{"slug": "conductor", "name": "Conductor", "category": "ai-coding", "category_name": "AI coding tools", "description": "Desktop app for running multiple Claude Code and Codex agents in parallel git worktrees.", "recommenders": 11, "commenters": 23, "warners": 3, "score": 9.589, "rising": -2.27, "first": "2026-02-13", "latest": "2026-10-01", "why": "Recommended for managing several Claude Code and Codex agents at once in parallel git worktrees, with some commenters calling it their daily driver or adopting it across a team.", "why_is_quote": false, "has_verdict": true, "sentiment": {"recommend": 11, "neutral": 8, "compare": 2, "warn": 3}, "spark": [0, 0, 0, 1, 0, 2, 1, 5, 1, 0, 0, 1], "listed": true, "loved": ["Parallel worktrees", "Daily driver"], "caveat": "Cluttered UX", "short_quote": "my team and I are very heavy users of https://www.conductor.build .", "icon": true, "domain": "conductor.build", "github_repo": null, "official_url": "https://www.conductor.build", "pricing": "unknown", "aliases": ["Conductor"], "verdict": [{"text": "Recommended for managing several Claude Code and Codex agents at once in parallel git worktrees,", "cites": [{"id": 765877648, "item_id": 47867353, "url": "https://news.ycombinator.com/item?id=47867353", "by": "jamie_ca", "date": "2026-04-22", "stance": "recommend", "quote": "The best at that that I've found is Conductor", "excerpt": "I'm buying into this workflow more the more I use it, but the real gamechanger is (a) parallel threads in worktrees, with (b) enough lifecycle hooks to treat them similarly to spinning up a VM. Specifically for me that means that after I create a worktree I get some local config files copied over and Postgres duplicating my local dev and test databases so I can test in isolation, and then when I close out a worktree ", "context": "uses Copilot at work", "use_case": "parallel agents in worktrees", "switched_from": "", "story": "Parallel Agents in Zed"}, {"id": 774647395, "item_id": 48415462, "url": "https://news.ycombinator.com/item?id=48415462", "by": "AndreVitorio", "date": "2026-06-05", "stance": "recommend", "quote": "Then use Conductor for worktrees w/ Claude/Codex for mid-size tasks and code review.", "excerpt": "If you are teaching newbies, just get them into the Claude Code or Codex desktop apps. For devs: Claude, Codex and Cursor. All on the $20 subscription. Then use Conductor for worktrees w/ Claude/Codex for mid-size tasks and code review. Cursor for manual or small changes w/ Composer 2.5.", "context": "", "use_case": "worktrees, code review", "switched_from": "", "story": "Ask HN: What is your (AI) dev tech stack / workflow? (June 2026)"}, {"id": 775125234, "item_id": 48445327, "url": "https://news.ycombinator.com/item?id=48445327", "by": "bohdanstefaniuk", "date": "2026-06-08", "stance": "recommend", "quote": "Use cmux or conductor to manage multiple instances of Claude Code", "excerpt": "My approach to work on new project - Setup proper CLAUDE.md or AGENTS.md - Use cmux or conductor to manage multiple instances of Claude Code When working of some business feature I always ask AI to summarize every conversation in following format: problem, brief solution, where change were made. And I store it in the repo under \"journal\" folder where each file has \"2026-06-08-add-offile-firts-support.md\" Also for me ", "context": "", "use_case": "managing multiple Claude Code instances", "switched_from": "", "story": "Ask HN: What is the AI setup for an experienced dev starting on a new project?"}, {"id": 798825984, "item_id": 49926624, "url": "https://news.ycombinator.com/item?id=49926624", "by": "jacobgold", "date": "2026-10-01", "stance": "recommend", "quote": "I usually recommend Conductor to most people.", "excerpt": "The important thing is just to a GUI agent multiplexer, they're all mostly doing the same kind of thing. IMHO it's very important to have the official claude and codex harnesses (not just models). I also like having each session in a isolated container (or VM) so the agent can go wild and run in yolo mode. I usually recommend Conductor to most people. Personally, I use the one I built, but it's got a few ergonomic is", "context": "built their own agent multiplexer", "use_case": "GUI agent multiplexer", "switched_from": "", "story": "Pi 1.0"}]}, {"text": " with some commenters calling it their daily driver or adopting it across a team.", "cites": [{"id": 774629665, "item_id": 48414354, "url": "https://news.ycombinator.com/item?id=48414354", "by": "solumos", "date": "2026-06-05", "stance": "recommend", "quote": "I use Claude Opus 4.8 + Conductor as my daily driver", "excerpt": "Something different that other folks might not have thought of: Robust multi-environment infra deploy scripts that leverage terraform + AWS SSO I've found that converting stuff that's previously been very ops-cli heavy into very detailed skills has worked really really well. I use Claude Opus 4.8 + Conductor as my daily driver", "context": "", "use_case": "daily coding", "switched_from": "", "story": "Ask HN: What is your (AI) dev tech stack / workflow? (June 2026)"}, {"id": 781586976, "item_id": 48849186, "url": "https://news.ycombinator.com/item?id=48849186", "by": "dgritsko", "date": "2026-07-09", "stance": "recommend", "quote": "I use Conductor pretty much exclusively and it makes it incredibly easy to try different models", "excerpt": "I use Conductor pretty much exclusively and it makes it incredibly easy to try different models, even within the same workspace - definitely recommend giving it a shot. Whenever I'm forced to use the Claude Code app directly it just seems woefully inadequate compared to Conductor", "context": "", "use_case": "running coding agents with multiple models", "switched_from": "Claude Code", "story": "GPT-5.6"}, {"id": 761950144, "item_id": 47621884, "url": "https://news.ycombinator.com/item?id=47621884", "by": "dominicholmes", "date": "2026-04-02", "stance": "recommend", "quote": "my team and I