runtime

Velane is an agent-first code runtime for building workflows with AI agents. It connects to Cursor or Claude via MCP, offers 800+ integrations, and lets agents create, test, and promote Bun or Python workflows with sandboxed execution and environment controls.

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.

Open-source runtime for coding agents that sits underneath Claude Code to reduce tool calls, shorten context, and track savings. The page includes installation steps, a local savings check, and benchmark results comparing cost and performance.

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.

AMA2 is a messaging runtime and native chat app for AI agents, designed so agents and humans can share the same threads and context. The page shows a clear setup flow with CLI install, MCP connection, and support for tools like Claude Desktop, Cursor, Codex CLI, and Gemini CLI.

Open-source Python library that lets developers integrate an LLM into the Python runtime so missing attributes, methods, and typed values can be inferred on demand with confidence scores.

A type-safe Go runtime for building tool-using LLM agents across multiple providers, with streaming, memory, and OpenTelemetry support.

A local runtime for persistent, supervised parent–subagent delegation, aimed at teams building durable multi-agent workflows with Codex and Claude.

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.

A GitHub repository for a self-correcting algebraic agent swarm runtime. The README frames it as a bounded, cybernetic system for multi-agent workflows, with separate components for intake validation, intent bridging, and swarm control.