jarvis-orb
Persistent 4-tier AI memory (episodic, semantic, project, procedural) with temporal scoring, contradiction detection, entity tracking, and real-time desktop visualization orb.
README
<div align="center">
<br>
<picture> <source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/whynowlab/jarvis-orb/main/assets/demo.gif"> <img src="https://raw.githubusercontent.com/whynowlab/jarvis-orb/main/assets/demo.gif" alt="Jarvis Orb" width="280"> </picture>
<sub>Actual footage. Not a mockup.</sub>
<br><br>
Jarvis Orb
Not a tool. A presence.
It remembers your decisions. It tracks your world. It glows on your desktop, alive.
<br>
Website · Download · Report Bug
English | 한국어
</div>
The Problem
Every session, your AI starts over. Your decisions, your preferences, your project context — gone. You explain yourself again. And again. And again.
- "We decided to use SQLite." → Three days later, it suggests PostgreSQL.
- "This PR was merged yesterday." → It doesn't know. It never remembers state.
- "What was the architecture decision?" → Gone. The session ended.
The Solution
Jarvis Orb gives your AI a persistent brain and shows its thought process as a living orb on your desktop.
| Without Jarvis Orb | With Jarvis Orb | |
|---|---|---|
| Context | Every session starts from zero | Carries over automatically |
| Decisions | Reversed decisions come back | Contradictions detected and filtered |
| State | "What's the status?" → guess | Exact state + transition history |
| Visibility | No idea what it's thinking | Every thought, live on your screen |
Install
macOS (Apple Silicon) / Linux:
curl -fsSL https://raw.githubusercontent.com/whynowlab/jarvis-orb/main/install.sh | bash
Requires Apple Silicon (M1/M2/M3/M4). Use the terminal command above for the smoothest install experience.
Windows (PowerShell):
irm https://raw.githubusercontent.com/whynowlab/jarvis-orb/main/install.ps1 | iex
That's it. Brain starts. Orb floats. Claude Code connects.
Brain Lite
Watch it think.
| # | Feature | Description |
|---|---|---|
| 01 | 4-Tier Memory | Episodic, semantic, project, procedural — auto-classified and ranked by recency |
| 02 | Temporal Scoring | 30-day half-life decay. Recent memories surface first. Old context fades naturally |
| 03 | Contradiction Detection | Conflicting memories flagged. Superseded decisions marked stale. Only truth surfaces |
| 04 | Entity Tracking | Projects, PRs, decisions tracked as objects with full state transition history |
| 05 | Relationship Storage | People → projects → decisions connected as a lightweight knowledge graph |
| 06 | FTS5 Search | Full-text search across all memories with observation filtering |
MCP Tools
memory_save Save a memory (auto-classified into 4 tiers)
memory_search Search with temporal scoring + contradiction filtering
memory_verify Mark memories as verified, superseded, or contradicted
entity_create Track a project, person, decision, or tool
entity_update Update entity state (records transition history)
entity_query Query entities by type or name
entity_relate Create relationships between entities
Works with Claude Code, Cursor, and any MCP-compatible tool.
Orb
Every thought, visible.
The orb is not decorative. It shows you what the brain is doing, in real time.
| Brain Event | Orb Response |
|---|---|
| Memory saved | Particles absorb into orb |
| Contradiction detected | Red/orange pulse wave |
| Entity state changed | Cyan flash + scale pulse |
| Search executed | Violet color shift |
| Context compressed | Shrink, brighten, expand |
| Team dispatched | Orb splits into sub-orbs |
3MB desktop app. Always-on-top. Draggable. Click to see logs.
In Practice
Monday morning standup — "What did we work on last week?" Brain searches episodic memories with temporal scoring. Returns a ranked summary. No digging through chat history.
Mid-project contradiction — "We should use Redis for caching." Brain detects this contradicts a previous decision. Flags the conflict. The orb pulses red. You see it happening.
New session, no context loss — "Continue where we left off." Brain loads project state, recent decisions, and your preferences. No re-explaining.
Architecture
Claude Code / Cursor
↕ MCP (stdio)
Brain Lite — Python · aiosqlite · FTS5 · ~/.jarvis-orb/brain.db
↕ WebSocket
Orb — Tauri · Three.js · WebGL · 3MB · Always-on-top
| 3MB | App size. Not 150MB. |
| 7 | MCP tools. Memory, entities, search. |
| 0 | Cloud dependencies. Everything local. |
Origin
Jarvis Orb was extracted from a working AI control plane — Jarvis — running 19 modules, a knowledge graph with 100+ entities, 500+ memories, and 22 agent teams. This is the lightweight, open-source version of that brain.
"I built a personal AI operating system. After months of using it, I realized the core — the brain and the visualization — should be available to everyone."
Roadmap
- Orb Customization — Custom orb skins, color themes, animation profiles
- Brain Pro — Advanced memory with full knowledge graph, multi-model routing, autonomous reasoning loop
- Auto-update — Seamless in-app updates
- Plugin System — Extend Brain with custom MCP tools
Contributing
PRs welcome. See CONTRIBUTING.md.
git clone https://github.com/whynowlab/jarvis-orb.git
cd jarvis-orb
# Brain
cd brain && uv venv .venv && source .venv/bin/activate
uv pip install aiosqlite websockets mcp pytest pytest-asyncio
python -m pytest tests/ -v
# Orb
cd ../orb && pnpm install && pnpm tauri dev
License
MIT
<div align="center">
<br>
Your AI will start remembering.
<br>
</div>
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。