Skip to main content

a TUI‑first Python package and multi‑agent market research engine that orchestrates validated data collection, analysis, and report synthesis into citation‑rich PDF reports

Project description

ambitus-intelligence 🔍

Ambitus Intelligence is a TUI‑first Python package and multi‑agent market research engine that orchestrates validated data collection, analysis, and report synthesis into citation‑rich PDF reports.

Technical diagrams : Flowcharts
UML of Ambitus : Ambitus-AI

https://github.com/user-attachments/assets/0b6cd0a2-a02f-4ea1-8fdb-6f51012f2fad

This repository contains AI/ML models, experiments, and tools powering ambitus Intelligence's market research automation platform.
All exploratory work, prototypes, and notebooks are organized under /notebooks.


🚀 Overview

ambitus-ai-models is the core engine behind Ambitus Intelligence’s automated market research platform. It provides:

  • Orchestrated Multi‑Agent Workflows
    A centralized Orchestrator sequences specialized AI agents, handles error‑flows, and manages user hand‑offs.

  • FastMCP Tool Server
    ambitus-tools-mcp—a MCP server, backed by FastMCP—hosts all external utilities (scrapers, API clients, validators) and the CitationAgent, allowing agents to discover and invoke tools at runtime.

  • Structured Agent Outputs
    Each agent emits well‑defined JSON payloads, which are persisted to a database and exposed via REST for downstream consumption.


🔑 Key Agents

Agent Name Responsibility
CompanyResearchAgent Scrape and ingest public & proprietary sources (Crunchbase, Wikipedia, web) to produce a company profile.
IndustryAnalysisAgent Analyze the company profile via LLM prompts to rank and rationalize potential expansion domains.
MarketDataAgent Retrieve quantitative metrics (market size, CAGR, trends) from external APIs (Google Trends, Statista).
CompetitiveLandscapeAgent Compile and summarize key competitors, their products, market share, and strategic positioning.
GapAnalysisAgent Use LLM reasoning to detect unmet needs and strategic gaps by comparing capabilities vs. competitors.
OpportunityAgent Brainstorm, validate, and rank growth opportunities grounded in data from upstream agents.
ReportSynthesisAgent Aggregate all agent outputs into a citation‑rich final report (Markdown, HTML, PDF).
CitationAgent (Tool) On‑demand retrieval of citations or data snippets, serving all agents via the MCP tool server.

📖 Documentation

Legacy Notion (for archival reference only):

📁 Repository Structure

ambitus-ai-models/
├── docs/                                       # Architecture & agent specs (Markdown)
│   ├── README.md                               # Index of spec docs
│   ├── system_overview.md
│   ├── agent_specs.md
│   ├── workflow_examples.md                    # TODO
│   └── mcp_server.md                           # TODO
├── notebooks/                                  # Experimental Jupyter/Colab prototypes
│   ├── Experiment ##- <experiment_name>.ipynb   
│   └── ...                                     # Additional experiments in ##-*.ipynb format
├── src/                          # Source code
│   ├── agents/                   # Individual agent implementations
│   │   ├── __init__.py
│   │   ├── company_research_agent.py
│   │   ├── industry_analysis_agent.py
│   │   ├── market_data_agent.py
│   │   ├── competitive_landscape_agent.py
│   │   ├── gap_analysis_agent.py
│   │   ├── opportunity_agent.py
│   │   ├── report_synthesis_agent.py
│   │   └── citation_agent.py
│   │
│   ├── mcp/                      # MCP server configuration and tools
│   │   ├── __init__.py
│   │   ├── server.py             # FastMCP server implementation
│   │   ├── tools/                # Tool implementations
│   │   │   ├── __init__.py
│   │   │   └── ...               # Individual tool modules
│   │   └── data_sources/         # Data source connectors
│   │       ├── __init__.py
│   │       └── ...               # Individual data source modules
│   │
│   ├── api/                      # Backend API for web application
│   │   ├── __init__.py
│   │   └── routes.py             # API endpoints
│   │
│   └── utils/                    # Shared utilities
│       ├── __init__.py
│       └── ...
│
├── .env.example                  # Example environment variables
├── pyproject.toml                # Project configuration and dependencies
├── README.md                     # Project overview
└── .gitignore                    # Git ignore file

📧 Contacts

For questions or collaborations, contact:

Lead Developers:


Part of the Next-Gen Market Intelligence Suite

ambitus Intelligence | Documentation | Main Repository

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

ambitus_cli-0.1.0.tar.gz (48.4 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

ambitus_cli-0.1.0-py3-none-any.whl (67.8 kB view details)

Uploaded Python 3

File details

Details for the file ambitus_cli-0.1.0.tar.gz.

File metadata

  • Download URL: ambitus_cli-0.1.0.tar.gz
  • Upload date:
  • Size: 48.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for ambitus_cli-0.1.0.tar.gz
Algorithm Hash digest
SHA256 e2db83876b57c9e63dd433f8959a5c423d9815dcea0b220143d9776fb1da71a4
MD5 88da3f4554193eb9367285d371e50141
BLAKE2b-256 cd241f0548daa97050d53c3753b17e059a189404aa35738554383e3f50f46697

See more details on using hashes here.

Provenance

The following attestation bundles were made for ambitus_cli-0.1.0.tar.gz:

Publisher: python-publish.yml on Ambitus-Intelligence/ambitus-ai-models

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file ambitus_cli-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: ambitus_cli-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 67.8 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for ambitus_cli-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 6f6603e527182c07ef3431d3eebea6d6a923e6ac9dbf4a80055efe6e096d8ca0
MD5 99d25440fc146563439f8b830dda72ca
BLAKE2b-256 ede4e30b1855a3f69bbe1887ceeecdaf16b9ac3a41df1edd3645648e240cddbb

See more details on using hashes here.

Provenance

The following attestation bundles were made for ambitus_cli-0.1.0-py3-none-any.whl:

Publisher: python-publish.yml on Ambitus-Intelligence/ambitus-ai-models

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page