bbagents

Python building blocks for agent systems: tools, planning, model selection, memory, human approval, tracing, and evaluation. Works with LangGraph or your own runtime.

Companion code for Agentic AI: Architecture, Theory, and Practice. Buy on Brilberry Press or Buy on Barnes & Nobles.

Requires Python 3.11+.

Install from PyPI:

python -m pip install bbagents

For development, install from a repository checkout and run the tests:

python -m pip install -e '.[dev]'
pytest

Complete application example

Agent Stranded is a more complete example: an autonomous survival game using bbagents planning, tools, memory, skills, communication, and tracing, with an optional local LLM. Its code, documentation, and run instructions live in that separate repository.

Features

• Typed tools, dependency-checked plans, structured model decisions and validation.
• Prioritized behavior controllers with explicit abstention and selection traces.
• Native behavior trees with running actions, cancellation and execution traces.
• Typed decision-tree policies compiled to native trees, with event priorities and hysteresis.
• Per-agent model selection, routing constraints, cost estimates and caching.
• Capability policies, human intervention, explicit delegation and LangGraph interrupts.
• Bounded async execution, retry policies, execution journals and effect reconciliation.
• Versioned checkpoints, SQLite persistence, task budgets and completion gates.
• Budgeted context, summarization contracts and provider-neutral retrieval (RAG).
• Scoped, revisioned memory and skills; evaluated and approved procedure promotion.
• Roles, messages, delegation and organizational governance.
• Structured traces, isolated evaluation trials and compaction-continuation checks.
• Optional Ollama, LangChain, LangGraph, LangSmith and Langfuse integrations.

No mandatory runtime dependencies. Applications own domain behavior and adapters.

See examples, demos and the guide.

Maintainers: see release instructions for publishing to PyPI.