are very heavy users of https://www.conductor.build .", "excerpt": "Wow, really negative comments here! I'm not a cursor user, and I can't say I love the look of this UI, but my team and I are very heavy users of https://www.conductor.build . Managing many agents, each in their own sandbox, felt like indisputably the future after using conductor for a day. We were a cursor company before conductor, but we cancelled all our seats around the time Opus 4.6 dropped because conductor was ", "context": "team lead, heavy agent user", "use_case": "managing many parallel coding agents", "switched_from": "Cursor", "story": "Cursor 3"}, {"id": 774700976, "item_id": 48418811, "url": "https://news.ycombinator.com/item?id=48418811", "by": "phildenhoff", "date": "2026-06-05", "stance": "recommend", "quote": "we've loved using Conductor here at Digits. I've been using it since February", "excerpt": "Hey -- we've loved using Conductor here at Digits. I've been using it since February and only recently swapped to using Orca for Remote SSH and perf improvements. Looking forward to your general release of Conductor Cloud! I've been wondering, since you're building desktop software, how do you get AI to test your changes? Boot the whole app? Run the frontend/UI with a mock backend?", "context": "works at Digits", "use_case": "running coding agents", "switched_from": "", "story": "Ask HN: What is your (AI) dev tech stack / workflow? (June 2026)"}]}, {"text": " Complaints vary rather than converge: some found its UX cluttered or clunky,", "cites": [{"id": 771836177, "item_id": 48239761, "url": "https://news.ycombinator.com/item?id=48239761", "by": "collin128", "date": "2026-05-22", "stance": "warn", "quote": "I really didn't like the extra stuff conductor added to the UX (the text rendering always drove me nuts).", "excerpt": "Just switched from Conductor to Superset and I'm a big fan. I really didn't like the extra stuff conductor added to the UX (the text rendering always drove me nuts). So far so good with Superset - even as a non-engineer builder.", "context": "Non-engineer builder", "use_case": "agent IDE", "switched_from": "", "story": "Launch HN: Superset (YC P26) \u2013 IDE for the agents era"}, {"id": 767193122, "item_id": 47949570, "url": "https://news.ycombinator.com/item?id=47949570", "by": "nzoschke", "date": "2026-04-29", "stance": "neutral", "quote": "I also use https://conductor.build/ and GitHub but this is starting to feel clunky", "excerpt": "Congrats! My daily driver is Zed developing on SSH remote servers on exe.dev. It's crazy to think of all the dev tools I've churned through over the last 18 months but these two feel sticky. Zed has everything I need in a unified pane. File editor, terminal, agents, SSH remotes. And it's fast and intuitive exe.dev is the first \"dev container\" I've ever *loved*. The remote sandbox means `dangerously-skip-permissions` ", "context": "", "use_case": "parallel coding agents", "switched_from": "", "story": "Zed is 1.0"}, {"id": 762007844, "item_id": 47625490, "url": "https://news.ycombinator.com/item?id=47625490", "by": "nocobot", "date": "2026-04-03", "stance": "warn", "quote": "haven't really been impressed", "excerpt": "i use tmux with one open session per project I'm working on. inside the session using nvim for edits, terminal panes for running tests / commands etc, and increasingly pi as a coding agent instead of claude code. i sometimes toy around with orchestration projects like capy.ai or conductor but haven't really been impressed. probably worth noting that usually all code i push will have been written by me. even if LLMs c", "context": "", "use_case": "agent orchestration", "switched_from": "", "story": "Ask HN: What is your dev set up like?"}]}, {"text": " and one disliked that it runs agents directly on the host instead of in a sandbox.", "cites": [{"id": 779468592, "item_id": 48716787, "url": "https://news.ycombinator.com/item?id=48716787", "by": "zavec", "date": "2026-06-29", "stance": "warn", "quote": "was not very jazzed about the fact that it was running the agents directly on the host", "excerpt": "I was just looking at conductor and was not very jazzed about the fact that it was running the agents directly on the host. Being able to launch from a terminal means this one can (hopefully) run from inside the sandboxing setup I use for coding agents.", "context": "runs coding agents in a sandboxing setup", "use_case": "running coding agents", "switched_from": "", "story": "Herdr: Agent multiplexer that lives in your terminal"}]}], "praise": [{"label": "Parallel worktrees", "summary": "Runs multiple coding agents side by side, each in its own git worktree.", "quotes": [{"id": 765877648, "item_id": 47867353, "url": "https://news.ycombinator.com/item?id=47867353", "by": "jamie_ca", "date": "2026-04-22", "stance": "recommend", "quote": "The best at that that I've found is Conductor", "excerpt": "I'm buying into this workflow more the more I use it, but the real gamechanger is (a) parallel threads in worktrees, with (b) enough lifecycle hooks to treat them similarly to spinning up a VM. Specifically for me that means that after I create a worktree I get some local config files copied over and Postgres duplicating my local dev and test databases so I can test in isolation, and then when I close out a worktree ", "context": "uses Copilot at work", "use_case": "parallel agents in worktrees", "switched_from": "", "story": "Parallel Agents in Zed"}, {"id": 774647395, "item_id": 48415462, "url": "https://news.ycombinator.com/item?id=48415462", "by": "AndreVitorio", "date": "2026-06-05", "stance": "recommend", "quote": "Then use Conductor for worktrees w/ Claude/Codex for mid-size tasks and code review.", "excerpt": "If you are teaching newbies, just get them into the Claude Code or Codex desktop apps. For devs: Claude, Codex and Cursor. All on the $20 subscription. Then use Conductor for worktrees w/ Claude/Codex for mid-size tasks and code