Management layers on top of coding work. Agents (Claude Code, Codex, GitHub Copilot, Gemini) write the code; this repository is the Studio: a task board, agent pipelines, and project wikis that assign, gate, review, and account for it.
- Batch remote and local coding-agent work with task management in one place.
- Reduces cognitive load: task state, progress and evidence are visible instead of remembered.
- A management layer over autonomous agent runs: assign, gate, review, account.
- Works with your existing CLI subscriptions, or bring your own API keys.
- Runs fully local or distributed, your choice per project. Project chat follows the project's execution runner and shows its host, repository checkout, branch, and revision.
- Keeps the Task Server as the durable control plane while separately fenced Remote Review Executors inspect immutable result revisions.
- Runs review decisions, council reactions, post-processing, gate dispatch, and completion judging in the separate API-only Orchestrator Engine. Flow definitions and in-flight runs remain durable Task Server data, so restarting the Engine does not orphan work.
git clone https://github.com/agent-orc/agent-studio.git
cd agent-studio
docker compose up --waitOpen http://localhost:4011. Docker Compose is the
primary new-user installation path. It pulls pinned, non-root
release container images
per service, so it requires at least 8 GB of free disk space but no host .NET
or Node.js install, local settings file, maintainer switch, or neighbouring
repository. See the
setup guide for prerequisites,
persistence, and troubleshooting. As an alternative for Linux x64 release
installs with no source checkout and no .NET prerequisite, the guided
agent-orchestrator-setup
executable offers an isolated Docker demo, a native single-machine install, and
a guided multi-machine join flow.
To add execution capacity after the Studio is running, follow the
Agent Host guide, or stay in
Docker with docker compose --profile runner up --wait after
scripts/compose-runner-bootstrap.sh (see
getting started, §5).
Source contributors use the separate
contributor setup.
scripts/scenario.sh --target inproc --level smoke runs the deployment
regression scenario: one seeded fixture driven end to end through bootstrap,
claim, run, and auto-review against the Task Server / Runner topology, no
Docker required. See
docs/operations/testing/deployment-scenario.md.
Agent Studio is part of the agent-orc ecosystem. It uses Chat for coding-agent conversations and sits alongside Runner for hardened CLI execution, Token Economy for model pricing and usage accounting, and Quality Studio for layered code review.
For future product direction, see the roadmap. For architecture, ADRs, contracts, and the full documentation index, see agent-orchestrator.dev.
Licensed under the Apache License 2.0.