github-starred/awesome-llm-apps
2
0
Fork 0
mirror of https://github.com/Shubhamsaboo/awesome-llm-apps.git synced 2026-03-11 17:48:31 -05:00
Code Issues 14 Packages Projects Releases Wiki Activity

Fix ai_services_agency deps and v1 cleanup

Browse Source
This commit is contained in:
Nick Bobrowski
2026-02-09 00:07:15 +00:00
parent 62e5c2b742
commit c326a6f942
3 changed files with 10 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
advanced_ai_agents/multi_agent_apps/agent_teams/ai_services_agency/README.md
View File

@@ -13,12 +13,12 @@ https://github.com/user-attachments/assets/a0befa3a-f4c3-400d-9790-4b9e37254405
- **CEO Agent**: Strategic leader and final decision maker
- Analyzes startup ideas using structured evaluation
- Makes strategic decisions across product, technical, marketing, and financial domains
- Uses AnalyzeStartupTool and MakeStrategicDecision tools
- Uses AnalyzeProjectRequirements tool
- **CTO Agent**: Technical architecture and feasibility expert
- Evaluates technical requirements and feasibility
- Provides architecture decisions
- Uses QueryTechnicalRequirements and EvaluateTechnicalFeasibility tools
- Uses CreateTechnicalSpecification tool
- **Product Manager Agent**: Product strategy specialist
- Defines product strategy and roadmap
@@ -41,18 +41,18 @@ The agency uses specialized tools built with OpenAI Schema for structured analys
- **Analysis Tools**: AnalyzeProjectRequirements for market evaluation and analysis of startup idea
- **Technical Tools**: CreateTechnicalSpecification for technical assessment
### 🔄 Asynchronous Communication
### 🤝 Multi-Agent Collaboration
The agency operates in async mode, enabling:
- Parallel processing of analyses from different agents
- Efficient multi-agent collaboration
- Real-time communication between agents
- Non-blocking operations for better performance
The agency coordinates five specialists through explicit communication flows:
- CEO drives strategic oversight across the team
- CTO and Developer collaborate on implementation feasibility
- Product and Client Success coordinate roadmap and go-to-market planning
- Each analysis is returned in a dedicated section in the Streamlit UI
### 🔗 Agent Communication Flows
- CEO ↔️ All Agents (Strategic Oversight)
- CTO ↔️ Developer (Technical Implementation)
- Product Manager ↔️ Marketing Manager (Go-to-Market Strategy)
- Product Manager ↔️ Client Success Manager (Go-to-Market Strategy)
- Product Manager ↔️ Developer (Feature Implementation)
- (and more!)

7
advanced_ai_agents/multi_agent_apps/agent_teams/ai_services_agency/agency.py
View File

@@ -23,9 +23,6 @@ class AnalyzeProjectRequirements(BaseTool):
def run(self) -> str:
"""Analyzes project and stores results in shared state"""
if self.context is None:
raise RuntimeError("Tool context is not available.")
if self.context.get("project_analysis", None) is not None:
raise ValueError("Project analysis already exists. Please proceed with technical specification.")
@@ -64,9 +61,6 @@ class CreateTechnicalSpecification(BaseTool):
def run(self) -> str:
"""Creates technical specification based on analysis"""
if self.context is None:
raise RuntimeError("Tool context is not available.")
project_analysis = self.context.get("project_analysis", None)
if project_analysis is None:
raise ValueError("Please analyze project requirements first using AnalyzeProjectRequirements tool.")
@@ -248,7 +242,6 @@ def main() -> None:
(product_manager, developer),
(product_manager, client_manager),
],
shared_files_folder="shared_files",
)
# Prepare project info

2
advanced_ai_agents/multi_agent_apps/agent_teams/ai_services_agency/requirements.txt
View File

@@ -1,3 +1,3 @@
python-dotenv==1.0.1
python-dotenv==1.1.1
agency-swarm==1.7.0
streamlit