runtime

Open-source runtime for multi-agent AI systems with job scheduling, DAG orchestration, shared memory, tool execution, and real-time observability.

RiskKernel is an open-source, self-hosted reliability runtime for AI agents. It adds hard budgets, kill switches, crash-resumable runs, human approval gates, and OpenTelemetry export, with support for OpenAI, Anthropic, and existing agent stacks.

Treenix is a typed runtime for building software shared between humans and agents. The repository describes an ECS-style tree of typed components with context-aware rendering, server actions, React views, access rules, realtime updates, and MCP tools.

Open-source Go runtime for autonomous multi-agent systems. Swarm models work as durable state machines, persists state, supports replay/fork, and integrates with multiple LLM backends.

Dropstone is a versioned coding agent runtime that routes work through open-weight models on US-hosted, no-retention infrastructure. The report explains its monthly re-baselining process, safety boundary, and cost model for Fast, Pro, and Heavy tiers.

An essay arguing that the BEAM runtime and OTP primitives map well to agent workloads, especially long-lived personal-assistant agents with supervision, registries, and structured concurrency.