Run a coordinated team of AI agents in parallel — with git worktree isolation, inter-agent messaging, and state machine governance. No cloud. No config files. One npm install.
The coordination problem
You copy-paste output between AI tools manually. Context gets lost. Mistakes compound.
productivity killerAgents message each other directly. Context flows through shared store and prompt injection.
coordinatedParallel agents overwrite each other's files. Merge conflicts pile up. Work gets lost.
wasted effortEach agent gets its own git worktree. Parallel execution without file conflicts. Auto merge-back.
safe parallelismNo review process. No state tracking. A failed run leaves broken state with no way back.
high riskEvery task flows through todo → in_progress → review → done. Nothing gets lost.
Most tools require cloud accounts and send your code to external servers. No control over your data.
vendor dependencyEverything runs on your machine. State stored in .orchestry/ as YAML, JSON, JSONL. Git clone and run.
You wait for each AI run to finish. No parallel execution. No automatic retries when things fail.
time sinkThe orchestrator dispatches, monitors, retries with backoff, and merges — unattended. You review the results.
automatedSee for yourself
Real-time TUI dashboard with task management, agent activity feed, team coordination, and inter-agent messaging.
Ready to orchestrate? One command to install. One command to start.
Get StartedAgents that communicate, coordinate, and build on each other's work — like a real engineering team.
Set a high-level goal. Agents decompose it into tasks and execute without hand-holding.
Every transition validated. Every agent isolated. Every change reviewed before merge.
todo → in_progress → review → doneFull-screen TUI, rework loops, and zero infrastructure. Clone and run.
.orchestry/Only in ORCH
Stop running agents in isolation. Build coordinated teams where agents communicate, share discoveries, and delegate subtasks — minus the standups.
How it works
One package, no dependencies. Ready in seconds.
npm i -g @oxgeneral/orchAdd tasks with scopes, priorities, and agent assignments — or let ORCH auto-assign.
orch task addAgents execute in parallel on isolated worktrees, messaging and sharing context.
orch run --all --watchApprove, reject with feedback, or let auto merge-back close the loop.
orch task review --approveBuilt for every workflow
Define your vision as a goal. ORCH spins up backend, frontend, QA, and reviewer agents that build your API, UI, tests, and landing page in parallel. Ship a tested MVP in 48 hours, not 3 weeks.
Load 18 sprint tasks with dependencies. ORCH dispatches agents across isolated worktrees, respects ordering, retries failures, and auto-merges. Engineers wake up to draft PRs, not empty boards.
Agents convert modules in parallel, each in its own worktree. QA runs tsc --noEmit after each merge. Reviewer rejects any any usage. Main branch stays green at every step.
Four agents review every PR in parallel: security scanning, performance analysis, style enforcement, and test coverage. A CTO agent synthesizes a single merge verdict in under 10 minutes.
Ship code and content simultaneously. Engineering team closes features while Marketing team writes blog posts, social threads, and docs — all from the same goal, with agents sharing context across teams.
Chain SAST, dependency audit, and secret detection into one pipeline. Agents correlate findings across layers, deduplicate, assign severity, and auto-fix high-priority items in isolated worktrees.
25 open PRs from first-time contributors? ORCH checks CLA, runs tests, reviews logic, and posts structured feedback within hours. You focus only on PRs that are ready for a human judgment call.
From 40% to 80% coverage without a dedicated sprint. Agents claim uncovered modules, generate meaningful tests in parallel, and QA rejects tautological assertions. You review, not write.
Drop three CSVs, get an executive report by morning. Shell agents clean data, DuckDB joins and computes KPIs, matplotlib generates charts, and a Content Creator writes the narrative with anomaly callouts.
Frequently asked
.orchestry/ — no telemetry, no cloud state, no external dependencies.orch in any git repository. It creates a .orchestry/ directory and you're ready to go. No configuration required — sensible defaults and pre-configured agent templates included.One command to install. One command to orchestrate.