The agynd daemon bridges agent CLIs with the platform by connecting to Threads and Notifications services, preparing the agent runtime environment, and managing the agent process lifecycle.
Architecture: https://github.com/agynio/architecture/blob/main/architecture/agynd-cli.md
Full setup: https://github.com/agynio/architecture/blob/main/architecture/operations/local-development.md
agynd is not deployed as a service. The Runner
starts it as the main process of an agent container, so there is no Deployment
to attach to and no devspace dev to run -- the way to exercise a change is to
put the binary in an agent init image and point an agent at it:
CGO_ENABLED=0 GOOS=linux GOARCH=amd64 go build -o .build/agynd ./cmd/agyndThen build an init image that copies .build/agynd over the one baked in, load
it into the local VM, and set it as the agent's init image:
agyn local load-image my-agent-init:devThe GitHub E2E workflow runs this repository's local E2E tests with:
go test -v -count=1 -tags e2e ./test/e2e/Those tests validate the local agent CLI bridge behavior against deterministic
TestLLM endpoints through the Codex and AGN SDK flows. The workflow checks out
agynio/agn-cli so the AGN coverage builds and runs the current AGN CLI during
the test. They also build and execute this repository's cmd/agynd binary with
/agyn/config.json installed by the test harness. That test uses a stub
Gateway and fake AGN agent to verify daemon startup, platform initialization,
and subscriber startup without requiring a full cluster.
This repository does not run the centralized agynio/e2e smoke suite. Broader
platform and service smoke coverage remains owned by the centralized E2E
repository and service-specific workflows.