try now or Stop whenever you like.
Honor roll 🎟️
First community conductor: @msuiche
First on the Maestro leaderboard after the founder, Dec 18 2025. Apprentice and Assistant Conductor inside 45 minutes.
Where it all started.
How much of your AI work actually runs without you?
Maestro's Usage Dashboard now has a Delegation Score: the share of agent time that came from Auto Runs and Cue pipelines instead of a prompt you typed and waited on.
A 500-line markdown file, and the section you want is somewhere in the middle.
In Maestro's markdown preview, press # and fuzzy search every heading. Enter jumps straight there. The table of contents button is still bottom right.
Honor roll 🎟️
Fastest climb on record: dr3
From first run to Chief Conductor, a month of unattended agent runtime, in 67 days. Nobody else has done it in under 260.
Your document graph or memory graph, as a picture.
A camera button in the bottom toolbar captures the graph exactly as it is on screen, preview pane included. Copy it to the clipboard or save a PNG.
Want to use the latest bleeding edge build? You can now download @pedramamini's build directly from the website.
Currently Pedram's build carries agent delegation, dictation, speech, local models with routing and system one support
New Maestro Cue trigger: Label Added. Put a label on a GitHub issue or PR and a pipeline starts.
Tag an issue for an agent and it picks it up. Maestro already turns user feedback into pull requests this way. It is building itself.
Honor roll 🎟️
Fastest to Principal Guest Conductor: @sounilyu
From 1 day to 1 week of unattended agent runtime in 3.0 days. Two agents' worth of work, every hour, three days straight.
Maestro's image annotator is not only for images you send to an agent.
Option+Cmd+E opens whatever is on your clipboard. Draw arrows, lines and shapes, change colors, and now crop. Hit Save and the edited image goes back to the clipboard.
Pick the coding agent, keep the workflow.
Maestro now supports 11 harnesses natively: Claude Code, Codex, OpenCode, Copilot CLI, Factory Droid, Grok CLI, Hermes, Pi, Oh My Pi, Antigravity CLI and Qwen3 Coder. Most are in beta.
Missing yours? Open a feature request on GitHub.
Honor roll 🎟️
First to Music Director: @ksylvan
Three months of unattended agent runtime. First human on Level 7, reached Sep 24.
Level 8 is still an open seat, Kayvan. 👀
Hundreds of tabs across dozens of agents. Which ones are waiting on you?
In Maestro, Opt+Cmd+Down jumps to the next unread or draft tab, and Unread Only trims both the agent list and the tab bar to just those.
Honor roll 🎟️
First to Chief Conductor: @PatrickRuddiman
A full month of unattended agent runtime, reached Feb 22. His climb from Level 5 took 11.8 days. The field median is 74.
Not every step of a playbook needs the top model. Reading the codebase is cheap; designing the change is not.
Maestro Auto Runs now switch model and effort per document and per task. Hover the pill to see why that level was picked.
A long Auto Run is drifting off course and you don't want to abort it.
Type a note into its Thought Stream. Maestro hands it to the agent at the start of the next task, and the run keeps going.