review. Cursor for manual or small changes w/ Composer 2.5.", "context": "", "use_case": "worktrees, code review", "switched_from": "", "story": "Ask HN: What is your (AI) dev tech stack / workflow? (June 2026)"}, {"id": 775125234, "item_id": 48445327, "url": "https://news.ycombinator.com/item?id=48445327", "by": "bohdanstefaniuk", "date": "2026-06-08", "stance": "recommend", "quote": "Use cmux or conductor to manage multiple instances of Claude Code", "excerpt": "My approach to work on new project - Setup proper CLAUDE.md or AGENTS.md - Use cmux or conductor to manage multiple instances of Claude Code When working of some business feature I always ask AI to summarize every conversation in following format: problem, brief solution, where change were made. And I store it in the repo under \"journal\" folder where each file has \"2026-06-08-add-offile-firts-support.md\" Also for me ", "context": "", "use_case": "managing multiple Claude Code instances", "switched_from": "", "story": "Ask HN: What is the AI setup for an experienced dev starting on a new project?"}]}, {"label": "Daily driver", "summary": "Several commenters use it as their main tool for agentic coding.", "quotes": [{"id": 774629665, "item_id": 48414354, "url": "https://news.ycombinator.com/item?id=48414354", "by": "solumos", "date": "2026-06-05", "stance": "recommend", "quote": "I use Claude Opus 4.8 + Conductor as my daily driver", "excerpt": "Something different that other folks might not have thought of: Robust multi-environment infra deploy scripts that leverage terraform + AWS SSO I've found that converting stuff that's previously been very ops-cli heavy into very detailed skills has worked really really well. I use Claude Opus 4.8 + Conductor as my daily driver", "context": "", "use_case": "daily coding", "switched_from": "", "story": "Ask HN: What is your (AI) dev tech stack / workflow? (June 2026)"}, {"id": 781586976, "item_id": 48849186, "url": "https://news.ycombinator.com/item?id=48849186", "by": "dgritsko", "date": "2026-07-09", "stance": "recommend", "quote": "I use Conductor pretty much exclusively and it makes it incredibly easy to try different models", "excerpt": "I use Conductor pretty much exclusively and it makes it incredibly easy to try different models, even within the same workspace - definitely recommend giving it a shot. Whenever I'm forced to use the Claude Code app directly it just seems woefully inadequate compared to Conductor", "context": "", "use_case": "running coding agents with multiple models", "switched_from": "Claude Code", "story": "GPT-5.6"}, {"id": 790266839, "item_id": 49391677, "url": "https://news.ycombinator.com/item?id=49391677", "by": "nzoschke", "date": "2026-08-21", "stance": "neutral", "quote": "My daily drivers are still:", "excerpt": "How does this compare to https://github.com/pingdotgg/t3code or https://github.com/getpaseo/paseo? Is there a good resource indexing all the coding agent tools / harnesses? Every awesome list I've found so far seems very incomplete, but I'm sure its impossible to keep up. My daily drivers are still: - exe.dev + Shelley + terminal multiplexer (https://zmx.sh/ or tmux) + `codex` CLI - Conductor.build I would love an op", "context": "", "use_case": "daily coding agent workflow", "switched_from": "", "story": "Show HN: Proliferate- open-source, self-hostable Codex for any coding agent"}]}, {"label": "Team productivity", "summary": "Teams report heavy use, with one dropping Cursor seats for it.", "quotes": [{"id": 761950144, "item_id": 47621884, "url": "https://news.ycombinator.com/item?id=47621884", "by": "dominicholmes", "date": "2026-04-02", "stance": "recommend", "quote": "my team and I are very heavy users of https://www.conductor.build .", "excerpt": "Wow, really negative comments here! I'm not a cursor user, and I can't say I love the look of this UI, but my team and I are very heavy users of https://www.conductor.build . Managing many agents, each in their own sandbox, felt like indisputably the future after using conductor for a day. We were a cursor company before conductor, but we cancelled all our seats around the time Opus 4.6 dropped because conductor was ", "context": "team lead, heavy agent user", "use_case": "managing many parallel coding agents", "switched_from": "Cursor", "story": "Cursor 3"}, {"id": 774700976, "item_id": 48418811, "url": "https://news.ycombinator.com/item?id=48418811", "by": "phildenhoff", "date": "2026-06-05", "stance": "recommend", "quote": "we've loved using Conductor here at Digits. I've been using it since February", "excerpt": "Hey -- we've loved using Conductor here at Digits. I've been using it since February and only recently swapped to using Orca for Remote SSH and perf improvements. Looking forward to your general release of Conductor Cloud! I've been wondering, since you're building desktop software, how do you get AI to test your changes? Boot the whole app? Run the frontend/UI with a mock backend?", "context": "works at Digits", "use_case": "running coding agents", "switched_from": "", "story": "Ask HN: What is your (AI) dev tech stack / workflow? (June 2026)"}, {"id": 798774144, "item_id": 49923384, "url": "https://news.ycombinator.com/item?id=49923384", "by": "cbzehner", "date": "2026-10-01", "stance": "neutral", "quote": "Engineers use Conductor, stacked PRs, Linear, and multiple frontier models every day", "excerpt": "Fazeshift | Senior Software Engineer | San Francisco, CA | ONSITE (5 days/week) | Full-time | $200k\u2013$235k + equity I\u2019m Chris, VP Engineering at Fazeshift. We\u2019re nine engineers plus our Founder/CTO and me, and I\u2019m hiring someone who can help us do more, better: increase both what we can build and the quality and sophistication of the software we build. Accounts receivable sounds boring until you look under the hood. I", "context": "VP Engineering at Fazeshift", "use_case": "coding agent workflow", "switched_from": "", "story": "Ask HN: Who is hiring? (October 