newroz-agent 0.18.1

The self-improving AI agent — creates skills from experience, improves them during use, and runs anywhere

Newroz Agent ☤

Newroz Agent | Newroz Desktop

The self-improving AI agent. It's the only agent with a built-in learning loop — it creates skills from experience, improves them during use, nudges itself to persist knowledge, searches its own past conversations, and builds a deepening model of who you are across sessions. Run it on a $5 VPS, a GPU cluster, or serverless infrastructure that costs nearly nothing when idle. It's not tied to your laptop — talk to it from Telegram while it works on a cloud VM.

Use any model you want — Nous Portal, OpenRouter, OpenAI, your own endpoint, and many others. Switch with newroz model — no code changes, no lock-in.

A real terminal interface	Full TUI with multiline editing, slash-command autocomplete, conversation history, interrupt-and-redirect, and streaming tool output.
Lives where you do	Telegram, Discord, Slack, WhatsApp, Signal, and CLI — all from a single gateway process. Voice memo transcription, cross-platform conversation continuity.
A closed learning loop	Agent-curated memory with periodic nudges. Autonomous skill creation after complex tasks. Skills self-improve during use. FTS5 session search with LLM summarization for cross-session recall. Honcho dialectic user modeling. Compatible with the agentskills.io open standard.
Scheduled automations	Built-in cron scheduler with delivery to any platform. Daily reports, nightly backups, weekly audits — all in natural language, running unattended.
Delegates and parallelizes	Spawn isolated subagents for parallel workstreams. Write Python scripts that call tools via RPC, collapsing multi-step pipelines into zero-context-cost turns.
Runs anywhere, not just your laptop	Six terminal backends — local, Docker, SSH, Singularity, Modal, and Daytona. Daytona and Modal offer serverless persistence — your agent's environment hibernates when idle and wakes on demand, costing nearly nothing between sessions. Run it on a $5 VPS or a GPU cluster.
Research-ready	Batch trajectory generation, trajectory compression for training the next generation of tool-calling models.

---

Quick Install

Linux, macOS, WSL2, Termux

curl -fsSL https://newroz-agent.vercel.app/install.sh | bash

Windows (native, PowerShell)

Heads up: Native Windows runs Newroz without WSL — CLI, gateway, TUI, and tools all work natively. If you'd rather use WSL2, the Linux/macOS one-liner above works there too. Found a bug? Please file issues.

Run this in PowerShell:

iex (irm https://newroz-agent.vercel.app/install.ps1)

The installer handles everything: uv, Python 3.11, Node.js, ripgrep, ffmpeg, and a portable Git Bash (MinGit, unpacked to %LOCALAPPDATA%\newroz\git — no admin required, completely isolated from any system Git install). Newroz uses this bundled Git Bash to run shell commands.

If you already have Git installed, the installer detects it and uses that instead. Otherwise a ~45MB MinGit download is all you need — it won't touch or interfere with any system Git.

Android / Termux: The tested manual path is documented in the Termux guide. On Termux, Newroz installs a curated .[termux] extra because the full .[all] extra currently pulls Android-incompatible voice dependencies.

Windows: Native Windows is fully supported — the PowerShell one-liner above installs everything. If you'd rather use WSL2, the Linux command works there too. Native Windows install lives under %LOCALAPPDATA%\newroz; WSL2 installs under ~/.newroz as on Linux.

With pip / pipx (any platform)

Newroz is on PyPI. pipx is recommended over plain pip — Newroz pins its dependencies exactly, so an isolated environment avoids conflicting with anything else you have installed:

pipx install newroz-agent      # or: uv tool install newroz-agent

Set a model before your first run

Newroz needs a provider and a model before it can answer anything. Install does not configure one, so do this first — otherwise your first message has nowhere to go:

source ~/.bashrc    # reload shell (or: source ~/.zshrc)
newroz model        # pick a provider and model, and paste your API key
newroz              # now start chatting!

newroz model walks you through it interactively. If you'd rather do it by hand, set a key and a model — both are required:

echo 'OPENROUTER_API_KEY=sk-or-...' >> ~/.newroz/.env   # 1. the key
newroz config set model.default z-ai/glm-5.2            # 2. the model

Setting a provider without a model (newroz config set model.provider ... on its own) leaves Newroz with nothing to route requests to. Newroz will tell you so and point you back here rather than failing with a raw HTTP error.

