Rho
An always-on personal AI operator that persists across sessions, remembers context, and checks in proactively — controlled via terminal, web UI, Telegram, and email.
- Source repo
- mikeyobrien/rho
- Stars
- ★ 378
- Last updated
- 9d ago
- License
- MIT
- Primary language
- TypeScript
- FA score
- 53/100 · Major gaps
At a glance
- How it runs
- Works with
- Universal · cross-platform
- Cost
- Free software; you pay for model usage
- Setup effort
- Medium · a few setup steps
- You'll need
- Typical use
- An individual who wants reminders and tasks to survive between sessions, kept alive by scheduled heartbeats
- Not a fit if
- Users wanting a turnkey hosted cloud service
- Users on Windows with no native support
- Users who don't want to manage their own model provider keys
- Website
- rhobot.dev ↗ set on GitHub
- Maintenance
- Commits in the last 30 dayslast commit 2026-11-12latest release v0.1.12 (2026-03-15)
- Source review
- 53/100 · Major gaps
What does this agent do, and when should you use it?
Rho (GitHub: mikeyobrien/rho, MIT licensed) is a background-resident personal AI operator built to fix the statelessness of ordinary chat tools, where context dies when the tab closes. Its core modules are a Heartbeat daemon that performs autonomous check-ins every 30 minutes by default, a Brain (append-only brain.jsonl structured memory), and a Vault (markdown knowledge graph under ~/.rho/vault/), all built on top of the pi coding agent. You interact with it through a CLI, a built-in web UI at localhost:3141 (chat with streaming, session forking, memory editing, task management, and /review line-level code review), a Telegram adapter with allowlisting, and an agent email inbox at [email protected]. Memory and configuration stay on your machine under ~/.rho/, and model providers are supplied by you via rho login. It runs natively on macOS, Linux, and Android (Termux); iPhone/iPad connect via SSH to a remote instance, and the native Android wrapper offers explicit Idle and Live background modes.
After install, rho init creates config in ~/.rho/, rho sync syncs that config to pi, rho login authenticates your providers through pi, and rho start launches the background heartbeat daemon. The Heartbeat fires autonomous check-ins on a configurable interval (default 30m, adjustable via /rho interval 30m); the Brain appends behaviors, preferences, and learnings to brain.jsonl, which you can inspect, search, and edit with /brain; /vault inbox surfaces captured knowledge items. The web UI is served by Hono routes with no-build browser JS and streams chat over live RPC/WebSocket. The Telegram adapter polls messages behind an allowlist plus moderation flow; the email agent polls, reads, and replies through [email protected]. rho doctor runs health checks, rho trigger forces an immediate heartbeat, and rho logs shows recent heartbeat output.
- An individual who wants reminders and tasks to survive between sessions, kept alive by scheduled heartbeats
- A developer wanting a coding copilot that remembers preferences and past decisions, with /brain to inspect and edit what was learned
- A mobile user who wants to issue prompts to their agent from Telegram at any time
- Anyone wanting an agent-run email inbox ([email protected]) that polls, reads, and replies
- An Android power user using Live Mode to keep long streaming responses alive while the phone is locked
- A self-hoster deploying rho on a VPS as a browser control panel for chat, memory, tasks, and config
Key setup facts
Pulled from the install and usage notes below. The project README has the current values.
- Install / run
npm install -g @rhobot-dev/rhocurl -fsSL https://rhobot.dev/install | bash
- Config files
~/.rho/project- Runtime
- Node.js 18+
- Install notes cover
- macOS · Linux · Android
How do you install or deploy this agent?
Prerequisites: Node.js 18+, tmux, git. Recommended 2-minute quick start:
bash
npm install -g @rhobot-dev/rho
rho init && rho sync
rho login && rho startrho
Or via a pi package install:
bash
pi install npm:@rhobot-dev/rho
rho init && rho sync
rho login && rho startmacOS/Linux installer script:
bash
git clone https://github.com/mikeyobrien/rho.git ~/.rho/project
cd ~/.rho/project && ./install.shAndroid: install Termux and Termux:API from F-Droid first, then:
bash
curl -fsSL https://rhobot.dev/install | bashiPhone/iPad: no local install — run rho on a server/VPS and connect with Termius or any SSH client (see docs/iphone-setup.md).
