MCPInstall

hermes-kanban-obsidian-integration

Turn Hermes into an autonomous project executor using Kanban boards inside Obsidian vault with visual rendering and REST API control

Installs
146
Last 24h
—
Trending rank
—
Security
Not audited

Install

Works with every agent the skills CLI supports.

npx skills add https://github.com/reason-machines/hermes-skills --skill hermes-kanban-obsidian-integration
  1. 01

    Install

    Run the command in your project. The CLI asks which agents to install for.

  2. 02

    Describe the task

    Ask your agent for something this skill covers. It loads hermes-kanban-obsidian-integration automatically when relevant.

  3. 03

    Review the result

    The agent follows the SKILL.md steps, scripts and references bundled with the skill.

SKILL.md

The instructions your agent reads when the skill is triggered.

Hermes Kanban Obsidian Integration

Skill by ara.so — Hermes Skills collection.

Overview

Hermes Kanban Bridge is an Obsidian plugin that exposes a REST API (default port 27124) allowing Hermes agents to manage Kanban boards inside your Obsidian vault. Boards are stored as Markdown files with YAML frontmatter, rendered visually by the obsidian-kanban community plugin.

Architecture:

  • Hermes Agent → HTTP REST API → hermes-kanban-bridge plugin → Obsidian Vault API → Markdown files → obsidian-kanban visual renderer

Key Features:

  • Break goals into structured Kanban boards via API
  • Move cards, update metadata, query state in real-time
  • Daily standups and weekly review rituals
  • Fully local, no cloud dependencies
  • Visual board rendering in Obsidian

Installation

Automated Install (Recommended)

# Clone the repository
git clone https://github.com/GumbyEnder/hermes-kanban.git
cd hermes-kanban

# Edit install script to set your vault path
export VAULT_PATH="/path/to/your/ObsidianVault"

# Run automated installer
bash hermes-kanban-install.sh

The script installs:

  1. hermes-kanban-bridge plugin (REST API server)
  2. obsidian-kanban plugin (visual renderer)
  3. Registers both in vault's community-plugins.json

Manual Installation

Build the plugin:

cd plugin
npm install
npm run build

Copy to vault:

VAULT="/path/to/your/vault"
mkdir -p "$VAULT/.obsidian/plugins/hermes-kanban-bridge"
cp main.js manifest.json "$VAULT/.obsidian/plugins/hermes-kanban-bridge/"

Install obsidian-kanban renderer:

KANBAN_DIR="$VAULT/.obsidian/plugins/obsidian-kanban"
mkdir -p "$KANBAN_DIR"
TAG="2.0.51"
for f in main.js manifest.json styles.css; do
  curl -sL "https://github.com/obsidian-community/obsidian-kanban/releases/download/$TAG/$f" -o "$KANBAN_DIR/$f"
done

Enable plugins in Obsidian:

  1. Reload Obsidian
  2. Settings → Community Plugins → disable Safe Mode
  3. Enable "Hermes Kanban Bridge" and "Kanban"
  4. Verify notice: "Hermes Kanban Bridge started on port 27124"

Install Hermes skills:

mkdir -p ~/.hermes/profiles/$HERMES_PROFILE/skills/productivity
cp skills/*.md ~/.hermes/profiles/$HERMES_PROFILE/skills/productivity/

Configuration

Plugin Settings (Obsidian → Settings → Hermes Kanban Bridge):

SettingDefaultDescription
Port27124Local REST API port
Board folderKanbanVault folder for boards
Trust modeconfirmconfirm = approval modal, auto = silent
Enable serveronToggle REST API

Network Configuration for Remote Access:

If Hermes runs on a different machine, use Tailscale/LAN IP instead of localhost.

Windows firewall rule:

netsh advfirewall firewall add rule name="Hermes Kanban Bridge" dir=in action=allow protocol=TCP localport=27124

Verify listening on all interfaces:

netstat -ano | findstr 27124
# Should show: TCP  0.0.0.0:27124  LISTENING

REST API Reference

Base URL: http://localhost:27124 (or remote IP)

Health Check

curl http://localhost:27124/health
# {"ok":true,"status":"running","port":27124,"version":"1.0.0"}

Create Board

curl -X POST http://localhost:27124/boards \
  -H "Content-Type: application/json" \
  -d '{
    "name": "Q3 Launch",
    "columns": ["Backlog", "In Progress", "Review", "Done"]
  }'
# {"success":true,"board_id":"Q3-Launch","path":"Kanban/Q3-Launch.md"}