2026)"}]}, {"label": "Model switching", "summary": "Makes it easy to try different models, even within one workspace.", "quotes": [{"id": 781586976, "item_id": 48849186, "url": "https://news.ycombinator.com/item?id=48849186", "by": "dgritsko", "date": "2026-07-09", "stance": "recommend", "quote": "I use Conductor pretty much exclusively and it makes it incredibly easy to try different models", "excerpt": "I use Conductor pretty much exclusively and it makes it incredibly easy to try different models, even within the same workspace - definitely recommend giving it a shot. Whenever I'm forced to use the Claude Code app directly it just seems woefully inadequate compared to Conductor", "context": "", "use_case": "running coding agents with multiple models", "switched_from": "Claude Code", "story": "GPT-5.6"}]}, {"label": "Lifecycle hooks", "summary": "Worktree setup and teardown hooks allow isolated databases and config per task.", "quotes": [{"id": 765877648, "item_id": 47867353, "url": "https://news.ycombinator.com/item?id=47867353", "by": "jamie_ca", "date": "2026-04-22", "stance": "recommend", "quote": "The best at that that I've found is Conductor", "excerpt": "I'm buying into this workflow more the more I use it, but the real gamechanger is (a) parallel threads in worktrees, with (b) enough lifecycle hooks to treat them similarly to spinning up a VM. Specifically for me that means that after I create a worktree I get some local config files copied over and Postgres duplicating my local dev and test databases so I can test in isolation, and then when I close out a worktree ", "context": "uses Copilot at work", "use_case": "parallel agents in worktrees", "switched_from": "", "story": "Parallel Agents in Zed"}]}], "caveats": [{"label": "Cluttered UX", "summary": "Some found the interface clunky or disliked its text rendering.", "quotes": [{"id": 771836177, "item_id": 48239761, "url": "https://news.ycombinator.com/item?id=48239761", "by": "collin128", "date": "2026-05-22", "stance": "warn", "quote": "I really didn't like the extra stuff conductor added to the UX (the text rendering always drove me nuts).", "excerpt": "Just switched from Conductor to Superset and I'm a big fan. I really didn't like the extra stuff conductor added to the UX (the text rendering always drove me nuts). So far so good with Superset - even as a non-engineer builder.", "context": "Non-engineer builder", "use_case": "agent IDE", "switched_from": "", "story": "Launch HN: Superset (YC P26) \u2013 IDE for the agents era"}, {"id": 767193122, "item_id": 47949570, "url": "https://news.ycombinator.com/item?id=47949570", "by": "nzoschke", "date": "2026-04-29", "stance": "neutral", "quote": "I also use https://conductor.build/ and GitHub but this is starting to feel clunky", "excerpt": "Congrats! My daily driver is Zed developing on SSH remote servers on exe.dev. It's crazy to think of all the dev tools I've churned through over the last 18 months but these two feel sticky. Zed has everything I need in a unified pane. File editor, terminal, agents, SSH remotes. And it's fast and intuitive exe.dev is the first \"dev container\" I've ever *loved*. The remote sandbox means `dangerously-skip-permissions` ", "context": "", "use_case": "parallel coding agents", "switched_from": "", "story": "Zed is 1.0"}]}, {"label": "Underwhelming", "summary": "One commenter tried it and was not impressed.", "quotes": [{"id": 762007844, "item_id": 47625490, "url": "https://news.ycombinator.com/item?id=47625490", "by": "nocobot", "date": "2026-04-03", "stance": "warn", "quote": "haven't really been impressed", "excerpt": "i use tmux with one open session per project I'm working on. inside the session using nvim for edits, terminal panes for running tests / commands etc, and increasingly pi as a coding agent instead of claude code. i sometimes toy around with orchestration projects like capy.ai or conductor but haven't really been impressed. probably worth noting that usually all code i push will have been written by me. even if LLMs c", "context": "", "use_case": "agent orchestration", "switched_from": "", "story": "Ask HN: What is your dev set up like?"}]}, {"label": "No sandboxing", "summary": "Agents run directly on the host machine rather than in a sandbox.", "quotes": [{"id": 779468592, "item_id": 48716787, "url": "https://news.ycombinator.com/item?id=48716787", "by": "zavec", "date": "2026-06-29", "stance": "warn", "quote": "was not very jazzed about the fact that it was running the agents directly on the host", "excerpt": "I was just looking at conductor and was not very jazzed about the fact that it was running the agents directly on the host. Being able to launch from a terminal means this one can (hopefully) run from inside the sandboxing setup I use for coding agents.", "context": "runs coding agents in a sandboxing setup", "use_case": "running coding agents", "switched_from": "", "story": "Herdr: Agent multiplexer that lives in your terminal"}]}, {"label": "Backend lock-in", "summary": "It works with Claude and Codex backends, so a Copilot-only workplace could not use it.", "quotes": [{"id": 765877648, "item_id": 47867353, "url": "https://news.ycombinator.com/item?id=47867353", "by": "jamie_ca", "date": "2026-04-22", "stance": "recommend", "quote": "The best at that that I've found is Conductor", "excerpt": "I'm buying into this workflow more the more I use it, but the real gamechanger is (a) parallel threads in worktrees, with (b) enough lifecycle hooks to treat them similarly to spinning up a VM. Specifically for me that means that after I create a worktree I get some local config files copied over and Postgres duplicating my local dev and test databases so I can test in isolation, and then when I close out a worktree ", "context": "uses Copilot at work", "use_case": "parallel agents in worktrees", "switched_from": "", "story": "Parallel Agents in Zed"}]}, {"label": "Remote and performance", "summary": "One user