Compose, orchestrate, and trace production multi-agent workflows with Microsoft Agent Framework.

Spin up isolated, reproducible sandboxes where agents can run generated code, install dependencies, execute tests, and discard state safely.

Use mcp-use to create, test, and package MCP servers or interactive MCP apps that work across agent clients.

Use OpenFang to run packaged autonomous agent workflows on schedules with manifests, dashboards, reporting, and guardrails for sensitive actions.

Use RAGFlow to ingest complex documents, build governed RAG knowledge bases, and give agents higher-fidelity context for retrieval-augmented workflows.

Use Playwright CLI to run token-efficient browser tests directly from coding agents, reducing overhead for automated UI and end-to-end testing workflows.

Guide an agent through property search, buyer/renter preference capture, and evidence-backed shortlist notes from structured listing data.

Use Docker MCP Gateway to run MCP servers in isolated containers, centralize profiles, secrets, tools, and client connections.

Launch coding agents such as Claude Code, Gemini, or Codex in clean sandboxed sessions with redaction and run observability.

Create disposable E2B cloud sandboxes where agents can execute generated code, install dependencies, collect outputs, and discard state safely.

Capture LLM and agent traces, run evaluations, inspect failures, and monitor RAG or multi-step agent behavior from prototype to production.

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine built on deep document understanding. Use it as a retrieval and context layer for agent workflows to ground LLM responses in your own documents, APIs, and knowledge bases.

Decompose goals into task DAGs, delegate work to agents and tools, and inspect execution traces.