Add Card

curl -X POST http://localhost:27124/boards/Q3-Launch/cards \
  -H "Content-Type: application/json" \
  -d '{
    "title": "Design landing page",
    "column": "Backlog",
    "metadata": {
      "priority": "high",
      "assignee": "alice"
    }
  }'
# {"success":true,"card_id":"card-001"}

Move Card

curl -X PATCH http://localhost:27124/boards/Q3-Launch/cards/card-001 \
  -H "Content-Type: application/json" \
  -d '{
    "column": "In Progress"
  }'
# {"success":true}

Query Board State

# Get all cards
curl http://localhost:27124/boards/Q3-Launch/cards
# {"cards":[{"id":"card-001","title":"Design landing page","column":"In Progress",...}]}

# Filter by column
curl http://localhost:27124/boards/Q3-Launch/cards?column=Backlog

# Filter by metadata
curl http://localhost:27124/boards/Q3-Launch/cards?assignee=alice

Daily Standup

curl -X POST http://localhost:27124/rituals/standup \
  -H "Content-Type: application/json" \
  -d '{
    "board_id": "Q3-Launch"
  }'
# {"summary":"3 cards in progress, 2 blocked, 5 completed yesterday"}

Weekly Review

curl -X POST http://localhost:27124/rituals/weekly-review \
  -H "Content-Type: application/json" \
  -d '{
    "board_id": "Q3-Launch"
  }'
# {"summary":"12 cards completed this week, velocity: 2.4 cards/day"}

Python Client Usage

import requests
import os

BASE_URL = os.getenv("HERMES_KANBAN_URL", "http://localhost:27124")

class KanbanClient:
    def __init__(self, base_url=BASE_URL):
        self.base = base_url
    
    def health_check(self):
        """Verify server is running"""
        r = requests.get(f"{self.base}/health")
        return r.json()
    
    def create_board(self, name, columns):
        """Create new Kanban board"""
        r = requests.post(
            f"{self.base}/boards",
            json={"name": name, "columns": columns}
        )
        return r.json()
    
    def add_card(self, board_id, title, column, metadata=None):
        """Add card to board"""
        payload = {"title": title, "column": column}
        if metadata:
            payload["metadata"] = metadata
        r = requests.post(
            f"{self.base}/boards/{board_id}/cards",
            json=payload
        )
        return r.json()
    
    def move_card(self, board_id, card_id, new_column):
        """Move card between columns"""
        r = requests.patch(
            f"{self.base}/boards/{board_id}/cards/{card_id}",
            json={"column": new_column}
        )
        return r.json()
    
    def query_cards(self, board_id, filters=None):
        """Query cards with optional filters"""
        params = filters or {}
        r = requests.get(
            f"{self.base}/boards/{board_id}/cards",
            params=params
        )
        return r.json()
    
    def daily_standup(self, board_id):
        """Run daily standup ritual"""
        r = requests.post(
            f"{self.base}/rituals/standup",
            json={"board_id": board_id}
        )
        return r.json()

# Example usage
client = KanbanClient()

# Verify connection
print(client.health_check())

# Create board
board = client.create_board(
    name="Product Roadmap",
    columns=["Ideas", "Planned", "In Development", "Shipped"]
)
board_id = board["board_id"]

# Add cards
client.add_card(
    board_id,
    "Implement dark mode",
    "Planned",
    metadata={"priority": "medium", "estimate": "3d"}
)

# Query blocked items
blocked = client.query_cards(board_id, {"status": "blocked"})
print(f"Blocked cards: {len(blocked['cards'])}")

# Run standup
standup = client.daily_standup(board_id)
print(standup["summary"])

Board Markdown Format

Boards are stored as Markdown with YAML frontmatter:

---
kanban-plugin: board
---

## Backlog

- [ ] Design landing page #high @alice
- [ ] Set up CI/CD pipeline #medium @bob

## In Progress

- [ ] Implement authentication #high @alice
  - Started: 2026-05-15
  - Blocked: waiting on API keys

## Review

- [ ] Write user documentation #low @carol

## Done

- [x] Initialize project repository
  - Completed: 2026-05-14

Important: The kanban-plugin: board frontmatter triggers visual rendering. Without it, boards display as plain Markdown.