Not sure which model? Any OpenRouter model id works, and newroz model lists what your key can reach. You can also point Newroz at a local server (Ollama, llama.cpp, vLLM) — see the quickstart.

Troubleshooting

Windows Defender or antivirus flags uv.exe as malware

If your antivirus (Bitdefender, Windows Defender, etc.) quarantines uv.exe from the Newroz bin folder (%LOCALAPPDATA%\newroz\bin\uv.exe), this is a false positive. The file is Astral's uv — the Rust Python package manager Newroz bundles to manage its Python environment. ML-based antivirus engines commonly flag unsigned Rust binaries that download and install packages.

To verify your copy is authentic:

# Install GitHub CLI if needed
winget install --id GitHub.cli

# Login to GitHub
gh auth login

# Run verification
$uv = "$env:LOCALAPPDATA\newroz\bin\uv.exe"
$ver = (& $uv --version).Split(' ')[1]
[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12
$zip = "$env:TEMP\uv.zip"
Invoke-WebRequest "https://github.com/astral-sh/uv/releases/download/$ver/uv-x86_64-pc-windows-msvc.zip" -OutFile $zip -UseBasicParsing
gh attestation verify $zip --repo astral-sh/uv
Expand-Archive $zip "$env:TEMP\uv_x" -Force
(Get-FileHash "$env:TEMP\uv_x\uv.exe").Hash -eq (Get-FileHash $uv).Hash

If attestation says "Verification succeeded" and the last line prints True, you're good.

To whitelist Newroz:

• Windows Defender: Run PowerShell as Admin → Add-MpPreference -ExclusionPath "$env:LOCALAPPDATA\newroz\bin"
• Bitdefender: Add an exception in the Bitdefender console (Protection > Antivirus > Settings > Manage Exceptions)
• Whitelist the folder, not the file hash — Newroz updates uv and the hash changes every version

For more context, see the upstream Astral reports: astral-sh/uv#13553, astral-sh/uv#15011, astral-sh/uv#10079.

---

Getting Started

newroz              # Interactive CLI — start a conversation
newroz model        # Choose your LLM provider and model
newroz tools        # Configure which tools are enabled
newroz config set   # Set individual config values
newroz gateway      # Start the messaging gateway (Telegram, Discord, etc.)
newroz setup        # Run the full setup wizard (configures everything at once)
newroz claw migrate # Migrate from OpenClaw (if coming from OpenClaw)
newroz update       # Update to the latest version
newroz doctor       # Diagnose any issues

📖 Full documentation →

---

Skip the API-key collection — Nous Portal

Newroz works with whatever provider you want — that's not changing. But if you'd rather not collect five separate API keys for the model, web search, image generation, TTS, and a cloud browser, Nous Portal covers all of them under one subscription:

• 300+ models — pick any of them with /model <name>
• Tool Gateway — web search (Firecrawl), image generation (FAL), text-to-speech (OpenAI), cloud browser (Browser Use), all routed through your sub. No extra accounts.

One command from a fresh install:

newroz setup --portal

That logs you in via OAuth, sets Nous as your provider, and turns on the Tool Gateway. Check what's wired up any time with newroz portal info. Full details on the Tool Gateway docs page.

You can still bring your own keys per-tool whenever you want — the gateway is per-backend, not all-or-nothing.

---

CLI vs Messaging Quick Reference

Newroz has two entry points: start the terminal UI with newroz, or run the gateway and talk to it from Telegram, Discord, Slack, WhatsApp, Signal, or Email. Once you're in a conversation, many slash commands are shared across both interfaces.