switched to another tool for remote SSH support and better performance.", "quotes": [{"id": 774700976, "item_id": 48418811, "url": "https://news.ycombinator.com/item?id=48418811", "by": "phildenhoff", "date": "2026-06-05", "stance": "recommend", "quote": "we've loved using Conductor here at Digits. I've been using it since February", "excerpt": "Hey -- we've loved using Conductor here at Digits. I've been using it since February and only recently swapped to using Orca for Remote SSH and perf improvements. Looking forward to your general release of Conductor Cloud! I've been wondering, since you're building desktop software, how do you get AI to test your changes? Boot the whole app? Run the frontend/UI with a mock backend?", "context": "works at Digits", "use_case": "running coding agents", "switched_from": "", "story": "Ask HN: What is your (AI) dev tech stack / workflow? (June 2026)"}]}, {"label": "GUI over terminal", "summary": "Terminal-focused users built alternatives that fit tools like tmux, neovim and lazygit.", "quotes": [{"id": 776530305, "item_id": 48533144, "url": "https://news.ycombinator.com/item?id=48533144", "by": "bakedbean", "date": "2026-06-14", "stance": "neutral", "quote": "born out of using Conductor and similar tools but preferring to work in the terminal", "excerpt": "I'm working on (yet another) git worktree multi agent development tool that just runs in any terminal. Supports Claude Code, Pi and Codex agents and provides a CLI that allows them to work together in a given worktree. Currently messing around with having the agent drive the app itself to record and caption screencasts. Fun project that is also my daily driver for agentic development at the day job. Idea was born out", "context": "", "use_case": "agent orchestration", "switched_from": "", "story": "Ask HN: What are you working on? (June 2026)"}, {"id": 775311681, "item_id": 48456980, "url": "https://news.ycombinator.com/item?id=48456980", "by": "hboon", "date": "2026-06-08", "stance": "compare", "quote": "I prefer to run sessions for the same project serially, working on main, rather than in parallel like how Conductor does with the help of worktrees.", "excerpt": "An inhouse orchestration tool to run coding agents. It's so useful. I used to use tmux to run my coding agents and have little scripts to help me manage the workflow so this tool lets me encode my workflows and preferences. eg. I prefer to run sessions for the same project serially, working on main, rather than in parallel like how Conductor does with the help of worktrees.", "context": "", "use_case": "running coding agents", "switched_from": "", "story": "Ask HN: What are tools you have made for yourself since the advent of AI"}]}], "who": [{"by": "jacobgold", "context": "built their own agent multiplexer", "url": "https://news.ycombinator.com/item?id=49926624", "date": "2026-10-01"}, {"by": "cbzehner", "context": "VP Engineering at Fazeshift", "url": "https://news.ycombinator.com/item?id=49923384", "date": "2026-10-01"}, {"by": "malisper", "context": "built pgrust", "url": "https://news.ycombinator.com/item?id=48852900", "date": "2026-07-09"}, {"by": "phildenhoff", "context": "works at Digits", "url": "https://news.ycombinator.com/item?id=48418811", "date": "2026-06-05"}, {"by": "jamie_ca", "context": "uses Copilot at work", "url": "https://news.ycombinator.com/item?id=47867353", "date": "2026-04-22"}, {"by": "dominicholmes", "context": "team lead, heavy agent user", "url": "https://news.ycombinator.com/item?id=47621884", "date": "2026-04-02"}, {"by": "martinald", "context": "Mac and WSL2 user", "url": "https://news.ycombinator.com/item?id=47144145", "date": "2026-02-24"}], "tags": ["for parallel agent workflows", "for Claude Code and Codex users", "for teams"], "use_cases": ["running coding agents", "workflow orchestration", "agent orchestration", "parallel coding agents", "gui agent multiplexer", "coding agent workflow"], "compared": [{"slug": "claude-code", "name": "Claude Code", "co": 5, "switched_from": 1, "switched_to": 0}, {"slug": "cursor", "name": "Cursor", "co": 3, "switched_from": 1, "switched_to": 0}, {"slug": "zed", "name": "Zed", "co": 3, "switched_from": 0, "switched_to": 0}, {"slug": "tmux", "name": "tmux", "co": 3, "switched_from": 0, "switched_to": 0}, {"slug": "orca", "name": "Orca", "co": 1, "switched_from": 0, "switched_to": 1}, {"slug": "superset", "name": "Superset", "co": 1, "switched_from": 0, "switched_to": 1}, {"slug": "neovim", "name": "Neovim", "co": 3, "switched_from": 0, "switched_to": 0}], "makers": [{"id": 774658400, "item_id": 48416150, "url": "https://news.ycombinator.com/item?id=48416150", "by": "Charlieholtz", "date": "2026-06-05", "stance": "recommend", "quote": "I'm biased (I'm the creator) but I use Conductor every day.", "excerpt": "I'm biased (I'm the creator) but I use Conductor every day. I've recently switched to Opus 4.8 (fast mode always on) as my default model but swap in GPT-5.5 quite a bit for reviewing Opus's work. My flow is something like: - Create a new workspace for a specific bug/feature - Ramble into the input box. I use a goose neck microphone and Spokenly (with Parakeet as the model ) for local speech-to-text - Hit enter! I don", "context": "creator of Conductor", "use_case": "parallel coding agent workspaces", "switched_from": "", "story": "Ask HN: What is your (AI) dev tech stack / workflow? (June 2026)"}], "threads": [{"url": "https://news.ycombinator.com/item?id=48413629", "title": "Ask HN: What is your (AI) dev tech stack / workflow? (June 2026)", "mentions": 4}, {"url": "https://news.ycombinator.com/item?id=49926069", "title": "Pi 1.0", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49922569", "title": "Ask HN: Who is hiring? (October 2026)", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49391630", "title": "Netflix Conductor: The Next Chapter", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49390739", "title": "Show HN: Proliferate- open-source, self-hostable