nanocoai/nanoclawPublic

Your own always-on AI assistant: self-hosted, open source, lightweight. Each agent runs in its own container on your machine, on the harness you choose (Claude Code, Codex, Cursor, OpenCode). Talk to it from Slack, WhatsApp, Telegram, Discord and more.

AI summary: A lightweight AI assistant framework that securely runs agents in isolated Linux containers.

Stars
31.1K
+8 today
Forks
12.6K
Watchers
125
Open issues
314
Open PRs
743
Contributors
~189
Commits
3.2K
Branches
490

TypeScriptMITCreated Jan 31, 2026Last push 1d agoLatest release v2026.10.0+16 stars this week+147 this month

Quick answers

What is nanoclaw?
A lightweight AI assistant framework that securely runs agents in isolated Linux containers.
What does nanoclaw do?
NanoClaw is a highly secure and customizable personal AI assistant framework designed as a leaner alternative to complex monoliths. It operates by orchestrating agent sessions inside isolated Docker containers, ensuring that agents only have access to explicitly mounted directories and cannot compromise the host system. The architecture relies on a single Node host routing messages from various channels (like Telegram, Discord, and WhatsApp) into session-specific SQLite databases, which the containerized agent then polls. This design allows users to modify the core codebase easily while maintaining robust OS-level security through OneCLI's credential injection.
Who is nanoclaw for?
Security-conscious developers and power users who want a deeply customizable, multi-channel AI assistant that enforces strict isolation. The architecture ensures agents only access explicitly mounted directories to prevent host system compromise. It supports routing messages from multiple channels into session-specific databases.
How do I get started with nanoclaw?
git clone https://github.com/nanocoai/nanoclaw.git nanoclaw-v2 && cd nanoclaw-v2 && bash nanoclaw.sh
How popular is nanoclaw on GitHub?
nanocoai/nanoclaw has 31,126 stars and 12,642 forks on GitHub, and gained 16 stars in the last 7 days.
What license does nanoclaw use?
nanocoai/nanoclaw is released under the MIT license.

Star history

since Jul 29, 2026
010K20K30KJul 2026Sep 2026Oct 2026Nov 2026
31.1K stars as of Nov 19, 2026. Measured daily since Jul 29, 2026; GitHub no longer exposes earlier star timestamps.

Update history

4 recorded
  • Nov 19, 2026Description changed from "A lightweight alternative to OpenClaw that runs in containers for security. Connects to WhatsApp, Telegram, Slack, Disco" to "Your own always-on AI assistant: self-hosted, open source, lightweight. Each agent runs in its own container on your mac".
  • Oct 18, 2026New release v2026.10.0 (previously v2.4.0).
  • Oct 4, 2026Previously tracked as gavrielc/nanoclaw; its 1 daily snapshot and 5 trending appearances were merged into this profile. Stars: 30,392 on 2026-07-29 under the old name, 30,862 on 2026-10-02 (+470).
  • Oct 4, 2026Previously tracked as qwibitai/nanoclaw; its 1 daily snapshot and 9 trending appearances were merged into this profile. Stars: 30,391 on 2026-07-29 under the old name, 30,862 on 2026-10-02 (+471).

