Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
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.
| Date | Stars |
|---|---|
| 2026-07-31 | 504 |
| 2026-08-02 | 550 |
| 2026-08-06 | 550 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
60.0
growth rate 0.00%/day
# Inno Agent > An open-source **personal learning agent** with layered memory, a proactive scheduler, multi-channel messaging, and a workspace-scoped Practice Lab — built on the [Pi coding-agent SDK](https://www.npmjs.com/package/@earendil-works/pi-coding-agent) **without modifying its kernel**. [](./LICENSE) [](https://nodejs.org) [](https://github.com/hhyqhh/inno-agent/releases) [](https://hhyqhh.github.io/inno-agent-website/) **English** | [简体中文](./README.zh-CN.md) 🌐 **[Homepage](https://hhyqhh.github.io/inno-agent-website/)** · 📄 **[Technical Report](./docs/inno-agent.pdf)** (arXiv, June 2026) · 📦 **[Resource Hub](https://github.com/Chloris-Blaxk/inno-agent-hub)** (skill library + workspace presets) <p align="center"> <img src="./docs/assets/l2-wiki.png" alt="Inno Agent — L2 wiki knowledge base and graph" width="100%" /> </p> Inno Agent is a single-learner companion that organizes long-term learning support into three explicit memory layers — an **L1 learner profile**, an **L2 native wiki knowledge base**, and **L3 session records with cross-conversation retrieval** — and wraps them in a learning loop: a cron scheduler, personal IM channels (Feishu / WeChat), and a Practice Lab with an in-browser terminal. It ships in three forms that share the same runtime state: - **Desktop app** (Electron) — one-click install for macOS and Windows. - **Web UI** (React 19 + Tailwind 4) — Node HTTP server with SSE streaming, terminal, wiki graph, jobs, skills, and settings. - **Terminal CLI** (`inno`) — a pure TUI agent, no HTTP. ## Why Inno Agent General-purpose coding agents optimize for open-ended software engineering. Education is a different target: the value lies in **personalized explanation, misconception diagnosis, exercise generation, feedback, review scheduling, privacy, and low-latency continuous interaction**. Inno Agent's stances: - **Layered memory, not a flat chat summary** — learner state, archived knowledge, and recent dialogue have different lifecycles and live in separate layers. - **Durable facts go to tools, not replies** — anything that affects future teaching is written to L1/L2 via tools, so personalization is evidence-driven and traceable. - **An open, correctable learner model** — the L1 profile is inspectable and editable by the learner; unevidenced labels are forbidden. - **The SDK kernel is never modified** — all learning behavior is added through registered tools and one extension hook, keeping the runtime upstream-compatible. ## Features - 🧠 **Three-layer memory** - **L1 learner profile** — goals, knowledge states, misconceptions, preferences; summarized into a context pack injected each turn. - **L2 native wiki** — human-readable, agent-queryable pages with hybrid retrieval (lexical BM25 + knowledge graph), LLM-assisted summarization, and PDF/Office/image ingestion. - **L3 session recall** — session history indexed into SQLite (FTS5) with threshold-gated cross-conversation retrieval. - ⏰ **Proactive scheduler** — cron jobs created in natural language, runnable from the agent, the UI, or the daemon. - 💬 **Personal IM channels** — Feishu (native) plus WeChat (iLink QR login or bridge mode), with a unified dispatcher for reminders. - 🧪 **Practice Lab** — workspace-scoped web terminal (xterm.js over WebSocket) with run records the agent can read. - 🎯 **Simple Mode + presets** — one-click preset workspaces (lesson plan, PPT creation, scenario explain) for non-technical users. - 🧩 **Skill system + content hub** — browse and import skills/presets from a remote hub (GitHub repo or self-hosted bundle service). - 🔌 **Pluggable providers** — any `openai-completions` or `anthropic-messages` endpoint (Anthropic,
Excerpt of 12,182 characters
Read on GitHub
226
31
17
7
6
5
4
3
2
1
1
1
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:8d6b1b7d930eecd3, topic:memory, desc:knowledge base
matched fp:8d6b1b7d930eecd3, topic:llm-agent