Codex for any coding agent", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48841676", "title": "Postgres rewritten in Rust, now passing 100% of the Postgres regression tests", "mentions": 1}], "sentiment_by_month": {"2025-11": {}, "2025-12": {}, "2026-01": {}, "2026-02": {"neutral": 1, "recommend": 1, "compare": 1}, "2026-03": {"neutral": 1}, "2026-04": {"recommend": 2, "warn": 1, "neutral": 1}, "2026-05": {"warn": 1, "recommend": 1}, "2026-06": {"recommend": 5, "compare": 1, "neutral": 1, "warn": 1}, "2026-07": {"recommend": 1, "neutral": 1}, "2026-08": {"neutral": 2}, "2026-09": {}, "2026-10": {"neutral": 1, "recommend": 1}}, "quotes": [{"id": 798825984, "item_id": 49926624, "url": "https://news.ycombinator.com/item?id=49926624", "by": "jacobgold", "date": "2026-10-01", "stance": "recommend", "quote": "I usually recommend Conductor to most people.", "excerpt": "The important thing is just to a GUI agent multiplexer, they're all mostly doing the same kind of thing. IMHO it's very important to have the official claude and codex harnesses (not just models). I also like having each session in a isolated container (or VM) so the agent can go wild and run in yolo mode. I usually recommend Conductor to most people. Personally, I use the one I built, but it's got a few ergonomic is", "context": "built their own agent multiplexer", "use_case": "GUI agent multiplexer", "switched_from": "", "story": "Pi 1.0"}, {"id": 798774144, "item_id": 49923384, "url": "https://news.ycombinator.com/item?id=49923384", "by": "cbzehner", "date": "2026-10-01", "stance": "neutral", "quote": "Engineers use Conductor, stacked PRs, Linear, and multiple frontier models every day", "excerpt": "Fazeshift | Senior Software Engineer | San Francisco, CA | ONSITE (5 days/week) | Full-time | $200k\u2013$235k + equity I\u2019m Chris, VP Engineering at Fazeshift. We\u2019re nine engineers plus our Founder/CTO and me, and I\u2019m hiring someone who can help us do more, better: increase both what we can build and the quality and sophistication of the software we build. Accounts receivable sounds boring until you look under the hood. I", "context": "VP Engineering at Fazeshift", "use_case": "coding agent workflow", "switched_from": "", "story": "Ask HN: Who is hiring? (October 2026)"}, {"id": 790269360, "item_id": 49391835, "url": "https://news.ycombinator.com/item?id=49391835", "by": "opiniateddev", "date": "2026-08-21", "stance": "neutral", "quote": "The open source continues to live:", "excerpt": "The open source continues to live: https://github.com/conductor-oss/conductor", "context": "", "use_case": "workflow orchestration", "switched_from": "", "story": "Netflix Conductor: The Next Chapter"}, {"id": 790266839, "item_id": 49391677, "url": "https://news.ycombinator.com/item?id=49391677", "by": "nzoschke", "date": "2026-08-21", "stance": "neutral", "quote": "My daily drivers are still:", "excerpt": "How does this compare to https://github.com/pingdotgg/t3code or https://github.com/getpaseo/paseo? Is there a good resource indexing all the coding agent tools / harnesses? Every awesome list I've found so far seems very incomplete, but I'm sure its impossible to keep up. My daily drivers are still: - exe.dev + Shelley + terminal multiplexer (https://zmx.sh/ or tmux) + `codex` CLI - Conductor.build I would love an op", "context": "", "use_case": "daily coding agent workflow", "switched_from": "", "story": "Show HN: Proliferate- open-source, self-hostable Codex for any coding agent"}, {"id": 781646401, "item_id": 48852900, "url": "https://news.ycombinator.com/item?id=48852900", "by": "malisper", "date": "2026-07-09", "stance": "neutral", "quote": "Initially I was doing parallel coding sessions with Conductor.", "excerpt": "My approach has changed throughout the course of this project. Throughout most of the project, we were working off of a c2rust translation of Postgres to Rust. That gave us a bunch of Rust code that was unsafe but did pass the Postgres test suite and was fast. c2rust had split Postgres into 1000 different crates. We then went through 1 by 1 and rewrote each crate into idiomatic rust. This naturally lended itself to a", "context": "built pgrust", "use_case": "parallel coding sessions", "switched_from": "", "story": "Postgres rewritten in Rust, now passing 100% of the Postgres regression tests"}, {"id": 781586976, "item_id": 48849186, "url": "https://news.ycombinator.com/item?id=48849186", "by": "dgritsko", "date": "2026-07-09", "stance": "recommend", "quote": "I use Conductor pretty much exclusively and it makes it incredibly easy to try different models", "excerpt": "I use Conductor pretty much exclusively and it makes it incredibly easy to try different models, even within the same workspace - definitely recommend giving it a shot. Whenever I'm forced to use the Claude Code app directly it just seems woefully inadequate compared to Conductor", "context": "", "use_case": "running coding agents with multiple models", "switched_from": "Claude Code", "story": "GPT-5.6"}, {"id": 779468592, "item_id": 48716787, "url": "https://news.ycombinator.com/item?id=48716787", "by": "zavec", "date": "2026-06-29", "stance": "warn", "quote": "was not very jazzed about the fact that it was running the agents directly on the host", "excerpt": "I was just looking at conductor and was not very jazzed about the fact that it was running the agents directly on the host. Being able to launch from a terminal means this one can (hopefully) run from inside the sandboxing setup I use for coding agents.", "context": "runs coding agents in a sandboxing setup", "use_case": "running coding agents", "switched_from": "", "story": "Herdr: Agent multiplexer that lives in your terminal"}, {"id": 779041696, "item_id": 48690106, "url": "https://news.ycombinator.com/item?id=48690106", "by": "bloomfieldj", "date": "2026-06-26", "stance": "recommend", "quote": "I use a mix of Conductor and Repoprompt!", "excerpt": "I use a mix of