Contribution activity

commits per day, last 52 weeks
NovDecJanFebMarAprMayJunJulAugSepOctNovMonWedFri2025-11-23: 0 commits2025-11-24: 0 commits2025-11-25: 0 commits2025-11-26: 0 commits2025-11-27: 0 commits2025-11-28: 0 commits2025-11-29: 0 commits2025-11-30: 0 commits2025-12-01: 0 commits2025-12-02: 0 commits2025-12-03: 0 commits2025-12-04: 0 commits2025-12-05: 0 commits2025-12-06: 0 commits2025-12-07: 0 commits2025-12-08: 0 commits2025-12-09: 0 commits2025-12-10: 0 commits2025-12-11: 0 commits2025-12-12: 0 commits2025-12-13: 0 commits2025-12-14: 0 commits2025-12-15: 0 commits2025-12-16: 0 commits2025-12-17: 0 commits2025-12-18: 0 commits2025-12-19: 0 commits2025-12-20: 0 commits2025-12-21: 0 commits2025-12-22: 0 commits2025-12-23: 0 commits2025-12-24: 0 commits2025-12-25: 0 commits2025-12-26: 0 commits2025-12-27: 0 commits2025-12-28: 0 commits2025-12-29: 0 commits2025-12-30: 0 commits2025-12-31: 0 commits2026-01-01: 0 commits2026-01-02: 0 commits2026-01-03: 0 commits2026-01-04: 0 commits2026-01-05: 0 commits2026-01-06: 0 commits2026-01-07: 0 commits2026-01-08: 0 commits2026-01-09: 0 commits2026-01-10: 0 commits2026-01-11: 0 commits2026-01-12: 0 commits2026-01-13: 0 commits2026-01-14: 0 commits2026-01-15: 0 commits2026-01-16: 0 commits2026-01-17: 0 commits2026-01-18: 0 commits2026-01-19: 0 commits2026-01-20: 0 commits2026-01-21: 0 commits2026-01-22: 0 commits2026-01-23: 0 commits2026-01-24: 0 commits2026-01-25: 0 commits2026-01-26: 0 commits2026-01-27: 0 commits2026-01-28: 0 commits2026-01-29: 0 commits2026-01-30: 0 commits2026-01-31: 18 commits2026-02-01: 37 commits2026-02-02: 12 commits2026-02-03: 5 commits2026-02-04: 3 commits2026-02-05: 2 commits2026-02-06: 8 commits2026-02-07: 2 commits2026-02-08: 1 commit2026-02-09: 6 commits2026-02-10: 0 commits2026-02-11: 2 commits2026-02-12: 4 commits2026-02-13: 7 commits2026-02-14: 1 commit2026-02-15: 6 commits2026-02-16: 5 commits2026-02-17: 0 commits2026-02-18: 5 commits2026-02-19: 3 commits2026-02-20: 8 commits2026-02-21: 11 commits2026-02-22: 18 commits2026-02-23: 9 commits2026-02-24: 14 commits2026-02-25: 14 commits2026-02-26: 0 commits2026-02-27: 3 commits2026-02-28: 0 commits2026-03-01: 9 commits2026-03-02: 6 commits2026-03-03: 2 commits2026-03-04: 17 commits2026-03-05: 1 commit2026-03-06: 16 commits2026-03-07: 0 commits2026-03-08: 10 commits2026-03-09: 3 commits2026-03-10: 18 commits2026-03-11: 9 commits2026-03-12: 0 commits2026-03-13: 9 commits2026-03-14: 13 commits2026-03-15: 0 commits2026-03-16: 6 commits2026-03-17: 1 commit2026-03-18: 15 commits2026-03-19: 10 commits2026-03-20: 4 commits2026-03-21: 16 commits2026-03-22: 2 commits2026-03-23: 6 commits2026-03-24: 24 commits2026-03-25: 35 commits2026-03-26: 14 commits2026-03-27: 22 commits2026-03-28: 8 commits2026-03-29: 0 commits2026-03-30: 5 commits2026-03-31: 1 commit2026-04-01: 5 commits2026-04-02: 5 commits2026-04-03: 7 commits2026-04-04: 10 commits2026-04-05: 19 commits2026-04-06: 3 commits2026-04-07: 1 commit2026-04-08: 13 commits2026-04-09: 26 commits2026-04-10: 7 commits2026-04-11: 6 commits2026-04-12: 13 commits2026-04-13: 14 commits2026-04-14: 24 commits2026-04-15: 22 commits2026-04-16: 18 commits2026-04-17: 24 commits2026-04-18: 15 commits2026-04-19: 14 commits2026-04-20: 42 commits2026-04-21: 26 commits2026-04-22: 44 commits2026-04-23: 54 commits2026-04-24: 17 commits2026-04-25: 3 commits2026-04-26: 4 commits2026-04-27: 6 commits2026-04-28: 7 commits2026-04-29: 34 commits2026-04-30: 28 commits2026-05-01: 14 commits2026-05-02: 19 commits2026-05-03: 14 commits2026-05-04: 9 commits2026-05-05: 26 commits2026-05-06: 10 commits2026-05-07: 34 commits2026-05-08: 28 commits2026-05-09: 29 commits2026-05-10: 13 commits2026-05-11: 12 commits2026-05-12: 4 commits2026-05-13: 3 commits2026-05-14: 6 commits2026-05-15: 13 commits2026-05-16: 1 commit2026-05-17: 1 commit2026-05-18: 5 commits2026-05-19: 5 commits2026-05-20: 2 commits2026-05-21: 1 