AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompare
Home/
Memory & Context/
inno-agent
inno-agent logo

inno-agent

Active·★ 1.3k·MIT·Updated 2026-10-21
★ Essential★ Trending

Inno Agent is a single-learner companion built on the Pi coding-agent SDK, adding all learning behavior through registered tools and one extension hook without modifying the SDK kernel. Its memory is split by lifecycle: an L1 learner profile (goals, knowledge states, misconceptions, preferences), an L2 native wiki with BM25 plus knowledge-graph retrieval and PDF/Office ingestion, and L3 session records indexed in SQLite FTS5 for cross-conversation recall.

Around that sits a learning loop: cron jobs created in natural language, Feishu and WeChat channels for reminders, and a Practice Lab with an in-browser terminal whose run records the agent can read. The learner profile is inspectable and editable, and the design forbids unevidenced labels. Simple Mode presets target non-technical users such as teachers preparing lesson plans or slides.

© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

MCP ServersCode AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.

Guides

It ships as an Electron desktop app (unsigned on macOS), a React web UI and a terminal CLI, with Docker for self-hosting. Providers can be any OpenAI- or Anthropic-compatible endpoint, including Ollama. It is explicitly single-user: one process, one active session, no auth or multi-tenancy. License is MIT.

This write-up is based on the project's README and public repository data. We have not hand-tested the tool. Data as of 2026-10-22.

License
MIT
Latest release
v0.7.0 · 2026-10-08
Last commit
2026-10-21
Contributors
18
Forks
231
Open issues and PRs
8
First published
2026-05-28

Source: GitHub, npm and PyPI public APIs.

#agent-framework#cli#electron#learning-agent#llm-agent#memory#personal-knowledge-management#pi-sdk
$ Install
$ git clone https://github.com/hhyqhh/inno-agent.git && cd inno-agent && npm install && npm run build
↗ Visit site★ GitHub
01

Features

01L1 learner profile, L2 wiki with BM25 + knowledge-graph retrieval, L3 session recall on SQLite FTS5
02Natural-language cron jobs for proactive reminders
03Feishu and WeChat channels with a unified reminder dispatcher
04Practice Lab with an in-browser terminal whose run records the agent can read
05Any OpenAI- or Anthropic-compatible provider, including Ollama and DeepSeek
02

Why choose it

+Layered memory keeps learner profile, knowledge and recent dialogue separate, so personalization is traceable.
+Proactive reminders through Feishu and WeChat turn it into an ongoing tutor rather than a chat box.
+Learner profile is open and editable, and unevidenced labels are disallowed by design.
03

Trade-offs

!Single-user by design, with no auth or multi-tenant support; one instance per person.
!macOS build is unsigned and needs a manual override on first launch.
!IM channels focus on Feishu and WeChat, which matters less outside China.
04

Maintenance check

ActiveChecked: 2026-10-20
Last commit
2026-10-12
Commits, last 90 days
100+
Releases, last 90 days
15
Latest release
v0.7.0 (2026-10-08)
Open issues
8
Recent issues with at least one comment
—

Status rule: archived on GitHub = Archived; last commit within 90 days = Active; 91 to 365 days = Slowing; older = Stale. All figures come from the GitHub API on the date shown.

Most discussed open issues

  • #169 Workspace legacy files can redirect model traffic and trigger private-channel jobs without confirmation0 comments · 2026-08-11
  • #162 [安全/健壮性] 中低危批量清单：进程兜底、body 上限、文件权限、realpath、日志落盘等 8 项0 comments · 2026-08-09
05

Compatibility

macOS / Windows
Desktop app
Verified via docs
Docker
Web UI
Verified via docs
Feishu / WeChat
IM channels
Verified via docs
Ollama
Local models
Verified via docs
06

Quick start

1
$ git clone https://github.com/hhyqhh/inno-agent.git
2
$ cd inno-agent
3
$ npm install
4
$ npm run build
07

Use cases

↳Personal tutor that tracks goals and misconceptions over time
↳Building a personal wiki from PDFs and notes
↳Teachers preparing lesson plans and slides with presets
08

Alternatives

⚡Top VS:
VSletta★25.2k→VSmagic-context★2.4k→VSVCPToolBox★2.4k→VS

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Why choose it03Trade-offs04Maintenance check05Compatibility06Quick start
  • #161 [安全] IM 渠道注入面：消息直驱 bash agent、WeChat 未自动锁定 allowlist、personalOnly 配置残留0 comments · 2026-08-09
  • #160 [安全] Docker 部署默认暴露面：容器内 root + 3000 端口全接口发布0 comments · 2026-08-09
  • #159 [安全] 默认绑定 0.0.0.0 + 全 API 无认证 + 未认证 WebSocket 终端（局域网可达 RCE）0 comments · 2026-08-09

    • Issue titles are quoted from GitHub. Open the link to check whether a problem still applies to the version you use.

    AReaL
    ★5.9k
    →
    letta logo
    letta★ 25.2k
    Letta is the platform for building stateful agents: open AI with advanced memory that can learn and self-improve over time.
    VSCompare→
    magic-context logo
    magic-context★ 2.4k
    Unbounded context. Memory that manages itself. One session, for life. The hippocampus for coding agents, part of CortexKit.
    VSCompare→
    VCPToolBox logo
    VCPToolBox★ 2.4k
    VCP 部署在 AI 模型 API 与前端应用之间，是面向AGI OS开发和探索的工业级基建示范项目。通过统一指令协议、多层级持久化记忆、分布式插件引擎及多 Agent 协作框架，将原本“无状态、无记忆、无工具调用能力”的大语言模型，彻底改造成拥有永久自我意识、物理世界操作权及群体协作智能的完整智能体系统。
    VSCompare→
    AReaL logo
    AReaL★ 5.9k
    The RL Bridge for LLM-based Agent Applications. Made Simple & Flexible.
    VSCompare→
    MaiBot logo
    MaiBot★ 6.4k
    MaiSaka, an LLM-based intelligent agent, is a digital lifeform devoted to understanding you and interacting in the style of a real human. She does not pursue perfection, nor does she seek efficiency; instead, she values warmth, authenticity, and genuine connection.
    VSCompare→
    Acontext logo
    Acontext★ 3.7k
    Data platform for context engineering. Context data platform that stores, observes and learns. Join the community❤️: https://discord.acontext.io
    VSCompare→
    mcp-memory-service logo
    mcp-memory-service★ 2.0k
    Stop re-explaining your project to AI every session. Automatic context memory for Claude, VS Code, Cursor, and 13+ AI tools.
    VSCompare→
    YourMemory logo
    YourMemory★ 270
    Agentic AI memory with Ebbinghaus forgetting curve decay. +16pp better recall than Mem0 on LoCoMo.
    VSCompare→
    See all alternatives →
    07
    Use cases
    08Alternatives
    hhyqhh /
    inno-agent
    ↗

    A personal learning agent with three memory layers, reminders and a practice terminal

    1.3k231MIT
    Last commit2d ago
    StatusActive
    CategoryMemory & Context
    Contributors18
    Latest releasev0.7.0
    Links
    Documentation↗Discussion↗Issues↗Releases↗
    Cloud Infrastructure
    Ad

    Deploy on DigitalOcean

    Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

    Claim $200 Free Credit