Probably just end up embarrassing myself, but here is Sidekick

Developer Geoff McCaughan released Sidekick, a self-hosted AI agent platform with persistent memory and 70 MCP tools that can extend itself without code changes. The platform runs on a remote machine, learns from user workflows, and provides autonomous agent capabilities via a single AGENTS.md file read by opencode. Sidekick distinguishes itself from other MCP servers by offering persistent memory, tool generation, and an independent Agent Bridge for complex tasks.

Autonomous Agent Platform A self-hosted AI agent platform with persistent memory, 70 MCP tools, and the ability to extend itself. Runs on your remote machine, learns from your workflow, and grows its own capabilities—no code changes required. How? A single AGENTS.md file that opencode reads on every session start. No plugins, no hooks — just markdown. Note:This project was developed using its own remote execution tools — the AI assistant used Sidekick's infrastructure to help build and test the very system it runs on. What you need: Node.js 22+, a remote Ubuntu/Debian machine with SSH access VPS, home server, Raspberry Pi , Git, ~15 minutes. Clone the repo git clone https://github.com/geoffmcc/sidekick.git cd sidekick Copy env template and edit copy .env.example .env Edit .env with your API key and settings Deploy to your remote machine Windows .\deploy.ps1 -IP "YOUR REMOTE IP" Or deploy Linux/Mac ./deploy.sh -IP YOUR REMOTE IP First deploy to a fresh VM: The script will automatically: - Prompt for the initial SSH user e.g., ubuntu, admin, root - Prompt for the initial user's password once - Create the sidekick user and install Node.js 20 LTS - Configure sudo permissions for service management - Install and enable systemd services - Install your SSH key for passwordless access - Open firewall ports if UFW is active - Deploy the application and start services Subsequent deploys are fully automated — no password required. For automation/CI , specify the initial user with -InitialUser : Windows .\deploy.ps1 -IP "YOUR REMOTE IP" -InitialUser "ubuntu" Linux/Mac ./deploy.sh -IP YOUR REMOTE IP -InitialUser ubuntu Airgap/Offline Deploy — If your remote server cannot reach GitHub firewall, air-gapped network, etc. , use the --scp flag to sync files individually via SSH: Windows .\deploy.ps1 -IP "YOUR REMOTE IP" -Scp Linux/Mac ./deploy.sh -IP YOUR REMOTE IP --scp This uses the original SCP-based approach, copying files one-by-one from your local machine. No internet access required on the remote server. Open http://YOUR REMOTE IP:4098/ in a browser. That's it — Sidekick is live. Every time you open opencode, it automatically reads ~/.config/opencode/AGENTS.md and loads whatever instructions are in it into the AI's context. Sidekick provides the infrastructure — remote execution tools, persistent memory, and an autonomous agent — that the AI can use. You open opencode — it reads AGENTS.md Sidekick's tools and instructions are loaded — the AI now knows about the remote machine, the tools, and how to use them You work — the AI can call sidekick tools to execute commands on the remote machine, store/retrieve persistent data, or you can submit tasks to the autonomous Agent Bridge via the dashboard Session ends — but anything stored in Sidekick's KV persists for next time Sidekick is the infrastructure. The AI running in opencode uses that infrastructure to help you work. Without AGENTS.md , the AI doesn't know Sidekick exists. With it, the AI has persistent remote capabilities. Most MCP servers are just tool wrappers—they give AI access to specific APIs or services. Sidekick is fundamentally different: Sidekick remembers everything. Your decisions, project context, API responses, workflow patterns—it all persists in a structured KV store organized by project. The AI doesn't start from scratch every session. Teach Sidekick new procedures, and it can generate its own tools. The sidekick teach tool lets you describe a workflow in natural language, and Sidekick creates the implementation. It's not just using tools—it's building them. The Agent Bridge runs independently from your main AI session. Submit a complex task via the dashboard, and Sidekick will plan, execute, and iterate until it's done—without you babysitting each step. Context tracking - Automatically recalls relevant past decisions and patterns Health monitoring - Real-time system health checks with scoring Predictive analysis - Identifies patterns in your workflow and suggests improvements Event-driven automation - Watches for conditions