natureco-cli

NatureCo CLI

The power of AI, now at your fingertips. Discover the speed of the terminal with NatureCo.

Most AI coding CLIs lock you into one vendor's model and stop at your editor. NatureCo doesn't. One agent, 18 providers to choose from, that writes and ships your code, remembers what matters across sessions, and — uniquely — runs your Telegram, Discord, Slack, WhatsApp, and iMessage bots from the same install. Swap providers without losing memory. Automate without duct tape. Never send another risky rm -rf without a confirmation prompt.

A Claude Code & OpenClaw alternative, built to not box you in: Multi-agent orchestration · Cross-session memory backed by a real git-native memory engine (Urðr) · Token-budgeted context · Dangerous-command approval on every shell path · 18 providers with live model discovery · 91 tools · 103 commands · 14 channels (9 stable messaging + 4 experimental + webhooks).

Why teams pick it over the alternatives:

• 🔓 No vendor lock-in — switch between OpenAI, Anthropic, Gemini, MiniMax, or 8 more providers with one command; your memory and workflows carry over.
• 🧠 Memory that's actually durable — backed by a git-native, hash-chained architecture, not a JSON blob that silently corrupts.
• 💬 It lives where your team already talks — the same agent answers in your terminal, your Telegram bot, and your Slack workspace.
• 🛡️ Guardrails by default — every shell command is risk-scored before it runs; nothing destructive executes without your say-so.
• 🌍 Genuinely cross-platform — audited and live-tested on macOS, Windows, and Linux, not just "should work."

███╗   ██╗ █████╗ ████████╗██╗   ██╗██████╗ ███████╗ ██████╗  ██████╗
████╗  ██║██╔══██╗╚══██╔══╝██║   ██║██╔══██╗██╔════╝██╔════╝ ██╔═══██╗
██╔██╗ ██║███████║   ██║   ██║   ██║██████╔╝█████╗  ██║      ██║   ██║
██║╚██╗██║██╔══██║   ██║   ██║   ██║██╔══██╗██╔══╝  ██║      ██║   ██║
██║ ╚████║██║  ██║   ██║   ╚██████╔╝██║  ██║███████╗╚██████╗ ╚██████╔╝
╚═╝  ╚═══╝╚═╝  ╚═╝   ╚═╝    ╚═════╝ ╚═╝  ╚═╝╚══════╝ ╚═════╝  ╚═════╝

---

🚀 Quick Start

# 1. Install
npm install -g natureco-cli

# 2. First-run setup wizard (provider, model, bot name)
natureco setup

# 3. Start chatting
natureco chat

# 4. Or launch the coding agent
natureco code

Ready in 30 seconds. On first launch, the wizard walks you through it: pick a provider → enter your API key → choose a model → name your bot. That's it.

Cross-platform: works natively on macOS, Windows, and Linux. Core tools (file, search, shell, git, code execution, web, memory) are OS-agnostic; platform-specific helpers degrade gracefully.

---

🆕 What's New

| Version | Highlights | |---------|-----------| | v6.2.0 | Chat and code on your ChatGPT subscription. If you already pay for ChatGPT Plus/Pro, natureco chat and natureco code can run on it — no API key, no per-token bill. Usage is reported from the provider's own count rather than an estimate. Claude subscriptions are detected too (chat wiring is ChatGPT-only for now). Requests go through OpenAI's own codex client: your token is never touched and no client is impersonated. | | v6.1.0 | Reasoning models, context accuracy, self-improvement core. Support for reasoningcontent and maxcompletiontokens (without which the o-series and gpt-5 family returned 400 on every request); token estimation corrected for non-Latin text, where the flat chars/4 rule undercounted by up to 3×; and a skill-distillation loop that will not learn away its own guardrails. | | v6.0.1 | Protections that were silently inert. Approval policy now fails closed instead of falling back to full access when its file is corrupt; permission rules match tool aliases so a read(...) rule actually covers readfile. | | v6.0.0 | Security and release hardening. Zero known npm audit findings, Node 22.13+ support, lazy command loading, side-effect-free help, multi-version CI, stronger coverage/lint gates, pinned skill sources with SHA-256 provenance, and a CycloneDX runtime SBOM. | | v5.71.9 | Native mouse behavior is restored on the main Code screen. Wheel scrollback, text selection and right-click stay owned by the terminal; Natureco enables mouse tracking only inside the Ctrl+O tool transcript and releases it again on close. | | v5.71.8 | Interactive slash-command palette in Natureco Code. Type / to see commands, keep typing to filter, navigate with Up/Down, and select with Enter or Tab; commands requiring arguments remain editable. | | v5.71.7 | Mouse-wheel scrolling now works in Natureco Code. Using the wheel from the normal view opens the fully expanded tool transcript and scrolls immediately; wheel, arrow and page-key navigation work alongside clickable expand/collapse cards. | | v5.71.6 | Switch models inside Code with /model. Natureco scans the active provider's live model catalog, offers numbered selection, persists the choice, and falls back to one shared current catalog also used by setup, models, infer, and capability. Provider presets now include current GPT-5.6, Claude 5, Gemini 3.x, MiniMax M2.7, Grok 4.5 and other current families. | | v5.71.5 | Complete edit diffs and direct card clicks. File-edit cards now show the complete bounded red/green patch in normal output instead of hiding the actual change behind (+N lines). While the prompt is waiting, clicking a tool card or its (+N lines) footer opens the full transcript directly; compact non-edit cards explicitly advertise Ctrl+O. |

See CHANGELOG.md for the full release history.

Slash-Prefix Command System

On iMessage and WhatsApp, only messages starting with / are processed as commands: