Physical AI runtime for embodied agents — governed action, verified experience, physical memory, and skill evolution.

A work-centered runtime for agentic software engineering. Work persists; agents, context, and graphs assemble around it.

Build AI agents you can trust in production. AgentFlow4J is a framework and runtime for governed, stateful multi-agent systems on the JVM. Human approvals · Checkpoints · Budget controls · Tool policies · Durable execution

ARES is a self-healing multi-agent runtime that combines event sourcing, memory distillation, chaos engineering, and evolutionary workflow optimization.

"Local LLM agent runtime in Rust — native tool-role support, tmux session persistence, two-tier summarization, SQLite tool logging and ShareGPT logging. Optional remote tool server with MCP support as well as an optional inference server. Works with OpenAI-compatible backends."

Local runtime self-learning engine for Hanako with policy gates, evidence chain, validation, rollback, and skill governance.

Open-source runtime for adding AI agents to your application. Start agent runs, connect MCP tools, and stream execution events—while your app owns the context, permissions, and business logic.

Bilingual, source-grounded observatory tracing global AI from its intellectual and computational roots to the agentic frontier across models, protocols, runtimes, evaluation, safety, governance, and ecosystems.

Managed platforms, durable execution engines and agent servers where AI agents live, keep state and run for long.

Governed AI work runtime for durable delegated work, explicit execution authority, and reproducible computational research.

API platform info for agents