and triggers actions automatically Every tool output is automatically scanned and redacted for sensitive data API keys, tokens, passwords . The dashboard has rate limiting, CSRF protection, and audit logging. The agent bridge is isolated and only accessible through the dashboard. Not just bash and file operations. Sidekick includes tools for: - GitHub integration PRs, issues, releases - Service and process management - Scheduled tasks and monitoring - Data transformation and validation - Multi-agent orchestration - Encrypted credential management - Network diagnostics and troubleshooting - Incident response and forensics - Operational runbooks and procedures - Dependency analysis and impact assessment Database operations query, backup, restore, search, migrations - And much more The result: Sidekick isn't just a tool server—it's an autonomous platform that learns, adapts, and grows with your workflow. Sidekick used its own tools to help develop itself. Here's the AI agent debugging Sidekick from within opencode: Testing the debug tool's store/cleanup/recall cycle: Diagnosing its own hallucination problem with sidekick fresheyes: Investigating why the self-improvement tool isn't working: | Capability | How | Why AGENTS.md Matters | |---|---|---| Remote code execution | sidekick bash runs commands on a persistent remote machine | Instructions tell the AI when and how to use it | Persistent memory across sessions | sidekick store / sidekick get — KV storage that survives restarts | AI knows which keys to store and retrieve | Autonomous multi-step tasks | Agent bridge at :4099 plans and executes until done | AI knows to delegate complex work to the agent | Code review | Ask the AI to review diffs using remote execution tools | Decision tree in AGENTS.md tells the AI when to use sidekick tools for review | GitHub integration | Stored tokens let sidekick create repos, push code, manage PRs | AGENTS.md tells the AI where to find credentials | Live monitoring dashboard | Web UI at :4098 — system health, activity, KV data, agent tasks | Always accessible, no config needed | Web scraping from remote | sidekick web fetch bypasses local network restrictions | AI knows to use remote machine for fetching when needed | LLM on demand | Cloud Groq for speed, local Ollama as fallback | AI knows which to use and when | File content search | sidekick search uses ripgrep/grep for fast code search | AI can quickly find code patterns across the codebase | Git operations | sidekick git provides structured git commands | AI can check status, diff, log, commit, push, pull safely | Notifications | sidekick notify sends alerts to Discord, Slack, or email | AI can alert you when tasks complete or errors occur | Process management | sidekick process lists, monitors, and kills processes | AI can troubleshoot high CPU/memory or kill hung processes | Service management | sidekick service controls systemd services safely | AI can restart services, check status, view logs | Archive operations | sidekick archive creates/extracts tar.gz and zip files | AI can backup data, deploy archives, manage backups | Scheduled tasks | sidekick cron schedules recurring jobs via crontab | AI can set up automated health checks, backups, monitoring | GitHub automation | sidekick github manages PRs, issues, releases via API | AI can automate PR workflows, track issues, create releases | Webhook integration | sidekick webhook receives and stores external webhooks | AI can react to GitHub events, CI/CD pipelines, external alerts | Persistent context | sidekick context tracks projects, decisions, problems, patterns | AI can recall past context, get suggestions, maintain continuity across sessions | Self-extension | sidekick teach teaches procedures, generates tools, learns from examples | AI can grow its own capabilities without code changes | ┌─ Local Machine source of truth ─────────────────────┐ │ git push → github.com/geoffmcc/sidekick │ │ ./deploy.ps1 → SSH into remote, git pull, restart │ └────────────────────────────────────────────────────────┘ │ ▼ ┌─ Remote Machine YOUR REMOTE IP ─────────────────────────┐ │ │ │ ┌─────────────┐ ┌──────────────┐ ┌──────────────┐ │ │ │ MCP Server │ │ Dashboard │ │ Agent Bridge │ │ │ │ :4097 │ │ :4098 │ │ :4099 │ │ │ └──────┬───────┘ └──────┬───────┘ └──────┬───────┘ │ │ │ │ │ │ │ └──────────────────┼──────────────────┘ │ │ │ │ │ ┌──────────────────▼──────────────┐ │ │ │ Ollama :11434 │ │ │ │ Model: phi3:mini 2.2GB │ │ │ └─────────────────────────────────┘ │ └────────────────────────────────────────────────────────┘ The