Conductor and Repoprompt! https://github.com/repoprompt/repoprompt-ce", "context": "", "use_case": "coding agents", "switched_from": "", "story": null}, {"id": 776530305, "item_id": 48533144, "url": "https://news.ycombinator.com/item?id=48533144", "by": "bakedbean", "date": "2026-06-14", "stance": "neutral", "quote": "born out of using Conductor and similar tools but preferring to work in the terminal", "excerpt": "I'm working on (yet another) git worktree multi agent development tool that just runs in any terminal. Supports Claude Code, Pi and Codex agents and provides a CLI that allows them to work together in a given worktree. Currently messing around with having the agent drive the app itself to record and caption screencasts. Fun project that is also my daily driver for agentic development at the day job. Idea was born out", "context": "", "use_case": "agent orchestration", "switched_from": "", "story": "Ask HN: What are you working on? (June 2026)"}, {"id": 775311681, "item_id": 48456980, "url": "https://news.ycombinator.com/item?id=48456980", "by": "hboon", "date": "2026-06-08", "stance": "compare", "quote": "I prefer to run sessions for the same project serially, working on main, rather than in parallel like how Conductor does with the help of worktrees.", "excerpt": "An inhouse orchestration tool to run coding agents. It's so useful. I used to use tmux to run my coding agents and have little scripts to help me manage the workflow so this tool lets me encode my workflows and preferences. eg. I prefer to run sessions for the same project serially, working on main, rather than in parallel like how Conductor does with the help of worktrees.", "context": "", "use_case": "running coding agents", "switched_from": "", "story": "Ask HN: What are tools you have made for yourself since the advent of AI"}, {"id": 775125234, "item_id": 48445327, "url": "https://news.ycombinator.com/item?id=48445327", "by": "bohdanstefaniuk", "date": "2026-06-08", "stance": "recommend", "quote": "Use cmux or conductor to manage multiple instances of Claude Code", "excerpt": "My approach to work on new project - Setup proper CLAUDE.md or AGENTS.md - Use cmux or conductor to manage multiple instances of Claude Code When working of some business feature I always ask AI to summarize every conversation in following format: problem, brief solution, where change were made. And I store it in the repo under \"journal\" folder where each file has \"2026-06-08-add-offile-firts-support.md\" Also for me ", "context": "", "use_case": "managing multiple Claude Code instances", "switched_from": "", "story": "Ask HN: What is the AI setup for an experienced dev starting on a new project?"}, {"id": 774700976, "item_id": 48418811, "url": "https://news.ycombinator.com/item?id=48418811", "by": "phildenhoff", "date": "2026-06-05", "stance": "recommend", "quote": "we've loved using Conductor here at Digits. I've been using it since February", "excerpt": "Hey -- we've loved using Conductor here at Digits. I've been using it since February and only recently swapped to using Orca for Remote SSH and perf improvements. Looking forward to your general release of Conductor Cloud! I've been wondering, since you're building desktop software, how do you get AI to test your changes? Boot the whole app? Run the frontend/UI with a mock backend?", "context": "works at Digits", "use_case": "running coding agents", "switched_from": "", "story": "Ask HN: What is your (AI) dev tech stack / workflow? (June 2026)"}, {"id": 774647395, "item_id": 48415462, "url": "https://news.ycombinator.com/item?id=48415462", "by": "AndreVitorio", "date": "2026-06-05", "stance": "recommend", "quote": "Then use Conductor for worktrees w/ Claude/Codex for mid-size tasks and code review.", "excerpt": "If you are teaching newbies, just get them into the Claude Code or Codex desktop apps. For devs: Claude, Codex and Cursor. All on the $20 subscription. Then use Conductor for worktrees w/ Claude/Codex for mid-size tasks and code review. Cursor for manual or small changes w/ Composer 2.5.", "context": "", "use_case": "worktrees, code review", "switched_from": "", "story": "Ask HN: What is your (AI) dev tech stack / workflow? (June 2026)"}, {"id": 774629665, "item_id": 48414354, "url": "https://news.ycombinator.com/item?id=48414354", "by": "solumos", "date": "2026-06-05", "stance": "recommend", "quote": "I use Claude Opus 4.8 + Conductor as my daily driver", "excerpt": "Something different that other folks might not have thought of: Robust multi-environment infra deploy scripts that leverage terraform + AWS SSO I've found that converting stuff that's previously been very ops-cli heavy into very detailed skills has worked really really well. I use Claude Opus 4.8 + Conductor as my daily driver", "context": "", "use_case": "daily coding", "switched_from": "", "story": "Ask HN: What is your (AI) dev tech stack / workflow? (June 2026)"}, {"id": 773338160, "item_id": 48333635, "url": "https://news.ycombinator.com/item?id=48333635", "by": "burner_acc001", "date": "2026-05-30", "stance": "recommend", "quote": "give conductor a try.  runs with sqlite or if you want to run it on a server mysql or postgres.", "excerpt": "give conductor a try. runs with sqlite or if you want to run it on a server mysql or postgres. I know people running with postgres with a decent scale and it works just fine. https://docs.conductor-oss.org/", "context": "", "use_case": "workflow orchestration", "switched_from": "", "story": "SQLite is all you need for durable workflows"}, {"id": 771836177, "item_id": 48239761, "url": "https://news.ycombinator.com/item?id=48239761", "by": "collin128", "date": "2026-05-22", "stance": "warn", "quote": "I really didn't like the extra stuff conductor added to the UX (the text rendering always drove me nuts).", "excerpt": "Just switched from Conductor to Superset and I'm a big fan. I really didn't like the extra stuff conductor added to the UX (the text rendering