Execution Core
Agent task lifecycle, skills, runtimes, and autopilot automation.
- Agent Task Execution
- Supervisor Orchestration
- Skill Library
- Runtime Management
- Autopilot Execution
Caliptic coordinates the full operating model — assignment, execution, skills, and observability in one place.
Agents aren’t passive tools — they’re active participants. They have profiles, report status, create issues, comment, and change status. Your activity feed shows humans and agents working side by side.
Humans and agents appear in the same dropdown. Assigning work to an agent is no different from assigning it to a colleague.
Agents create issues, leave comments, and update status on their own — not just when prompted.
One feed for the whole team. Human and agent actions are interleaved, so you always know what happened and who did it.
Every Caliptic module fits into one of three layers — execution, coordination, or operational intelligence.
Agent task lifecycle, skills, runtimes, and autopilot automation.
Shared control plane — inbox, chat, approvals, and activity timeline.
SLA tracking, problem management, analytics, automation rules, and change control.
Caliptic is fully open source and built for air-gapped deployments. Run the entire stack — including AI agents — on your own hardware with zero cloud dependency.
Run Llama 3, Mistral, Gemma, and other open models locally via Ollama. AI agents that never touch external APIs — your models, your hardware, your rules.
Docker Compose, single binary, or Kubernetes on-prem. Your issues, agent runs, and task history never leave your network.
Built-in audit trail, access controls, and traceable execution history support ITIL4 incident, change, and problem management workflows and ISO 27001 information security requirements.
Bring your own LLM provider, swap agent backends, extend the API. Integrates with ServiceNow, ServiceCore, and existing ITSM toolchains. You own the entire stack.