Lightning-fast personal AI assistant with layered memory, graph-based recall, MCP support, workflow repair, and multi-channel runtime. fagent helps long-running, interrupted workflows stay organized, allowing the agent to remember task state, decisions, and relationships, not just chat history.

AppSignal — Track your app’s health, errors and performance with ease

Track your app’s health, errors and performance with ease

Hi everyone! I'm a beginner developer fascinated by AI, neural networks, and agents. I built fagent because I noticed that most agent runtimes work fine for short tasks, but struggle with long-running or interrupted workflows. Agents often forget context, previous decisions, or dependencies once you restart them. To address this, I designed fagent with layered memory, graph-based recall, and a simple workflow repair system. It also supports multiple channels like CLI, terminal, and messaging platforms. My goal was to create a personal AI assistant that actually remembers and helps maintain continuity over time. I’d love your feedback on the usefulness of graph-based memory, workflow inspection, and real-world use cases for a memory-first agent.

AppSignal — Track your app’s health, errors and performance with ease

Track your app’s health, errors and performance with ease

fagent

Memory-first AI agent runtime for long-running.

Memory-first AI agent runtime for long-running.