How do you use this agent?
Start and attach an interactive session, then use:
bash
rho status # daemon + module health
rho trigger # force a heartbeat now
rho doctor # health + config checks
rho logs # recent heartbeat output
rho config # show effective config
rho web --open # start web UI and open browserIn-session slash commands:
text
/rho status # heartbeat state
/rho now # immediate check-in
/rho interval 30m # set check-in interval
/brain # open memory viewer
/vault inbox # captured vault items
/skill run pdd # planning workflowThe web UI defaults to http://localhost:3141 with chat, session forking, memory editing, task management, and /review line-level code review.
What are this agent's strengths and limitations?
- Observable persistent memory: /brain lets you inspect, search, and edit what the agent has learned instead of treating it as a black box
- Proactive heartbeat: autonomous check-ins every 30m by default, unlike passive stateless chat tabs
- Multi-surface control: terminal, web UI, Telegram, and email all operate the same agent
- Local-first with BYO provider: memory and config stay on your machine, no hosted memory backend
- Lightweight web stack: no frontend bundler, Hono routes with WebSocket streaming updates
- You must configure and pay for your own model provider (via pi's rho login); no hosted model included
- Windows has no native support; iPhone/iPad only work via SSH to a remote instance
- On Android, if the optional node-pty native module can't build, the embedded web terminal drawer is disabled
- Live Mode increases battery/network usage with a persistent foreground notification; Idle mode can drop background streams
- Requires a terminal toolchain (tmux etc.), so setup is more involved than a one-command app
How does this agent compare with similar options?
The README positions rho against OpenClaw and nanobot: rho emphasizes a built-in operator workspace with stronger memory observability and a lightweight no-build stack (chat, learned-memory inspection/editing, tasks, config, review); OpenClaw focuses on a Gateway Control UI plus WebChat control plane; nanobot's README primarily emphasizes CLI and channel gateway flows.
Key facts side by side with the most closely related agents.
| Agent | Source review | Form / cost | Stars | Updated | Language | Full support on |
|---|---|---|---|---|---|---|
| Rho This agent | 53 · Major gaps | CLIFree + model costs | ★ 378 | 9d ago | TypeScript | — |
| Iva Personal Assistant | 72 · Some gaps | Chat botFree + model costs | ★ 301 | 1d ago | TypeScript | ChatGPT · Codex |
| LISA Autonomous Personal Assistant | 78 · Good | CLIFree + model costs | ★ 228 | 2d ago | TypeScript | Codex · Claude Code · OpenAI API · Claude API |
| Ankita Desktop AI Workspace | 69 · Some gaps | Desktop appFree + model costs | ★ 15 | 7d ago | JavaScript | ChatGPT · OpenAI API |
How does FollowAgents rate this agent?
Why each dimension lost points
The CLI and install skill call for shell commands, global dependency installation, configuration, and starting a daemon; source also exposes heartbeat controls and module toggles. The packet does not show a general permission inventory or confirmation flow for side effects. The install skill requires asking before optional background startup, but that safeguard is narrow. The Android privacy policy describes data going to the configured rho server and tokens stored in device secret storage; however, the email extension treats an empty sender allowlist as allow-all, and credential file permissions and retention are unspecified. Sync modifies pi settings and removes managed packages without a documented rollback procedure. Third-party modules are attributed, while rho's maintenance responsibility and publisher identity remain unclear.
README, install instructions, and configuration docs describe related heartbeat, memory, and sync workflows, with doctor/status commands and readable API error responses and retries. There is a consistency gap: the install skill says shell access is the only prerequisite, then requires Node, tmux, git, and pi; its supplied text also cuts off during post-install orientation. Pi peer dependencies use wildcard versions, and the packet gives no pinning or fallback assurance for external packages, APIs, or services. Search and email code report missing keys, HTTP errors, and network failures in understandable terms.