always drove me nuts). So far so good with Superset - even as a non-engineer builder.", "context": "Non-engineer builder", "use_case": "agent IDE", "switched_from": "", "story": "Launch HN: Superset (YC P26) \u2013 IDE for the agents era"}, {"id": 767193122, "item_id": 47949570, "url": "https://news.ycombinator.com/item?id=47949570", "by": "nzoschke", "date": "2026-04-29", "stance": "neutral", "quote": "I also use https://conductor.build/ and GitHub but this is starting to feel clunky", "excerpt": "Congrats! My daily driver is Zed developing on SSH remote servers on exe.dev. It's crazy to think of all the dev tools I've churned through over the last 18 months but these two feel sticky. Zed has everything I need in a unified pane. File editor, terminal, agents, SSH remotes. And it's fast and intuitive exe.dev is the first \"dev container\" I've ever *loved*. The remote sandbox means `dangerously-skip-permissions` ", "context": "", "use_case": "parallel coding agents", "switched_from": "", "story": "Zed is 1.0"}, {"id": 765877648, "item_id": 47867353, "url": "https://news.ycombinator.com/item?id=47867353", "by": "jamie_ca", "date": "2026-04-22", "stance": "recommend", "quote": "The best at that that I've found is Conductor", "excerpt": "I'm buying into this workflow more the more I use it, but the real gamechanger is (a) parallel threads in worktrees, with (b) enough lifecycle hooks to treat them similarly to spinning up a VM. Specifically for me that means that after I create a worktree I get some local config files copied over and Postgres duplicating my local dev and test databases so I can test in isolation, and then when I close out a worktree ", "context": "uses Copilot at work", "use_case": "parallel agents in worktrees", "switched_from": "", "story": "Parallel Agents in Zed"}, {"id": 762007844, "item_id": 47625490, "url": "https://news.ycombinator.com/item?id=47625490", "by": "nocobot", "date": "2026-04-03", "stance": "warn", "quote": "haven't really been impressed", "excerpt": "i use tmux with one open session per project I'm working on. inside the session using nvim for edits, terminal panes for running tests / commands etc, and increasingly pi as a coding agent instead of claude code. i sometimes toy around with orchestration projects like capy.ai or conductor but haven't really been impressed. probably worth noting that usually all code i push will have been written by me. even if LLMs c", "context": "", "use_case": "agent orchestration", "switched_from": "", "story": "Ask HN: What is your dev set up like?"}, {"id": 761950144, "item_id": 47621884, "url": "https://news.ycombinator.com/item?id=47621884", "by": "dominicholmes", "date": "2026-04-02", "stance": "recommend", "quote": "my team and I are very heavy users of https://www.conductor.build .", "excerpt": "Wow, really negative comments here! I'm not a cursor user, and I can't say I love the look of this UI, but my team and I are very heavy users of https://www.conductor.build . Managing many agents, each in their own sandbox, felt like indisputably the future after using conductor for a day. We were a cursor company before conductor, but we cancelled all our seats around the time Opus 4.6 dropped because conductor was ", "context": "team lead, heavy agent user", "use_case": "managing many parallel coding agents", "switched_from": "Cursor", "story": "Cursor 3"}, {"id": 760754288, "item_id": 47547143, "url": "https://news.ycombinator.com/item?id=47547143", "by": "eloga", "date": "2026-03-27", "stance": "neutral", "quote": "I use Conductor personally.", "excerpt": "I use Conductor personally. At work I use worktrunk. But I like your web based approach. Do you plan to have worktrees support anytime soon. I would be a killer feature for me!", "context": "", "use_case": "personal agent workflow", "switched_from": "", "story": "Show HN: Kanna \u2013 OSS Web UI for Claude Code and Codex with Embedded Terminals"}, {"id": 754689809, "item_id": 47168113, "url": "https://news.ycombinator.com/item?id=47168113", "by": "jcjmcclean", "date": "2026-02-26", "stance": "compare", "quote": "How does it compare to Conductor?", "excerpt": "Very cool. I'll definitely give this a try. I'd say code review is the most important part of a tool like this for me. How does it compare to Conductor?", "context": "", "use_case": "parallel coding agents", "switched_from": "", "story": "Show HN: DevSwarm 2.0, fix parallel Claude Code sprawl"}, {"id": 754306320, "item_id": 47144145, "url": "https://news.ycombinator.com/item?id=47144145", "by": "martinald", "date": "2026-02-24", "stance": "recommend", "quote": "I love Conductor on my Mac", "excerpt": "Thanks. Btw, doesn't work at all for me. I installed, tried to connect to my WSL2 instance on localhost via SSH, which worked. Selected a folder and got Claude Code is not installed (it is very much installed :)). Then tried running the Linux version on WSL2 (not ideal because the wayland server on WSL2 is slow) - doesn't work. This 404s: https://github.com/generalaction/emdash/releases/download/v0.4.17/emdash-x64.de", "context": "Mac and WSL2 user", "use_case": "running coding agents", "switched_from": "", "story": "Show HN: Emdash \u2013 Open-source agentic development environment"}, {"id": 752064082, "item_id": 47004005, "url": "https://news.ycombinator.com/item?id=47004005", "by": "pkilgore", "date": "2026-02-13", "stance": "neutral", "quote": "sitting in Claude / https://www.conductor.build", "excerpt": "As far as I can tell, no. I moved to zed from nvim for fast starts + better AI UX with edit prediction & agents than nvim without start time/RAM of cursor. It delivered on that, but now that I think about it my coding practices have changed so much since that decision (sitting in Claude / https://www.conductor.build) I should probably just go back to nvim!", "context": "", "use_case": "running Claude coding agents", "switched_from": "", "story": "Zed editor switching graphics lib from blade to wgpu"}]}