AgencyForge AI

Multi-agent project analysis agency by Sharad Khare.

AgencyForge AI is an agency-swarm Streamlit app where a CEO analyzes project requirements and a CTO creates technical specifications using shared-state tools — alongside product, engineering, and client success agents.

Built and maintained by Sharad Khare — AI strategist, full-stack developer, and creator of practical agent workflows.

---

What this project does

AgencyForge turns your project brief into a full agency analysis through five specialized agents:

1. Project Director (CEO) — analyzes requirements and feasibility with shared-state tooling

2. Technical Architect (CTO) — creates architecture specs from CEO analysis via shared context

3. Product Manager — defines scope, roadmap, and product features

4. Lead Developer — plans implementation, estimates effort, and reviews feasibility

5. Client Success Manager — shapes go-to-market and customer acquisition strategy

The CEO and CTO tools write to and read from shared agency state, enforcing a strict analyze-then-specify workflow.

---

Why Sharad Khare built AgencyForge AI

Software agency workflows require sequential handoffs — strategy before architecture, architecture before implementation. AgencyForge demonstrates how agency-swarm shared-state tools enforce that order while multiple agents collaborate on a single project brief.

---

How it works

Project Brief (name, description, type, budget...)
   │
   ▼
CEO → AnalyzeProjectRequirements tool → shared state
   │
   ▼
CTO → CreateTechnicalSpecification tool → shared state
   │
   ▼
Product Manager / Developer / Client Success → role-specific analysis
   │
   ▼
Streamlit tabs with full agency report

Shared-state tools

| Tool | Agent | Purpose |

|------|-------|---------|

| AnalyzeProjectRequirements | CEO | Stores project analysis in shared context |

| CreateTechnicalSpecification | CTO | Reads analysis, writes technical spec |

---

Features

• Five-agent agency-swarm with communication flows
• Shared-state tools enforce CEO-before-CTO workflow
• Rich Streamlit form: type, timeline, budget, priority, requirements
• Tabbed output for each agent's analysis
• Analysis history in sidebar

---

Quick start

cd agencyforge-ai
pip install -r requirements.txt
streamlit run app.py

Required API key

• OpenAI API key — enter in the sidebar when running the app

---

Example inputs

• Project: AI-powered customer support platform
• Type: Web Application · Budget: $50k–$100k · Timeline: 5–6 months
• Priority: High · Requirements: Real-time chat, CRM integration, analytics dashboard

---

Project structure

agencyforge-ai/
├── app.py
├── agencyforge/
│   ├── agency_setup.py
│   └── tools.py
├── requirements.txt
├── pyproject.toml
└── README.md

---

Who this is for

• Agency owners prototyping AI-assisted project scoping
• Consultants evaluating client project feasibility
• Developers learning agency-swarm shared-state patterns
• Product teams exploring multi-agent delivery workflows

Use cases

• Analyze a startup idea across strategy, tech, product, and GTM
• Generate technical specifications from project requirements
• Scope budget and timeline with multi-role agent feedback
• Learn shared-state tool patterns in agency-swarm

---

Author

• Website: sharadkhare.in

License

MIT © Sharad Khare