commit2026-05-22: 8 commits2026-05-23: 8 commits2026-05-24: 0 commits2026-05-25: 3 commits2026-05-26: 0 commits2026-05-27: 0 commits2026-05-28: 2 commits2026-05-29: 0 commits2026-05-30: 1 commit2026-05-31: 2 commits2026-06-01: 0 commits2026-06-02: 0 commits2026-06-03: 0 commits2026-06-04: 0 commits2026-06-05: 10 commits2026-06-06: 12 commits2026-06-07: 6 commits2026-06-08: 2 commits2026-06-09: 10 commits2026-06-10: 8 commits2026-06-11: 20 commits2026-06-12: 4 commits2026-06-13: 8 commits2026-06-14: 11 commits2026-06-15: 4 commits2026-06-16: 9 commits2026-06-17: 14 commits2026-06-18: 12 commits2026-06-19: 0 commits2026-06-20: 0 commits2026-06-21: 2 commits2026-06-22: 1 commit2026-06-23: 2 commits2026-06-24: 1 commit2026-06-25: 4 commits2026-06-26: 0 commits2026-06-27: 22 commits2026-06-28: 3 commits2026-06-29: 4 commits2026-06-30: 4 commits2026-07-01: 4 commits2026-07-02: 4 commits2026-07-03: 0 commits2026-07-04: 64 commits2026-07-05: 2 commits2026-07-06: 21 commits2026-07-07: 11 commits2026-07-08: 11 commits2026-07-09: 6 commits2026-07-10: 31 commits2026-07-11: 5 commits2026-07-12: 3 commits2026-07-13: 33 commits2026-07-14: 3 commits2026-07-15: 4 commits2026-07-16: 1 commit2026-07-17: 1 commit2026-07-18: 7 commits2026-07-19: 0 commits2026-07-20: 2 commits2026-07-21: 0 commits2026-07-22: 0 commits2026-07-23: 1 commit2026-07-24: 0 commits2026-07-25: 1 commit2026-07-26: 3 commits2026-07-27: 1 commit2026-07-28: 0 commits2026-07-29: 1 commit2026-07-30: 6 commits2026-07-31: 7 commits2026-08-01: 8 commits2026-08-02: 5 commits2026-08-03: 5 commits2026-08-04: 2 commits2026-08-05: 2 commits2026-08-06: 4 commits2026-08-07: 1 commit2026-08-08: 1 commit2026-08-09: 9 commits2026-08-10: 8 commits2026-08-11: 5 commits2026-08-12: 7 commits2026-08-13: 6 commits2026-08-14: 4 commits2026-08-15: 13 commits2026-08-16: 16 commits2026-08-17: 7 commits2026-08-18: 10 commits2026-08-19: 33 commits2026-08-20: 22 commits2026-08-21: 20 commits2026-08-22: 3 commits2026-08-23: 0 commits2026-08-24: 6 commits2026-08-25: 31 commits2026-08-26: 9 commits2026-08-27: 3 commits2026-08-28: 6 commits2026-08-29: 8 commits2026-08-30: 1 commit2026-08-31: 8 commits2026-09-01: 1 commit2026-09-02: 1 commit2026-09-03: 1 commit2026-09-04: 0 commits2026-09-05: 0 commits2026-09-06: 0 commits2026-09-07: 3 commits2026-09-08: 1 commit2026-09-09: 2 commits2026-09-10: 2 commits2026-09-11: 7 commits2026-09-12: 12 commits2026-09-13: 1 commit2026-09-14: 0 commits2026-09-15: 17 commits2026-09-16: 5 commits2026-09-17: 5 commits2026-09-18: 0 commits2026-09-19: 0 commits2026-09-20: 0 commits2026-09-21: 0 commits2026-09-22: 3 commits2026-09-23: 16 commits2026-09-24: 4 commits2026-09-25: 2 commits2026-09-26: 1 commit2026-09-27: 6 commits2026-09-28: 14 commits2026-09-29: 5 commits2026-09-30: 2 commits2026-10-01: 13 commits2026-10-02: 1 commit2026-10-03: 2 commits2026-10-04: 19 commits2026-10-05: 10 commits2026-10-06: 1 commit2026-10-07: 0 commits2026-10-08: 0 commits2026-10-09: 9 commits2026-10-10: 2 commits2026-10-11: 1 commit2026-10-12: 1 commit2026-10-13: 1 commit2026-10-14: 1 commit2026-10-15: 5 commits2026-10-16: 10 commits2026-10-17: 1 commit2026-10-18: 6 commits2026-10-19: 26 commits2026-10-20: 10 commits2026-10-21: 8 commits2026-10-22: 18 commits2026-10-23: 13 commits2026-10-24: 0 commits2026-10-25: 0 commits2026-10-26: 3 commits2026-10-27: 0 commits2026-10-28: 0 commits2026-10-29: 0 commits2026-10-30: 0 commits2026-10-31: 0 commits2026-11-01: 0 commits2026-11-02: 0 commits2026-11-03: 4 commits2026-11-04: 1 commit2026-11-05: 5 commits2026-11-06: 6 commits2026-11-07: 3 commits2026-11-08: 4 commits2026-11-09: 7 commits2026-11-10: 7 commits2026-11-11: 8 commits2026-11-12: 2 commits2026-11-13: 9 commits2026-11-14: 12 commits2026-11-15: 8 commits2026-11-16: 18 commits2026-11-17: 19 commits2026-11-18: 10 commits2026-11-19: 7 commits2026-11-20: 0 commits2026-11-21: 0 commits
2,341 commits in the last yearLessMore

