Skip to main content
Back to projects
LiveTool

Founder Knowledge Graph

AI Memory System for Solo Founders

A persistent knowledge graph that gives AI agents real memory, context, and continuity across sessions. Built to solve the problem every solo founder faces: AI tools that forget everything the moment you close the window.

The Problem

AI assistants are powerful but stateless. Every new session starts from zero. For a solo founder managing multiple projects, this means repeating context, losing decisions, and watching agents make the same mistakes twice.

The Solution

A structured knowledge graph that captures entities, relationships, decisions, tasks, goals, and learning moments. AI agents connect via MCP (Model Context Protocol) and get a full briefing at the start of every session, including what happened while they were away.

The Story

Where it started

After months of working with AI agents across multiple projects, the same problem kept appearing: every new session was a blank slate. Decisions got lost, context had to be re-explained, and agents would repeat mistakes they had already been corrected on. The knowledge graph was built to fix that, to give AI agents the kind of persistent memory and institutional knowledge that a human team member would naturally accumulate.

Where it is now

Live and in daily use across all projects. The system tracks entities, relationships, tasks, goals, metrics, and learning moments. Agents get a tiered briefing at session start, with real-time drift detection and cross-project awareness. The infrastructure enforces the rules that agents would otherwise forget.

Where it's going

Open-sourcing the core as a tool for other solo founders and AI-native teams. Adding a web dashboard for visual exploration, deeper analytics on agent learning patterns, and expanding the automated scheduling and monitoring capabilities.

Key Highlights

Full MCP server for Claude Code and other AI tools

Tiered session briefing system (load only what you need)

Cross-project dispatcher that recommends what to work on next

Automated drift detection and codebase auditing

Daily plan tracking with goal alignment

Tech Stack

TypeScriptSQLiteMCP ProtocolRailwayAnthropic APIResend

By the Numbers

6 projects tracked

MCP-native integration

Cross-session continuity

Automated daily briefings