Common Patterns

Breaking Down a Project

def break_down_project(client, project_name, tasks):
    """Create board and populate with tasks"""
    board = client.create_board(
        name=project_name,
        columns=["Backlog", "In Progress", "Review", "Done"]
    )
    board_id = board["board_id"]
    
    for task in tasks:
        client.add_card(
            board_id,
            task["title"],
            "Backlog",
            metadata=task.get("metadata", {})
        )
    
    return board_id

# Usage
tasks = [
    {"title": "Research competitors", "metadata": {"priority": "high"}},
    {"title": "Draft wireframes", "metadata": {"priority": "medium"}},
    {"title": "Set up analytics", "metadata": {"priority": "low"}}
]

board_id = break_down_project(client, "Market Analysis", tasks)

Automated Workflow Progression

def progress_workflow(client, board_id):
    """Move cards through workflow automatically"""
    # Get all cards in Review
    cards = client.query_cards(board_id, {"column": "Review"})
    
    for card in cards["cards"]:
        # Check if ready to move (example: all subtasks done)
        if card_is_complete(card):
            client.move_card(board_id, card["id"], "Done")
            print(f"Completed: {card['title']}")

def card_is_complete(card):
    """Example validation logic"""
    metadata = card.get("metadata", {})
    return metadata.get("reviewed", False) and metadata.get("tests_passing", False)

Daily Ritual Integration

import schedule
import time

def daily_standup_job():
    """Run standup for all active boards"""
    client = KanbanClient()
    
    # Get all boards
    boards = requests.get(f"{client.base}/boards").json()
    
    for board in boards["boards"]:
        if board.get("active", True):
            result = client.daily_standup(board["id"])
            send_notification(result["summary"])

# Schedule daily at 9 AM
schedule.every().day.at("09:00").do(daily_standup_job)

while True:
    schedule.run_pending()
    time.sleep(60)

Testing

The project includes 105 tests (59 unit, 46 E2E):

# All tests
pytest tests/

# E2E only
pytest tests/e2e/

# Skip slow TUI tests
pytest tests/e2e/ -k "not tui"

# Mock API server (no Obsidian required)
python tests/e2e/mock_api_server.py

Mock API for development:

# tests/e2e/mock_api_server.py implements all REST endpoints
# Use for testing without running Obsidian

import requests
# Start mock server on port 27125
response = requests.get("http://localhost:27125/health")
assert response.json()["ok"] == True

Troubleshooting

Connection Refused

Symptoms: curl: Failed to connect to localhost port 27124

Solutions:

  1. Verify plugin is enabled: Settings → Community Plugins → Hermes Kanban Bridge = ON
  2. Look for notice "Hermes Kanban Bridge started on port 27124"
  3. Toggle plugin off/on to restart server
  4. Check port not in use: lsof -i :27124 (Unix) or netstat -ano | findstr 27124 (Windows)

Board Shows as Markdown List

Symptoms: Board opens as plain text instead of visual kanban

Solution: Add YAML frontmatter to top of file:

---
kanban-plugin: board
---

All API-created boards include this automatically. Manually created boards need it added.

Remote Access Not Working

Symptoms: Can't connect from Hermes on different machine

Solutions:

  1. Use Obsidian machine's Tailscale/LAN IP instead of localhost
  2. Verify server binds to 0.0.0.0 not 127.0.0.1:
    netstat -ano | findstr 27124
    # Should show: TCP  0.0.0.0:27124  LISTENING
    
  3. Add firewall rule (Windows):
    netsh advfirewall firewall add rule name="Hermes Kanban Bridge" dir=in action=allow protocol=TCP localport=27124
    
  4. macOS: System Settings → Network → Firewall → allow Obsidian

Plugin Not Appearing

Symptoms: Plugin not in Community Plugins list

Solution: Quit Obsidian completely (not just reload), then reopen. Obsidian requires full restart to detect new plugin folders.

Port Conflict

Symptoms: Server fails to start, port already in use

Solution:

  1. Change port: Settings → Hermes Kanban Bridge → Port → set to 27125 (or other)
  2. Toggle plugin off/on to apply
  3. Update Hermes skill configs and HERMES_KANBAN_URL to new port

Environment Variables

# REST API base URL (default: http://localhost:27124)
export HERMES_KANBAN_URL="http://192.168.1.100:27124"

# Hermes profile for skills installation
export HERMES_PROFILE="frodo"

# Obsidian vault path for scripts
export VAULT_PATH="/Users/alice/Documents/ObsidianVault"

Integration with Hermes Agent

Once skills are installed (~/.hermes/profiles/*/skills/productivity/), interact naturally:

Voice Commands:

  • "Break down the Q3 launch into a Kanban board"
  • "Run my daily standup"
  • "What cards are blocked?"
  • "Move the authentication task to In Progress"
  • "Give me a weekly review"

Hermes uses the installed skills to translate commands into REST API calls automatically.

Resources

FAQ

What does the hermes-kanban-obsidian-integration skill do?

