Release Date: April 25, 2026
This release adds multi-agent examples, a pluggable workflow registry, CLI onboarding, and an in-memory cost reporter for evaluation.
These release notes describe the v0.2.0 feature set. They do not claim production readiness, full air-gap validation, durable chargeback, real OPA execution, or same-run signed evidence.
- Research Swarm — A2A agent discovery, persona
toolProfilechecks, approval-threshold inputs, and a local Ollama overlay. - SRE Incident Response —
collaborationMode: delegation, 3-tier cost-aware model routing (cheap triage → mid analysis → expensive remediation), adversarial tone on remediator, hierarchical memory. 4 alert scenarios included.
@register_workflowdecorator for custom LangGraph workflows- Auto-discovery from built-in + custom directories
WORKFLOW_NAMEenv var selects workflow at runtime- Ships with 3 workflows: research_swarm, code_review (fan-out security/performance/style), doc_processor (parallel entity extraction + summarization)
- MemoryCostReporter with Prometheus metrics (
agentic_workload_cost_usd,agentic_workload_tokens_total) - Pre-loaded pricing for OpenAI, Anthropic, Azure OpenAI, and Ollama (local = $0)
- Budget enforcement with configurable thresholds
- Per-workload cost annotations scraped by Prometheus
agentctl init— Interactive cluster onboarding wizardagentctl approve— Resume PendingApproval workloads via annotation patch + Argo resumeagentctl workflows— List all registered workflowsagentctl status— Cluster health overview- Total: 10 commands (init, apply, get, describe, logs, cost, approve, workflows, status, version)
spec.workflowNamefield on AgentWorkload for workflow selection- deepcopy regenerated for all CRD changes
cd examples/multi-agent-swarm
cp .env.example .env # add your API key (or use Ollama)
make up # starts 7 containers
make demo # runs full 6-stage pipelinecd examples/sre-incident-response
cp .env.example .env
docker compose up -d
curl -X POST http://localhost:9010/incidents \
-H "Content-Type: application/json" \
-d '{"alert_type":"PodCrashLoopBackOff","namespace":"default","resource":"app-server-7b9f4c6d8-x2k9p"}'agentctl init # interactive cluster setup
agentctl status # check cluster health
agentctl workflows # list available workflowsgit clone https://github.com/Clawdlinux/agentic-operator-core.git
cd agentic-operator-core
helm dependency build ./charts
helm upgrade --install clawdlinux ./charts \
--namespace agentic-system --create-namespace# macOS
curl -sL https://github.com/Clawdlinux/agentic-operator-core/releases/download/v0.2.0/agentctl-darwin-arm64 -o agentctl
chmod +x agentctl && sudo mv agentctl /usr/local/bin/- GitHub: https://github.com/Clawdlinux/agentic-operator-core
- Landing: https://clawdlinux.org
- Docs: https://github.com/Clawdlinux/agentic-operator-core/tree/main/docs
See CHANGELOG.md for the complete list of changes since v0.1.1.
- HTTPS-only enforcement for MCP endpoints
- Webhook TLS via cert-manager,
failurePolicy: Fail - Distroless containers, non-root user
- Credential sanitizer in logs (OpenAI, GitHub, AWS, JWT, bearer tokens)
- Prompt injection sanitization on scraped content
- In-process action evaluator and separate Rego policy assets
- See SECURITY.md for vulnerability disclosure (48h SLA)
Binaries are attached to this release. Pick the one for your platform:
agentctl-linux-amd64agentctl-linux-arm64agentctl-darwin-amd64agentctl-darwin-arm64
Apache License 2.0 — see LICENSE.