donbr

import os
import requests
import asyncio
import nest_asyncio
from typing import Annotated, Literal
from typing_extensions import TypedDict
from dotenv import load_dotenv

# LangChain & LangGraph Imports
from langchain_openai import ChatOpenAI

donbr

{
	"folders": [
		{
			"name": "🏗️ architecture",
			"path": "biosciences-architecture"
		},
		{
			"name": "🤖 deepagents",
			"path": "biosciences-deepagents"
		},

donbr

Agent Team Definition

Nine specialized agents coordinate across the Open Biosciences platform. Each agent owns specific repos and has clear responsibilities.

Agent Roster

1. Program Director

Field	Value

donbr

# # Advanced Retrieval with LangChain

# Standard Library Imports
import getpass
import os
from operator import itemgetter
from uuid import uuid4

# Third-Party Imports
from dotenv import load_dotenv

donbr

❯ /lifesciences-graph-builder What known genes or pathways are implicated in minimizing Doxorubicin toxicity
while preserving its anti-tumor efficacy?

● I'll execute the Fuzzy-to-Fact protocol to answer this question about Doxorubicin toxicity mitigation. Let me start by loading the necessary MCP tools and beginning Phase 1 ANCHOR.

● Now let me load additional tools I'll need for the full protocol.

● Tools loaded. Starting the Fuzzy-to-Fact protocol now.

donbr

Deep Agents Cloud Deployment Guide

This guide documents how to deploy Deep Agents to LangSmith cloud with a focus on workspace/file lifecycle - a critical topic for production deployments.

Overview

Deep Agents CAN be deployed to LangSmith cloud. From the official LangChain documentation:

"Deep agents applications can be deployed via LangSmith Deployment and monitored with LangSmith Observability."

donbr

Agent Memory - All demos

based on running test script from https://github.com/donbr/agent-memory

uv run python -m agent_memory

Agent Memory - All Demos

donbr

LangGraph memory mechanisms (mechanism × persistence)

1. Execution / short-term memory (checkpointers)

Mechanism	Purpose	In-memory / local	DB-persisted	Notes
MemorySaver	Persist graph state per step (thread continuity)	✅ Yes	❌ No	Notebook/dev only; lost on process restart
PostgresSaver	Durable execution state	❌ No	✅ Postgres	Required for resumable workflows, HITL, failures
(others)	(Future / custom savers)	—	—	Checkpointer interface is pluggable

donbr

AI Makerspace Video Deliverable Guide (2026 Edition)

The Objective: Your video is an exercise in Developer Advocacy. It serves to prove two things:

1. Functionality: You actually built the application.
2. Grokking: You deeply understand the concepts and can teach them to a teammate.

---

1. The Setup: Anchor with a Diagram

donbr

Multi-Agent Graph Coordination Architecture

Problem Statement

Multiple AI agents (Claude Desktop, Claude Code, future agents) share write access to a Graphiti knowledge graph without coordinated protocols. This has resulted in:

• Namespace pollution: 97 episodes in graphiti_meta_knowledge vs intended 8-10.
• Duplicate episodes: Lack of idempotency checks.
• Inconsistent content categorization: Different agents, different rules.
• Loss of namespace semantic integrity.