Agentic orchestrator for parallel coding agents — plans tasks, spawns agents, and autonomously handles CI fixes, merge conflicts, and code reviews.

agent-fleet agent-swarm claude-code codex-cli git-worktrees multi-agent orchestration orchestrator parallel-agents parallel-coding skills tmux

Go to file

itrytoohard 2d00e4675d fix(cli): harden daemon control surface and stop CLI from writing the store Addresses review findings on PR #53 (on top of the rebase onto main). - doctor: stop opening/migrating SQLite. The daemon is the sole store writer/migrator (architecture.md §7); the CLI must not run migrations or open a second writer against a DB a live daemon owns. doctor now reports database-file presence and gains --json. - stop: only remove running.json when it still belongs to the PID we stopped, so a concurrent `ao start` that wrote a new run-file is not clobbered into looking stopped. - httpd: gate POST /shutdown to loopback callers with no Origin header, closing the CSRF / DNS-rebinding vector against an unauthenticated, state-changing endpoint. - start: detach the spawned daemon into its own session/process group so a Ctrl-C while `ao start` waits for readiness doesn't also kill it. - cli: exit 2 for usage errors (bad flag / arg count) vs 1 for runtime failures. - daemon: unexport newLogger (only used in-package). - tests: /shutdown guard (cross-origin + rebinding) and stop run-file ownership guard. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>		2026-06-01 01:55:14 +05:30
.github/workflows	ci: add Go build/test and gitleaks secret-scan workflows	2026-05-26 21:02:58 +05:30
backend	fix(cli): harden daemon control surface and stop CLI from writing the store	2026-06-01 01:55:14 +05:30
docs	fix(cli): harden daemon control surface and stop CLI from writing the store	2026-06-01 01:55:14 +05:30
frontend	chore: scaffold backend/ and frontend/ skeletons for rewrite	2026-05-26 15:22:36 +05:30
.gitignore	feat(backend): SQLite storage layer + CDC pipeline, LCM/reaper wiring	2026-05-30 16:02:07 +05:30
README.md	feat(backend): add cobra cli foundation	2026-06-01 01:44:43 +05:30

README.md

agent-orchestrator

Rewrite of the agent-orchestrator: a long-running Go backend daemon (backend/)
paired with an Electron + TypeScript frontend (frontend/).

See docs/ for architecture and status — start with the
Lifecycle Manager + Session Manager lane in docs/architecture.md.

Backend daemon

The Go backend now has a Cobra-based ao CLI in backend/cmd/ao.
The CLI controls the HTTP daemon — a loopback-only sidecar the Electron
supervisor will also use. The daemon skeleton includes the chi router,
middleware stack (recoverer → request-id → logger → real-ip), /healthz +
/readyz, atomic running.json PID/port handshake, graceful shutdown on
SIGINT/SIGTERM, SQLite storage, CDC polling, and lifecycle/reaper wiring.

Run

cd backend
go run ./cmd/ao start             # start the daemon and wait for readiness
go run ./cmd/ao status            # inspect PID/port/health/readiness
go run ./cmd/ao stop              # gracefully stop the daemon
go run ./cmd/ao daemon            # internal daemon entrypoint

go run .                          # compatibility wrapper; starts the daemon
AO_PORT=3019 go run ./cmd/ao start # override per invocation

Health check:

curl localhost:3001/healthz       # {"status":"ok"}
curl localhost:3001/readyz        # {"status":"ready"}

Configuration (env only)

The bind host is always 127.0.0.1: the daemon is a loopback-only sidecar
and binding any other interface would be a security regression, so the host
is intentionally not env-configurable.

Var	Default	Purpose
`AO_PORT`	`3001`	bind port; fails fast if taken
`AO_REQUEST_TIMEOUT`	`60s`	per-request timeout (Go duration)
`AO_SHUTDOWN_TIMEOUT`	`10s`	graceful-shutdown hard cap
`AO_RUN_FILE`	`<UserConfigDir>/agent-orchestrator/running.json`	PID + port handshake path

Test

cd backend
gofmt -l . && go build ./... && go vet ./... && go test -race ./...