Agent Runtime Python Packages

runloop-api-client

Official Python SDK for Runloop — secure Linux sandboxes (Devboxes) where AI agents run code, edit files, and expose ports

containarium-telemetry

Open-source agent runtime — SSH-native isolation, eBPF egress policy, Kubernetes + LXC backends, GPU passthrough, MCP-native CLI

chatwalaau

The localhost AI Agent Runtime - Chat UI, Tools, RAG, and MCP in one pip install

trustgraph-base

The Semantic Intelligence Layer for Ontologies

trustgraph-embeddings-hf

The Semantic Intelligence Layer for Ontologies

trustgraph-flow

The Semantic Intelligence Layer for Ontologies

trustgraph-cli

The Semantic Intelligence Layer for Ontologies

trustgraph

The Semantic Intelligence Layer for Ontologies

trustgraph-vertexai

The Semantic Intelligence Layer for Ontologies

aindy-runtime

Self-hosted runtime for AI agents and workflows. Durable execution, capability-gated tools, human approval gates, and a memory system that accumulates. Runs survive restarts and resume where they stopped. Mount your domain logic as a plugin package or drive it over the HTTP SDK

trustgraph-bedrock

The Semantic Intelligence Layer for Ontologies

trustgraph-ocr

The Semantic Intelligence Layer for Ontologies

trustgraph-mcp

The Semantic Intelligence Layer for Ontologies

runtm-worker

Open-source sandboxes where coding agents build and deploy. Spin up isolated environments where Claude Code, Cursor, and other agents code and deploy software.

runtm-api

Open-source sandboxes where coding agents build and deploy. Spin up isolated environments where Claude Code, Cursor, and other agents code and deploy software.

runtm

Open-source sandboxes where coding agents build and deploy. Spin up isolated environments where Claude Code, Cursor, and other agents code and deploy software.

protocore

Protocore — the agent loop, and nothing else. A protocol-first ReAct runtime for LLM agents in Python 3.12+: context budget, tool surface, compaction, snapshot and resume. No database driver, no HTTP endpoint — everything outward is a Protocol you implement. MPL-2.0.

reactifact

Reactive, artifact-driven agent runtime: agents transform versioned, typed, provenance-aware artifacts inside an evolving context — no graphs to draw.

dashclaw

Remote approvals, policy checks, and execution evidence for unattended AI agents.

celesto

Secure and persistent computer for AI agents

trustgraph-docling

The Semantic Intelligence Layer for Ontologies

promptise

The foundation layer for agentic intelligence.

agentcat

AgentCat is an analytics platform for MCP server owners 🐱.

flowing-agent

Flowing is a lightweight, extensible agent runtime framework for complex interactions. It consolidates the entire definition of a single agent into one declarative file, leaves the hosting and organization of multiple agents to an embeddable runtime, and opens behavior up to extension through plugins, composables, and hooks.