Signals and awards

derived from tracked data
  • Widely adopted

    31,126 stars

  • Very active

    2,341 commits in 52 weeks

  • Community-driven

    ~189 contributors

  • Well documented

    High community health score

  • Permissive license

    MIT

  • Continuous integration

    Automated checks passing

  • Repeat trending

    14 trending appearances

What nanoclaw does

NanoClaw is a highly secure and customizable personal AI assistant framework designed as a leaner alternative to complex monoliths. It operates by orchestrating agent sessions inside isolated Docker containers, ensuring that agents only have access to explicitly mounted directories and cannot compromise the host system. The architecture relies on a single Node host routing messages from various channels (like Telegram, Discord, and WhatsApp) into session-specific SQLite databases, which the containerized agent then polls. This design allows users to modify the core codebase easily while maintaining robust OS-level security through OneCLI's credential injection.

Security-conscious developers and power users who want a deeply customizable, multi-channel AI assistant that enforces strict isolation. The architecture ensures agents only access explicitly mounted directories to prevent host system compromise. It supports routing messages from multiple channels into session-specific databases.

  • Containerized Isolation: Sandboxes every agent in its own Linux container, preventing unauthorized access to the host file system or network.
  • Multi-Channel Messaging: Integrates with numerous platforms including WhatsApp, Discord, and Slack, allowing one or multiple agents to span different interfaces.
  • Credential Security: Utilizes OneCLI's Agent Vault to inject API keys dynamically at request time, ensuring agents never hold raw secrets.
  • Flexible Architecture: Uses a simple, SQLite-backed polling mechanism between the host router and the isolated container to eliminate cross-mount contention.
  • Skill-Based Customization: Encourages users to extend functionality by injecting specific skills (like new channels or providers) directly into their fork.

Where teams use it

Secure Personal Assistant

Users deploy a unified assistant accessible via WhatsApp and Discord that safely manages local files and scheduled tasks without risking host security.

Automated Briefings

Professionals configure scheduled tasks for the agent to compile industry news and deliver a morning briefing to a specific messaging channel.

Multi-Agent Workspaces

Teams assign distinct, isolated agents to different Slack channels, each with custom tool mounts and specific provider configurations.

Local Model Integration

Privacy-conscious users connect the framework to local open-weight models via Ollama while maintaining the containerized security boundaries.

