adk-python and iam-bobs-brain
The first is a foundational Python framework for building AI agents on Google ADK, while the second is a specialized enterprise orchestration system built on top of that framework, making them complements designed to be used together.
About adk-python
google/adk-python
An open-source, code-first Python toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.
Supports model-agnostic agent development with built-in integration for Gemini, MCP tools, and OpenAPI specs, plus hierarchical multi-agent orchestration where coordinator agents delegate to specialized sub-agents. Features a modular architecture enabling deployment to Cloud Run or Vertex AI Agent Engine, with a built-in development UI for testing and an evaluation framework for benchmarking agent performance. Includes session management capabilities like rewinding invocations and tool confirmation flows for human-in-the-loop control.
About iam-bobs-brain
intent-solutions-io/iam-bobs-brain
General-purpose enterprise orchestrator on Google ADK + Vertex AI Agent Engine. Multi-agent system with risk tiers (R0-R4), policy gates, evidence bundles, and Mission Spec v1 workflows.
Implements a multi-specialist agent system where autonomous agents coordinate through Google ADK's Agent Engine with persistent state via dual memory (Session + Memory Bank), delegating compliance tasks across 8 specialized agents. Built-in audit trails use evidence bundles with cryptographic validation, and all workflows—from Slack interactions to portfolio-wide scans—are expressed as declarative Mission Spec v1 YAML for reproducibility and governance.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work