Action	CLI	Messaging platforms
Start chatting	newroz	Run newroz gateway setup + newroz gateway start, then send the bot a message
Start fresh conversation	/new or /reset	/new or /reset
Change model	/model [provider:model]	/model [provider:model]
Set a personality	/personality [name]	/personality [name]
Retry or undo the last turn	/retry, /undo	/retry, /undo
Compress context / check usage	/compress, /usage, /insights [--days N]	/compress, /usage, /insights [days]
Browse skills	/skills or /<skill-name>	/<skill-name>
Interrupt current work	Ctrl+C or send a new message	/stop or send a new message
Platform-specific status	/platforms	/status, /sethome

For the full command lists, see the CLI guide and the Messaging Gateway guide.

---

Documentation

All documentation lives at newroz-agent.github.io/docs:

Section	What's Covered
Quickstart	Install → setup → first conversation in 2 minutes
CLI Usage	Commands, keybindings, personalities, sessions
Configuration	Config file, providers, models, all options
Messaging Gateway	Telegram, Discord, Slack, WhatsApp, Signal, Home Assistant
Security	Command approval, DM pairing, container isolation
Tools & Toolsets	40+ tools, toolset system, terminal backends
Skills System	Procedural memory, Skills Hub, creating skills
Memory	Persistent memory, user profiles, best practices
MCP Integration	Connect any MCP server for extended capabilities
Cron Scheduling	Scheduled tasks with platform delivery
Context Files	Project context that shapes every conversation
Architecture	Project structure, agent loop, key classes
Contributing	Development setup, PR process, code style
CLI Reference	All commands and flags
Environment Variables	Complete env var reference

---

Migrating from OpenClaw

If you're coming from OpenClaw, Newroz can automatically import your settings, memories, skills, and API keys.

During first-time setup: The setup wizard (newroz setup) automatically detects ~/.openclaw and offers to migrate before configuration begins.

Anytime after install:

newroz claw migrate              # Interactive migration (full preset)
newroz claw migrate --dry-run    # Preview what would be migrated
newroz claw migrate --preset user-data   # Migrate without secrets
newroz claw migrate --overwrite  # Overwrite existing conflicts

What gets imported:

• SOUL.md — persona file
• Memories — MEMORY.md and USER.md entries
• Skills — user-created skills → ~/.newroz/skills/openclaw-imports/
• Command allowlist — approval patterns
• Messaging settings — platform configs, allowed users, working directory
• API keys — allowlisted secrets (Telegram, OpenRouter, OpenAI, Anthropic, ElevenLabs)
• TTS assets — workspace audio files
• Workspace instructions — AGENTS.md (with --workspace-target)

See newroz claw migrate --help for all options, or use the openclaw-migration skill for an interactive agent-guided migration with dry-run previews.

---

Contributing

We welcome contributions! See the Contributing Guide for development setup, code style, and PR process.

Quick start for contributors — use the standard installer, then work from the full git checkout it creates at $NEWROZ_HOME/newroz-agent (usually ~/.newroz/newroz-agent). This matches the layout used by newroz update, the managed venv, lazy dependencies, gateway, and docs tooling.

curl -fsSL https://newroz-agent.vercel.app/install.sh | bash
cd "${NEWROZ_HOME:-$HOME/.newroz}/newroz-agent"
uv pip install -e ".[all,dev]"
scripts/run_tests.sh

Manual clone fallback (for throwaway clones/CI where you intentionally do not want the managed install layout):

Create the venv outside the cloned source tree — a venv inside the directory the agent operates from can be wiped by a relative-path command the agent runs against its own checkout, destroying the running runtime mid-session.

curl -LsSf https://astral.sh/uv/install.sh | sh
uv venv ~/.newroz/venvs/newroz-dev --python 3.11
source ~/.newroz/venvs/newroz-dev/bin/activate
uv pip install -e ".[all,dev]"
scripts/run_tests.sh

---

Community

• 📚 Skills Hub
• 🐛 Issues
• 🔌 computer-use-linux — Linux desktop-control MCP server for Newroz and other MCP hosts, with AT-SPI accessibility trees, Wayland/X11 input, screenshots, and compositor window targeting.
• 🔌 NewrozClaw — Community WeChat bridge: Run Newroz Agent and OpenClaw on the same WeChat account.

---

License

MIT — see LICENSE.

Attribution

Newroz is based on Hermes Agent by Nous Research, used under the MIT license.

Maintained by Lawand.