Skip to main content

orchestra picker

eight questions, neutral recommendation across seven multi-agent CLI orchestrators. sometimes the answer is bernstein, sometimes it is claude squad, sometimes it is plain git worktrees and discipline. all client-side.

question 1 of 8

how many CLI agents do you want to run at the same time?

tools fork sharply at "many vs few".

comparison matrix

all data taken from the project README in May 2026; refreshed manually each quarter.

toolcostlicensedeterminismparallelaudit chainlearninglanguagemax agents
bernsteinfree / OSSApache 2.0yesyesHMAC-signedmediumpython40+
claude squadfree / OSSMITnoyessession log onlylowgo (tmux ui)~8 (tmux pane practical)
composio AOfree tier · paid scaleApache 2.0 (free tier)partialyesplatform logmediumpython / ts20+
awslabs CAOfree OSS · cloud billsApache 2.0partialyescloudwatch loghigh (AWS)typescript10+
manual git worktreefreen/amanualmanualnonelowshell1-2
conductorpaidproprietarypartialyesplatform loglowweb uitier-dependent
devin (cognition)paidproprietarynono (single agent)platform loglowcloud1 per session

how the picker works

each answer adjusts the score for every tool by a small integer weight. the tool with the highest sum wins; ties break alphabetically. bernstein deliberately has zero weight on questions where competitors are objectively stronger — for example, “cloud only” gives devin and composio AO an edge. the rule table lives at /lib/tools/orchestra-rules.ts in the bernstein-landing repo; PRs welcome when README docs update.

acceptance test: a simulation of 1000 random answer vectors must not pin more than 70% of recommendations on bernstein. when it does, the rules need rebalancing.