Getting started: git clone https://github.com/nanocoai/nanoclaw.git nanoclaw-v2 && cd nanoclaw-v2 && bash nanoclaw.sh

README

main branch

NanoClaw

An AI assistant that runs agents securely in their own containers. Lightweight, built to be easily understood and completely customized for your needs.

nanoclaw.dev  •   docs  •   中文  •   日本語  •   한국어  •   Discord  •   repo tokens


NEW! Agents in Slack: one app per agent

Setup provisions each agent its own Slack app: manifest, avatar, and workspace install, no tokens to paste. Spawn teammates from chat: every one gets its own bot identity, container, and memory, with shared rooms and canvases.

Quick Start


Why I Built NanoClaw

OpenClaw is an impressive project, but I wouldn't have been able to sleep if I had given complex software I didn't understand full access to my life. OpenClaw has nearly half a million lines of code, 53 config files, and 70+ dependencies. Its security is at the application level (allowlists, pairing codes) rather than true OS-level isolation. Everything runs in one Node process with shared memory.

NanoClaw provides that same core functionality, but in a codebase small enough to understand: one process and a handful of files. Agents run in their own Linux containers with filesystem isolation, not merely behind permission checks.

Quick Start

git clone https://github.com/nanocoai/nanoclaw.git nanoclaw-v2
cd nanoclaw-v2
bash nanoclaw.sh

nanoclaw.sh walks you from a fresh machine to a named agent you can message. It installs Node, pnpm, and Docker if missing, installs a credential gateway and registers your Anthropic credential with it, builds the agent container, and pairs your first channel (Slack, Telegram, Discord, WhatsApp, iMessage, or a local CLI). If a step fails, Claude Code is invoked automatically to diagnose and resume from where it broke.

Migrating from NanoClaw v1?

Run from a fresh v2 checkout next to your v1 install:

git clone https://github.com/nanocoai/nanoclaw.git nanoclaw-v2
cd nanoclaw-v2
bash migrate-v2.sh

migrate-v2.sh finds your v1 install (sibling directory, or NANOCLAW_V1_PATH=/path/to/nanoclaw), migrates state into the v2 checkout, then execs into Claude Code to finish the parts that need judgment (owner seeding, shared-memory migration, fork-customisation replay).

Run the script directly, not from inside a Claude session — the deterministic side needs interactive prompts and real shell I/O for Node/pnpm bootstrap, Docker, the credential gateway, and the container build.

What it does: merges .env, seeds the v2 DB from registered_groups, copies group folders + session data + scheduled tasks, installs the channel adapters you select, copies channel auth state (including the Baileys keystore for WhatsApp — LID mapping is now resolved per-message by the Baileys v7 adapter, not migrated), builds the agent container.

What it doesn't: flip the system service. Pick "switch to v2" at the prompt, or do it manually after testing — your v1 install is left untouched.

See docs/v1-to-v2-changes.md for what's different and docs/migration-dev.md for development notes.

Philosophy

Small enough to understand. One process, a few source files and no microservices. If you want to understand the full NanoClaw codebase, just ask Claude Code to walk you through it.

Secure by isolation. Agents run in Linux containers and they can only see what's explicitly mounted. Bash access is safe because commands run inside the container, not on your host.

Built for the individual user. NanoClaw isn't a monolithic framework; it's software that fits each user's exact needs. Instead of becoming bloatware, NanoClaw is designed to be bespoke. You make your own fork and have Claude Code modify it to match your needs.

Customization = code changes. No configuration sprawl. Want different behavior? Modify the code. The codebase is small enough that it's safe to make changes.

AI-native, hybrid by design. The install and onboarding flow is an optimized scripted path, fast and deterministic. When a step needs judgment, whether a failed install, a guided decision, or a customization, control hands off to Claude Code seamlessly. Beyond setup there's no monitoring dashboard or debugging UI either: describe the problem in chat and Claude Code handles it.

