BigHugger
GH Repository · hhyqhh

inno-agent

An open-source personal learning agent with three-layer memory (learner profile / wiki knowledge base / cross-conversation recall), a proactive scheduler, personal IM channels, and a workspace-scoped Practice Lab — built on the Pi SDK.

stars
1,283
30-day movement
starts with the next reading
Related entries
60
Connections
2
agent-frameworkdockerpi-sdkTypeScriptpersonal-knowledge-managementllm-agenttypescriptlearning-agentnodememoryelectroncli

inno-agent is an open-source personal learning agent built on the Pi SDK, written in TypeScript. It combines a three-layer memory system (learner profile, wiki knowledge base, cross-conversation recall) with a proactive scheduler, personal IM channels, and a workspace-scoped Practice Lab.

You want a self-hosted learning companion that remembers your profile and past conversations rather than starting fresh each session.

Use it to

  • Run a personal learning agent from the CLI or Electron app
  • Maintain a wiki knowledge base alongside a learner profile
  • Recall context across separate conversations
  • Schedule proactive learning prompts via personal IM channels
  • Practice skills in a workspace-scoped Practice Lab

For Developers building personal LLM agents for learning and knowledge management

Role
agent-framework
Language
TypeScript
Licence
MIT
Forks
231
Open issues
5
Last push
2026-09-16
Latest release
v0.2.0 · 2026-05-30
topicslearning-agentllm-agentmemorypersonal-knowledge-managementpi-sdktypescript