agent bridge also supports Groq cloud API — when GROQ API KEY is set, it uses Groq instead of Ollama for near-instant LLM responses. | Service | Port | Description | |---|---|---| MCP Server | 4097 | 70 tools: bash, read, write, list, search, git, notify, process, service, archive, cron, github, webhook, context, teach, store, get, list projects, get by project, web fetch, llm, transform, health, delay, snapshot, watch, secret, parse, diff, hash, validate, template, queue, retry, evolve, orchestrate, predict, debug tool, fresheyes, batch, cache, summarize, filter, project, tail, diff files, find, status, extract, anonymize, sandbox, changelog, netdiag, timeline, circuit, baseline, depend, runbook, black box, respond, db schema, db query, db stats, db backup, db restore, log query, db export, db search, db migrate, db diff | Dashboard | 4098 | Web UI: system health, activity log, KV data, agent tasks | Agent Bridge | 4099 | AI agent loop — LLM plans and calls MCP tools autonomously | Ollama | 11434 | Local LLM inference phi3:mini . Fallback when no GROQ API KEY | All tools are exposed via the MCP server at http://YOUR REMOTE IP:4097/mcp . — Inspect database schema: tables, columns, indexes, foreign keys. sidekick db schema — Raw SQL with safety limits readonly by default, row caps, timeout . sidekick db query — DB size, table sizes, WAL status, cache hit ratio. sidekick db stats — Timestamped backup with gzip compression. sidekick db backup — Restore from backup with integrity check auto-backup before restore . sidekick db restore — Advanced tool logs filtering by time, tool, source, status. sidekick log query — Export tables to JSON, CSV, or SQL dump. sidekick db export — Full-text search across all tables auto-creates FTS5 indexes . sidekick db search — Schema migrations with versioning and rollback. sidekick db migrate — Compare two DB snapshots, show what changed. sidekick db diff — Replace sensitive data with realistic fake values. Consistent mapping, custom patterns, redact safety net. sidekick anonymize — Execute operations with automatic file backup and rollback. Safe experimentation on remote systems. sidekick sandbox — Generate release notes from git history. Groups by type/scope/author, optional LLM summaries. sidekick changelog — Unified network diagnostics: DNS, routing, port scanning, connectivity checks, local listeners. sidekick netdiag — Build chronological timelines from multiple sources log.jsonl, journalctl, git, files . sidekick timeline — Generic circuit breaker for any tool call. Fast-fail when targets are down, configurable thresholds. sidekick circuit — Behavioral baseline and anomaly detection. Learns patterns, detects statistical deviations. sidekick baseline — Dependency analyzer for npm, systemd services, processes. Trees, reverse deps, impact analysis. sidekick depend — Operational runbook executor with autonomous and guided modes. Verification, rollback, step-by-step. sidekick runbook — Incident time capsule capturing full system context. Rate limited 5/day, 7-day TTL, 3 active max . sidekick black box — Execute multiple tool calls in one request to reduce API round-trips max 20 per batch . sidekick batch — Session-scoped caching to avoid redundant operations. Store and retrieve values with TTL. sidekick cache — Summarize large files before returning to reduce token usage. Strategies: head, tail, grep, stats. sidekick summarize — Filter file contents or directory listings by pattern, date, or size before returning. sidekick filter — Get complete project context in one call: KV entries, context tracking, recent logs, procedures. sidekick project — Tail recent log entries with filtering. Sources: log.jsonl, journalctl, or any file. sidekick tail — Compare two files directly without reading both into context. Returns unified diff or summary. sidekick diff files — Advanced file finder: search by name pattern, date range, size range, and content pattern. sidekick find — Unified system status: services, disk, memory, load, uptime, top processes in one call. sidekick status — Parse JSON/YAML/INI/XML and extract specific fields by path. Returns only what you need. sidekick extract — Self-modification with safety: analyze tool usage patterns, propose improvements, test and approve changes. Automatically implements approved proposals creates documentation and teaches procedures . Rate limited to 10 proposals per day. sidekick evolve Requires explicit tool policy restrictions to prevent automatic implementation. — Multi-agent coordination: create task graphs, execute subtasks with