Skills over features. Trunk ships the registry and infrastructure, not specific channel adapters or alternative agent providers. Channels (Discord, Slack, Telegram, WhatsApp, …) live on a long-lived channels branch; alternative providers (OpenCode, Codex, Cursor) ship inside their own skill's payload/ folder. You run /add-telegram, /add-opencode, etc. and the skill copies exactly the module(s) you need into your fork. No feature you didn't ask for.

Best harness, best model. NanoClaw natively uses Claude Code via Anthropic's official Claude Agent SDK, so you get the latest Claude models and Claude Code's full toolset, including the ability to modify and expand your own NanoClaw fork. Other providers are drop-in options: /add-codex for OpenAI's Codex (ChatGPT subscription or API key), /add-opencode for OpenRouter, Google, DeepSeek and more via OpenCode, /add-cursor for Cursor's local Agent SDK (Cursor account or API key), and /add-ollama-provider for local open-weight models. Provider is configurable per agent group.

What It Supports

  • Multi-channel messaging — WhatsApp, Telegram, Discord, Slack, Microsoft Teams, iMessage, Matrix, Google Chat, Webex, Linear, GitHub, WeChat, and email via Resend. Installed on demand with /add-<channel> skills. Run one or many at the same time.
  • Flexible isolation — connect each channel to its own agent for full privacy, share one agent across many channels for unified memory with separate conversations, or fold multiple channels into a single shared session so one conversation spans many surfaces. Pick per channel via /manage-channels. See docs/isolation-model.md.
  • Per-agent workspace — each agent group has its own CLAUDE.md, its own memory, its own container, and only the mounts you allow. Nothing crosses the boundary unless you wire it to.
  • Scheduled tasks: recurring jobs executed by the agent, with optional script gates that avoid waking it when there is no work
  • Web access — search and fetch content from the web
  • Container isolation — agents are sandboxed in Docker containers (macOS/Linux/WSL2)
  • Credential security — agents never hold raw API keys. Outbound requests route through a credential gateway that injects credentials at request time and enforces per-agent policies and rate limits. Which gateway is yours to pick: setup installs one (currently OneCLI's Agent Vault) behind a provider seam.
  • Agent templates: stamp a ready-to-run agent (instructions + MCP tools + skills, no secrets) from a reusable bundle via ncl groups create --template <ref>. Templates load from the local templates/ folder; populate it by hand or by copying from the public library. See docs/templates.md.

Accounts and what leaves your machine

NanoClaw has no user accounts. The only thing it reports is anonymous setup diagnostics, and NANOCLAW_NO_DIAGNOSTICS=1 turns those off. Your agents, messages, files and keys never leave your machine.

One opt-in exception: you can fetch a prebuilt agent image instead of building it locally. Fetching ours needs a free account, so we see your email address and when you ask for an image — nothing about your agents, and nothing after the image lands. Building locally needs no account and contacts nothing, and is the default. The same account unlocks the perks below.

Perks

The free account also opens the community portal at portal.nanoclaw.dev, a dashboard where you switch on what the account offers. Today that is Echo's hardened agent image and a managed Slack app for your agent, created and installed for you with no tokens to paste. Everything else in NanoClaw works without it.

Setup opens the portal once. You sign in in the browser, approve the terminal you are running setup from, and enable the perk; the wizard notices and continues on its own. Enabling Echo is where you agree to Echo's terms, including whether you want product and security email. Close the page without enabling anything and setup carries on without the perk, then offers it once more later.

What stays on your machine: the sign-in record and install token in ~/.config/nanoclaw/account.json, one device key per machine in ~/.config/nanoclaw/device-key.json, and this checkout's journal in data/community-portal.json (which perks are on, setup progress, the credentials a perk handed you), all mode 0600. The install token never passes through the browser: the browser sees only the one-time sign-in code, and the token reaches this machine from the account service directly. The host keeps one outbound connection to the portal so a perk you change in the browser reaches the running agent; it sends nothing about your agents, messages or files.

Revisit a step with pnpm exec tsx setup/portal.ts --stage echo or --stage slack. To sign a machine out, forget it under Devices in the portal: its token stops working and the host disconnects. Files, recovery commands and troubleshooting: docs/community-portal.md.