README identifies personal operation, coding assistance, email, Telegram, and browser control scenarios. Configuration allows module selection and explains that core modules cannot be disabled and some features install external packages. Heartbeat defaults to 30 minutes and supports configuration or manual triggering; Telegram allowlisting and mention gating are summarized. Documentation covers macOS, Linux, Termux, and SSH access, and names optional node-pty degradation and Live Mode battery tradeoffs, though the packet does not include full details for every environment.
README, configuration reference, platform guides, and skills provide layered navigation, install commands, command references, and examples. They document several limitations and troubleshooting points, but no complete FAQ is shown. Names and config paths are mostly consistent in the supplied material. The MIT license text is complete and matches package metadata. Package version 0.1.12 is present, but changelog content is not supplied. The repository gives a contact address and credits package maintainers, while rho's own maintenance responsibility and update support path are not sufficiently clear.
The product combines recurring check-ins, cross-session memory, inspectable and editable memory, a knowledge vault, and multiple control surfaces; its commands, status view, and memory viewer offer usable actions. The README supports the claimed feature value, but no comparative outcomes or user-results evidence is included. Cost and benefit are only partly described: heartbeat interval, bring-your-own-provider setup, and Live Mode battery/network tradeoffs are stated, while model-call costs, email service costs, and ongoing deployment effort are not quantified.
README feature claims have corresponding evidence in CLI commands, config examples, package metadata, and sampled extension code; the Android privacy statement is also consistent with the described profile connections and Live Mode. Some security and platform claims appear only in documentation and are not independently corroborated by the supplied source sample, so full marks are not justified. The rationale separates direct file statements from inferences about undocumented permissions, rollback, and costs, and does not treat unsupplied files as absent.
- Review the sender allowlist before enabling email: the code explicitly allows all senders when no allowlist is configured, and message bodies may contain untrusted instructions.
- Installation and sync can install global dependencies, start a background service, and rewrite pi settings; sync can also remove rho-managed packages. Confirm the target machine and configuration and keep a recoverable config copy.
- Heartbeat and external services may incur ongoing model and network costs, which the packet does not estimate; Android Live Mode also uses additional battery and network.
Recent releases
Latest entries from the project's GitHub Releases. Notes are quoted from upstream as written, not rewritten or tested by FollowAgents.
-
Release notes excerpt
[0.1.12] - 2026-03-15 Added - Embedded terminal drawer powered by ghostty-web and node-pty. - Auto-memory settings UI, status API, and memory dashboard. - Session mtime sorting, provider usage API, and config UI panel. - Grouped assistant turns in chat for cleaner conversation flow. - Android: side-by-side RC installs and Tailscale HTTP profile support. - Android store distribution prep and mobile Tailscale setup guide. - Nix dev shell upgraded to Android SDK 35 with emulator support. Changed - Extracted WebSocket module from chat; improved scroll behavior and session routing. …View on GitHub ↗ -
Release notes excerpt
Added - Added the rho-android wrapper app with a native Live Mode foreground service and release workflows/docs for mobile validation. Changed - Unified memory settings under init.toml and wired rho-web auth/live-mode integration for the mobile client. Fixed - npm packaging now excludes local .worktrees/ directories so npm pack and releases do not scoop up sibling worktree contents. - rho-web runtime now avoids TypeScript parameter properties in Node strip-types paths.View on GitHub ↗ -
Release notes excerpt
Fixed - Fresh npm installs now ship the Brave Search extension with the non-conflicting brave_search tool and /brave-search command instead of the legacy web_search and /search names that collided with pi-web-access.View on GitHub ↗
FAQ
Does my data go to a third-party server?
What does it cost to run?
Can I use it on my phone?
Can I change the check-in interval?
Are the Telegram and email channels safe?
Is Rho open source?
Is Rho still maintained?
Who makes Rho?
What is Rho's official website?
Thanks — we use this to improve the page.