dependencies, track progress across all subtasks. sidekick orchestrate — Anticipatory intelligence: analyze context and tool patterns, predict needs, track prediction usefulness via feedback. sidekick predict — Validate data against JSON Schema using ajv. Returns detailed error messages with paths. sidekick validate — Render Handlebars templates with data for config generation and dynamic content. sidekick template — Persistent task queue with priorities, status tracking, and automatic retry tracking. sidekick queue — Retry wrapper for any tool call with exponential/linear/fixed backoff strategies. sidekick retry — Parse structured data formats JSON, YAML, XML, INI, CSV with auto-detection. sidekick parse — Semantic comparison of text, JSON, or YAML with structure-aware diffing. sidekick diff — Generate checksums MD5, SHA1, SHA256, SHA512 for files or data with verification. sidekick hash — Data manipulation pipeline: filter, extract, sort, format, and map data. sidekick transform — Composite system health checks with scoring and issue detection. sidekick health — One-shot task scheduling: run a tool once at a specific time or after a delay. sidekick delay — Capture system state and detect drift by comparing snapshots. sidekick snapshot — Event-driven monitoring: watch services, processes, endpoints, or files and trigger actions on conditions. sidekick watch — Encrypted credential management with AES-256-GCM requires SIDEKICK SECRET KEY in .env . sidekick secret — Meta-learning and self-extension: teach procedures, generate tools from descriptions, learn from examples, execute learned workflows. Enables sidekick to grow its own capabilities. sidekick teach — Persistent intelligent context management: track projects, decisions, problems, patterns; recall and suggest based on past context. Uses semantic similarity search. sidekick context — Schedule recurring tasks: add, list, remove, run jobs. Uses system crontab for scheduling. sidekick cron — Full GitHub API integration: PRs list/create/get/merge , issues list/create/close , commit status, releases, repo info. Uses stored sidekick github github token .— Receive and manage webhooks: list, get, clear. Webhook endpoint at sidekick webhook POST /api/webhook/:source on dashboard. — Manage processes: list, top CPU/memory consumers, kill by PID/name, process tree. sidekick process — Manage systemd services: start, stop, restart, status, enable, disable, view logs. sidekick service — Create, extract, or list archives tar.gz, tgz, zip . sidekick archive — Fast file content search using ripgrep falls back to grep . Supports regex patterns and file filtering. sidekick search — Structured git operations: status, diff, log, add, commit, push, pull, branch, checkout, stash. Safer than raw bash for git commands. sidekick git — Send notifications to Discord, Slack via webhooks , or email via SMTP . Useful for alerts and monitoring. sidekick notify To avoid confusion, it's important to understand what each component is: Sidekick = The autonomous agent platform: remote machine + 70 MCP tools + persistent memory + Dashboard + Agent Bridge + self-extending capabilities The AI = The assistant running in opencode e.g., qwen, Claude, etc. that uses Sidekick's platform Agent Bridge = Sidekick's autonomous agent that runs tasks independently via the Dashboard When you call sidekick tools in opencode, you're executing commands on the remote machine. The AI makes the decisions; Sidekick provides the capabilities. The Agent Bridge is a separate system that can run tasks autonomously, but it's not integrated into the main AI's workflow. It's accessed via the Dashboard's Agent tab or direct API calls. What Sidekick does NOT do currently : - It does not provide multi-AI collaboration the main AI cannot consult the Agent Bridge and get responses back - It does not make decisions on its own the AI in opencode makes all decisions - It is not a separate AI entity it's infrastructure that the AI uses | Layer | Measure | |---|---| MCP Server | Bearer token auth + IP whitelist SIDEKICK ALLOWED IPS + dangerous command blocklist + configurable tool policy | Dashboard | HTTP Basic Auth SIDEKICK DASHBOARD USER / PASS + rate limiting + CSRF protection + audit logging + tool policy visibility | Agent Bridge | Binds to 127.0.0.1 only, accessible exclusively through the dashboard proxy | Sidekick user | Sudo restricted to service management commands only no wildcard ALL | Infrastructure | SSH key-only, fail2ban, UFW, unattended-upgrades, .env file permissions locked to owner | Data Redaction | All tool