# 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.

Repository: https://github.com/hhyqhh/inno-agent
Canonical: https://ross.abutalabs.com/products/inno-agent
Homepage: https://hhyqhh.github.io/inno-agent-website
Language: TypeScript
License: MIT
License Family: permissive
Topics: cli, electron, learning-agent, llm-agent, memory, personal-knowledge-management, pi-sdk, typescript
Last push: 2026-09-02T16:29:28+00:00

## Health v2 (maintenance only)
Score: 81/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 100, release rhythm 100, longevity 6
- inputs: {"age_days": 97, "days_push": 0, "days_rel": 1, "gap_med": 2.5, "n_releases_24m": 25}
- flags: young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1064, forks 201 (observed 2026-09-03T02:15:12.694014+00:00)

## Summary
No AI-extracted summary yet.

## Member repositories
- hhyqhh/inno-agent (main) score 81

## Provenance
- Observed fields: from GitHub, fetched 2026-09-03T02:15:12.694014+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Data as of 2026-08-30T08:39:29.467469+00:00.