Metadata-Version: 2.4
Name: 3tears-agent-knowledge
Version: 0.14.0
Summary: Governed-knowledge retrieval + injection for LLM agents -- concepts, playbook entries, three-scope shadow merge, and before_model middleware
Project-URL: Repository, https://github.com/pacepace/3tears
Author: pace
License-Expression: MIT
License-File: LICENSE
Classifier: Development Status :: 3 - Alpha
Classifier: Framework :: AsyncIO
Classifier: Intended Audience :: Developers
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.14
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: Software Development :: Libraries
Classifier: Typing :: Typed
Requires-Python: >=3.14
Requires-Dist: 3tears
Requires-Dist: 3tears-agent-acl
Requires-Dist: 3tears-agent-memory
Requires-Dist: 3tears-langgraph
Requires-Dist: 3tears-nats
Requires-Dist: 3tears-observe
Requires-Dist: langchain-core
Requires-Dist: pgvector
Description-Content-Type: text/markdown

# 3tears-agent-knowledge

Agent-side governed-knowledge read stack for LangGraph agents.

Homes the playbook-entry / concept collections (over the platform RBAC proxy), the
`KnowledgeIntegration` wiring, and the `create_agent` `before_model` injection
middleware, on top of the shared three-scope shadow-merge authority in
`threetears.knowledge` (core). It lives in its own package because the collections
depend on `threetears.agent.acl`, which core cannot depend on.