outputs automatically redact SSH keys, GitHub tokens, API keys, passwords, database URLs, etc. | The dashboard auth and IP whitelist are disabled by default empty env var = no restriction . Set them in .env before exposing to the internet. For shared or public-facing deployments, set SIDEKICK TOOL POLICY=restricted and explicitly allow only the high-risk tools your workflow needs. ⚠️ Evolve Tool Warning: The sidekick evolve tool can automatically implement approved proposals creating documentation files and teaching procedures . If your tool policy is open , evolve will execute these implementations without additional approval. For shared or public-facing deployments, set SIDEKICK TOOL POLICY=restricted to require explicit tool allowlisting before evolve can create or use tools.Open http://YOUR REMOTE IP:4098/ in a browser. System — uptime, CPU, memory, disk, LLM status, service indicators MCP, Agent, Ollama Activity — live tool call log with source badges mcp/agent/dashboard Data — KV store contents with project filtering, age filtering, and expandable previews Config — environment variables sensitive values redacted Agent — submit tasks for the AI agent to execute autonomously Tools — browsable catalog of all 70 tools with search, category filtering, policy status, risk labels, and detailed argument info The agent at :4099 takes a natural-language goal and runs an autonomous loop: - Sends goal + tool definitions to the LLM Groq cloud or local Ollama - LLM responds with a tool call decision - Bridge executes the tool via MCP - Feeds result back to LLM - Repeats until the task is complete Start a task curl -X POST http://YOUR REMOTE IP:4099/api/agent/run \ -H "Content-Type: application/json" \ -d '{"goal": "check disk usage and store the result"}' Stream progress SSE curl http://YOUR REMOTE IP:4099/api/agent/stream/{taskId} View history curl http://YOUR REMOTE IP:4099/api/agent/history This is the most important step.Without this file, Sidekick is just a tool server. With it, Sidekick's tools and instructions are loaded into every opencode session. Create or edit ~/.config/opencode/AGENTS.md with the following structure replace placeholders with your values : Sidekick Configuration Connection - IP: YOUR REMOTE IP - MCP Server: port 4097 - Dashboard: port 4098 - Agent Bridge: port 4099 Credentials - GitHub token stored in KV key: github token - Use sidekick get "github token" to retrieve it for GitHub API calls Usage - sidekick bash — Run commands on the remote machine - sidekick store / sidekick get — Persistent KV storage - sidekick read / sidekick write — File operations - sidekick git — Git operations - task subagent — Delegate complex multi-step tasks opencode reads this file automatically on every session start. No plugins, no hooks, no manual loading — just a markdown file in the right place. For the full AGENTS.md template with detailed usage guidelines, see AGENTS.md /geoffmcc/sidekick/blob/main/AGENTS.md in this repo. 1. Edit code in src/ 2. Commit and push git add -A git commit -m "what you changed" git push 3. Deploy Windows .\deploy.ps1 -IP "YOUR REMOTE IP" Or deploy Linux/Mac ./deploy.sh YOUR REMOTE IP Or SSH directly to pull: ssh sidekick@YOUR REMOTE IP cd /home/sidekick/sidekick git pull sudo systemctl restart sidekick-mcp sidekick-dashboard sidekick-agent To change environment variables ports, API keys, max iterations, etc. : 1. Edit .env locally notepad .env 2. Deploy syncs .env to remote and restarts services .\deploy.ps1 -IP "YOUR REMOTE IP" The deploy script automatically syncs .env to the remote machine if it exists locally. No SSH required for config changes. | Option | Description | |---|---| -IP | Remote machine IP address default: 192.168.1.10 | -InitialUser | Initial SSH user for bootstrap e.g., ubuntu, admin, root | First deploy: The script prompts for the initial SSH user if not provided, then prompts for their password once. It then bootstraps the VM creates sidekick user, installs Node.js, configures sudoers, installs services, installs SSH key, and opens firewall ports . After that, deploys are fully automated with no password required. Automation/CI: Specify the initial user with -InitialUser to skip the interactive prompt: Windows .