Turn Hermes into an autonomous project executor using Kanban boards inside Obsidian vault with visual rendering and REST API control

How do I install hermes-kanban-obsidian-integration?

Run npx skills add https://github.com/reason-machines/hermes-skills --skill hermes-kanban-obsidian-integration in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/hermes-kanban-obsidian-integration/ (personal) or .claude/skills/hermes-kanban-obsidian-integration/ (project).

Which AI agents can use hermes-kanban-obsidian-integration?

Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.

Is hermes-kanban-obsidian-integration safe to install?

No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.

Who maintains hermes-kanban-obsidian-integration?

It is published by reason-machines in reason-machines/hermes-skills. It has 146 recorded installs.

More from reason-machines/hermes-skills

View all →

hermes-agent-self-evolution

reason-machines/hermes-skills

Evolutionary self-improvement for Hermes Agent using DSPy + GEPA to optimize skills, prompts, and code

AI & Agents323 installs

hermes-webui-agent

reason-machines/hermes-skills

Expert in deploying, configuring, and using Hermes WebUI—a web interface for Hermes Agent with persistent memory, scheduled jobs, and multi-platform messaging.

267 installs

awesome-hermes-agent-ecosystem

reason-machines/hermes-skills

Open the skill to read its SKILL.md instructions.

232 installs

hermes-agent-framework

reason-machines/hermes-skills

Open the skill to read its SKILL.md instructions.

219 installs

hermes-workspace-ai-agent-ui

reason-machines/hermes-skills

Open the skill to read its SKILL.md instructions.

Frontend & Design213 installs

hermes-desktop-companion

reason-machines/hermes-skills

Open the skill to read its SKILL.md instructions.

206 installs

Popular productivity & automation skills

View category →

agent-browser

vercel-labs/agent-browser

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.

OfficialProductivity & Automation1.3M installs

lark-doc

open.feishu.cn

飞书云文档(Docx / Wiki)内容操作:读取、创建、编辑文档,插入或下载图片附件,以及操作思维笔记。用户提供文档 URL/token(包括 doubao.com 的 /docx/、/wiki/)时使用;按 URL 路径/token 而非域名路由;/page/ 是妙搭应用,非飞书云文档。文档内嵌资源按读取参考中的统一规则分流。独立评论操作走 lark-drive;随正文读取评论使用 docs +fetch。表格或 Base 内部数据操作不在本 skill。

lark-base

open.feishu.cn

飞书多维表格(Base)操作:建表、字段、记录、视图、统计、公式/lookup、表单、仪表盘、应用模式(BaseApp/AppMode 页面与组件)、Workspace 目录、workflow、角色权限、模板中心(多维表格模板分类/列表/搜索);遇到 Base/多维表格/bitable、BaseApp/AppMode、/base/ 或 /app/ 链接时使用。BaseApp 不走 lark-apps;文件导入/导出转 lark-drive,认证/授权转 lark-shared。

lark-drive

open.feishu.cn

飞书云空间(云盘/云存储):管理 Drive 文件和文件夹,包含上传/下载、创建文件夹、复制/移动/删除、查看元数据、查询权限设置、评论/权限/订阅、标题、版本、飞书文档密级标签(secure labels)和本地文件导入。用户需要整理云盘目录、处理云空间资源 URL/token、判断链接类型/真实 token/标题,或导入 Word/Markdown/Excel/CSV/PPTX/.base 为 docx/sheet/bitable/slides 时使用;doubao.com 云空间 URL/token 也按资源路径和 token 路由,不回退 WebFetch。不负责:文档内容编辑(走 lark-doc)、表格/Base 表内数据操作(走 lark-sheets/lark-base)、知识空间节点/成员管理(走 lark-wiki)、原生 Markdown 文件读写/patch/diff(走 lark-markdown)。

lark-shared

open.feishu.cn

Use for lark-cli setup/auth tasks: auth login/status/logout, user vs bot identity, business-domain permissions (--domain, including all/docs/drive), missing scopes, revoking authorization, or handling notice JSON.

lark-im

open.feishu.cn

飞书即时通讯:收发消息和管理群聊。发送和回复消息、搜索聊天记录、管理群聊成员、上传下载图片和文件、管理表情回复、发送应用内/短信/电话加急、发送和处理交互卡片(Interactive Card)、监听卡片按钮回调(card.action.trigger)。当用户需要发消息、查看或搜索聊天记录、下载聊天中的文件、查看群成员、搜索群、创建群聊或话题群、管理标记数据、管理 Feed 置顶(添加/移除/查询置顶会话)、管理标签数据、处理卡片回调时使用。