bagofwords1/bagofwords

Chat with your data - with memory, rules, and observability built in. Deploy in 2 minutes

What it solves

Bag of Words (BOW) is an agentic analytics platform that bridges the gap between Large Language Models (LLMs) and enterprise data. It solves the problem of giving AI agents the necessary context—such as specific data sources, tools, credentials, and permissions—to perform complex analytical tasks, generate reports, and conduct root cause analysis without requiring manual setup for every interaction.

How it works

BOW acts as a governed gateway between LLMs, data sources, and communication channels. It allows users to configure "agents" with specific instructions and access to a wide array of connectors (databases, warehouses, BI tools, and APIs). These agents can then be deployed across various surfaces like chat, scheduled reports, dashboards, and MCP clients. The platform includes a query acceleration cache to speed up analytical queries and an evaluation framework that uses self-improving loops to automatically draft and test instruction fixes when agents fail to meet expected behaviors.

Who it’s for

It is designed for teams and enterprises that need to scale the use of data agents for business intelligence, automated reporting, and event-driven investigations across their organization.

Highlights

  • Extensive Connectivity: Supports a vast range of data connectors including PostgreSQL, Snowflake, BigQuery, and various BI tools like Tableau and Power BI.
  • Agent Governance: Provides RBAC, audit logs, and row-level security to control exactly what data and tools each agent can access.
  • Self-Improving Loops: Uses eval sets to monitor agent behavior and automatically iterate on instructions to improve reliability.
  • MCP Gateway: Connects agents to Model Context Protocol (MCP) servers and exposes them to MCP clients like Claude Code.
  • Query Acceleration: Features an auto-updating cache that can speed up analytical queries by 10–1000×.
  • Multi-Surface Deployment: Agents can operate via a web app, Slack, Microsoft Teams, WhatsApp, email, and Excel.

Related

  • Project
    lightdash/lightdash

    An open-source agentic BI platform that uses a governed context layer to power dashboards, AI agents, and data apps with a software-engineering workflow.

  • Project
    getnao/nao

    An open-source framework to build and deploy analytics agents that enable business users to query data using natural language and generate visualizations.

  • Project
    CopilotKit/OpenBot

    An agent platform for deploying secure AI coworkers with isolated browser/shell environments and a strict governance gateway for auditing and policy enforcement.

  • Project
    eosphoros-ai/DB-GPT

    An open-source agentic AI data assistant that connects to databases and files to autonomously write SQL and code for data analysis and reporting.

  • Project
    desplega-ai/agent-swarm

    agent‑swarm is an open‑source platform that turns a lead AI agent into a task‑routing hub, delegating work to containerised worker agents (Claude Code, Codex, etc.). It integrates with Slack, GitHub, email, and many other tools, persisting context via vector memory, and can automatically generate PRs, replies, or scheduled scripts. The system is model‑agnostic, runs via Docker (or Helm on Kubernetes), and is licensed under MIT.