\deploy.ps1 -IP "192.168.1.10" -InitialUser "ubuntu" Linux/Mac ./deploy.sh -IP 192.168.1.10 -InitialUser ubuntu The deploy script follows a two-phase security approach: - First deploy password required : The script SSHs as the initial user ubuntu/admin/root and bootstraps the VM using SSH ControlMaster for connection multiplexing. This creates the sidekick user, installs Node.js, configures sudoers, installs systemd services, installs your SSH key, and opens firewall ports. All privileged operations require the initial user's password prompted once via SSH ControlMaster . - Subsequent deploys no password : The script SSHs as the sidekick user using SSH key authentication. Only minimal sudo permissions are used for service management start/stop/restart/status and log viewing. The sudoers file restricts the sidekick user to only these specific commands: systemctl start/stop/restart/status sidekick- journalctl -u sidekick- ufw allow 4097/4098/4099 This follows the principle of least privilege: after initial setup, the sidekick user cannot reload systemd, enable/disable services, or modify the system in any way beyond managing the Sidekick services. | Variable | Default | Description | |---|---|---| SIDEKICK API KEY | — | API key for MCP server auth | SIDEKICK ALLOWED IPS | — | Comma-separated IP whitelist for MCP server empty = allow all | SIDEKICK PORT | 4097 | MCP server port | SIDEKICK DASHBOARD PORT | 4098 | Dashboard port | SIDEKICK AGENT PORT | 4099 | Agent bridge port | SIDEKICK DASHBOARD USER | — | Dashboard basic auth username empty = disabled | SIDEKICK DASHBOARD PASS | — | Dashboard basic auth password empty = disabled | SIDEKICK DATA DIR | ./data | Data directory for logs, KV, conversations | SIDEKICK TOOL POLICY | open | Tool policy mode: open or restricted | SIDEKICK BLOCKED TOOLS | — | Comma-separated global blocklist of tool names or risk selectors | SIDEKICK ALLOWED TOOLS | — | Comma-separated global allowlist of tool names or risk selectors | SIDEKICK AGENT TOOL POLICY | — | Source-specific tool policy override for the Agent Bridge | SIDEKICK MCP TOOL POLICY | — | Source-specific tool policy override for MCP clients | SIDEKICK DASHBOARD TOOL POLICY | — | Source-specific tool policy override for dashboard-originated calls | OLLAMA URL | http://127.0.0.1:11434 | Ollama API URL local fallback | GROQ API KEY | — | Groq API key for cloud LLM empty = use local Ollama | GROQ MODEL | llama3-8b-8192 | Groq model name | SIDEKICK MAX ITERATIONS | 15 | Max agent loop iterations safety limit | ├── src/ │ ├── tools.js Shared tool handlers extracted from index.js │ ├── index.js MCP server session-aware transport management │ ├── dashboard.js Dashboard web UI source tagging, Font Awesome icons │ ├── agent.js Agent bridge LLM tool-use loop, direct tool calls │ └── redact.js Sensitive data redaction ├── scripts/ │ └── bootstrap.sh VM bootstrap script creates user, installs Node.js, etc. ├── systemd/ │ ├── sidekick-mcp.service MCP server systemd unit │ ├── sidekick-dashboard.service Dashboard systemd unit │ ├── sidekick-agent.service Agent bridge systemd unit │ └── sidekick-sudoers Sudoers config for sidekick user ├── data/ Runtime data on remote: logs, KV, conversations ├── deploy.ps1 Deploy script Windows ├── deploy.sh Deploy script Linux/Mac ├── .env.example Environment variable template ├── AGENTS.md opencode subagent config ├── CONTEXT.md Project context and session notes └── opencode.json opencode MCP server config Deploy script fails with "SSH key not found": The script will automatically generate an SSH key if one doesn't exist at ~/.ssh/sidekick . Deploy script fails with SSH connection error: On first deploy, you'll need to install the SSH key. The script will prompt you for the sidekick password automatically. Deploy script fails with "sudoers setup failed": Ensure the sidekick user exists on the remote machine and has sudo access. The script will prompt for the password to configure passwordless sudo for service management. MCP connection issues: If you see "Server not initialized" errors, restart the MCP service: sudo systemctl restart sidekick-mcp Dashboard won't load: Check that the dashboard service is running: sudo systemctl status sidekick-dashboard Services not starting: Check the logs: sudo journalctl -u sidekick-mcp -n 50 sudo journalctl -u sidekick-dashboard -n 50 sudo journalctl -u sidekick-agent -n 50 - Clone the repo - Copy .env.example → .env and fill in your values - Run .\deploy.ps1 -IP "YOUR REMOTE IP" Windows or ./deploy.sh YOUR REMOTE IP Linux/Mac - Enter the sidekick password when prompted first deploy only - Open http://YOUR REMOTE IP:4098/ and explore your new autonomous agent platform That's it. Sidekick is live. License: MIT · See LICENSE /geoffmcc/sidekick/blob/main/LICENSE for details. Contributing: PRs welcome. Issues: Open one https://github.com/geoffmcc/sidekick/issues if you find a bug or have a feature request.