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 |
|---|---|
| 2026-08-02 | 550 |
| 2026-08-06 | 550 |
| 2026-08-12 | 708 |
| 2026-08-18 | 811 |
| 2026-08-19 | 827 |
| 2026-08-20 | 844 |
| 2026-08-21 | 859 |
| 2026-08-22 | 871 |
| 2026-08-23 | 882 |
| 2026-08-24 | 899 |
| 2026-08-25 | 919 |
| 2026-08-26 | 938 |
| 2026-08-27 | 950 |
| 2026-08-28 | 968 |
| 2026-08-29 | 983 |
| 2026-08-30 | 1005 |
| 2026-08-31 | 1020 |
| 2026-09-01 | 1037 |
| 2026-09-02 | 1053 |
| 2026-09-03 | 1071 |
| 2026-09-04 | 1086 |
| 2026-09-05 | 1107 |
| 2026-09-06 | 1116 |
| 2026-09-07 | 1141 |
| 2026-09-08 | 1157 |
| 2026-09-09 | 1172 |
| 2026-09-10 | 1183 |
| 2026-09-11 | 1207 |
| 2026-09-12 | 1214 |
| 2026-09-13 | 1230 |
| 2026-09-14 | 1242 |
| 2026-09-15 | 1259 |
| 2026-09-16 | 1276 |
| 2026-09-17 | 1283 |
| 2026-09-18 | 1284 |
| 2026-09-19 | 1285 |
| 2026-09-25 | 1286 |
| 2026-09-29 | 1287 |
| 2026-09-30 | 1288 |
| 2026-10-03 | 1290 |
| 2026-10-05 | 1289 |
| 2026-10-06 | 1290 |
| 2026-10-09 | 1293 |
| 2026-10-10 | 1294 |
| 2026-10-13 | 1295 |
| 2026-10-14 | 1297 |
| 2026-10-15 | 1298 |
| 2026-10-16 | 1299 |
| 2026-10-18 | 1300 |
| 2026-10-19 | 1302 |
| 2026-10-20 | 1304 |
| 2026-10-21 | 1305 |
| 2026-10-22 | 1306 |
| 2026-10-25 | 1306 |
| 2026-10-26 | 1307 |
| 2026-10-27 | 1309 |
| 2026-10-29 | 1321 |
| 2026-10-30 | 1330 |
| 2026-10-31 | 1335 |
| 2026-11-01 | 1346 |
| 2026-11-02 | 1354 |
| 2026-11-03 | 1361 |
| 2026-11-04 | 1372 |
Today
+11 stars today
This week
+63 stars this week
This month
+83 stars this month
Momentum
142.0
growth rate 4.81%/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/app-overview-2026-09-13-v2.png" alt="Inno Agent — redesigned welcome page with preset workspaces" width="100%" /> </p> > 🎨 **September 2026 — the Web UI was rebuilt around the InnoSpark design language** (light + dark themes): a welcome page with one-click preset workspaces, a unified composer with permission-mode and model pills, an artifact-browser right panel, and rich streaming Markdown (Mermaid / SVG / ECharts / runnable code blocks) in the conversation. 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. ### Non-goals Inno Agent is a **personal** agent, and the architecture deliberately reflects that: - **One process, one active agent session.** A single in-memory prompt queue serializes all work; sessions, workspaces, and channels share it. Session switching swaps session files in place — there is no per-session agent pool. - **No multi-user concurrency, no horizontal scaling.** There is no auth model, no tenant isolation, and no sharded state. If you need a team deployment, run one instance per person. - **Backpressure is a feature, not a bug.** When the queue is busy (e.g. another session's long turn or an unanswered question card), cross-session operations answer `409 session_busy` with blocker details instead of silently queueing for minutes — the UI surfaces this so you can finish or abort the blocking turn. See
Excerpt of 18,803 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