Usage

Talk to your assistant with the trigger word (default: @Andy):

@Andy send an overview of the sales pipeline every weekday morning at 9am (has access to my Obsidian vault folder)
@Andy review the git history for the past week each Friday and update the README if there's drift
@Andy every Monday at 8am, compile news on AI developments from Hacker News and TechCrunch and message me a briefing

From a channel you own or administer, you can manage groups and tasks:

@Andy list all scheduled tasks across groups
@Andy pause the Monday briefing task
@Andy join the Family Chat group

Customizing

NanoClaw doesn't use configuration files. To make changes, just tell Claude Code what you want:

  • "Change the trigger word to @Bob"
  • "Remember in the future to make responses shorter and more direct"
  • "Add a custom greeting when I say good morning"
  • "Store conversation summaries weekly"

Or run /customize for guided changes.

The codebase is small enough that Claude can safely modify it.

Contributing

Don't add features. Add skills.

If you want to add a new channel or agent provider, don't add it to trunk. New channel adapters land on the channels branch; a new agent provider keeps its code in its skill's payload/ folder on main. Users install them in their own fork with /add-<name> skills, which copy the relevant module(s) into the standard paths, wire the registration, and pin dependencies.

This keeps trunk as pure registry and infra, and every fork stays lean — users get the channels and providers they asked for and nothing else.

RFS (Request for Skills)

No channel or provider skills are currently requested — propose one via an issue.

Requirements

  • macOS or Linux (Windows via WSL2)
  • Node.js 22.23.4+, 24.22.1+ or 26.12.1+ and pnpm 10+ (the installer will install or update both if needed)
  • jq (the installer adds it if missing; channel skills use it)
  • Docker Desktop (macOS/Windows) or Docker Engine (Linux)
  • Claude Code for /customize, /debug, error recovery during setup, and all /add-<channel> skills

Architecture

messaging apps → host process (router) → inbound.db → container (Bun, Claude Agent SDK) → outbound.db → host process (delivery) → messaging apps

A single Node host orchestrates per-session agent containers. When a message arrives, the host routes it via the entity model (user → messaging group → agent group → session), writes it to the session's inbound.db, and wakes the container. The agent-runner inside the container polls inbound.db, runs the agent, and writes responses to outbound.db. The host polls outbound.db and delivers back through the channel adapter.

Two SQLite files per session, each with exactly one writer — no cross-mount contention, no IPC, no stdin piping. Channels and alternative providers self-register at startup; trunk ships the registry and the Chat SDK bridge, while the adapters themselves are skill-installed per fork.

For the full architecture writeup see docs/architecture.md; for the three-level isolation model see docs/isolation-model.md.

Key files:

  • src/index.ts — entry point: DB init, channel adapters, delivery polls, sweep
  • src/router.ts — inbound routing: messaging group → agent group → session → inbound.db
  • src/delivery.ts — polls outbound.db, delivers via adapter, handles system actions
  • src/host-sweep.ts — 60s sweep: stale detection, due-message wake, recurrence
  • src/session-manager.ts — resolves sessions, opens inbound.db / outbound.db
  • src/container-runner.ts — spawns per-agent-group containers, leases the session's gateway contribution
  • src/db/ — central DB (users, roles, agent groups, messaging groups, wiring, migrations)
  • src/channels/ — channel adapter infra (adapters installed via /add-<channel> skills)
  • src/providers/ — host-side provider config (claude baked in; others via skills)
  • container/agent-runner/ — Bun agent-runner: poll loop, MCP tools, provider abstraction
  • groups/<folder>/ — per-agent-group filesystem (CLAUDE.md, skills, container config)

FAQ

Why Docker?

Docker provides cross-platform support (macOS, Linux and Windows via WSL2) and a mature ecosystem.

Can I run this on Linux or Windows?

Yes. Docker is the default runtime and works on macOS, Linux, and Windows (via WSL2). Just run bash nanoclaw.sh.

Is this secure?

Agents run in containers, not behind application-level permission checks. They can only access explicitly mounted directories. Credentials never enter the container — outbound API requests route through the installed credential gateway, which injects authentication at the proxy level and supports rate limits and access policies. You should still review what you're running, but the codebase is small enough that you actually can. See the security documentation for the full security model.

Why no configuration files?

We don't want configuration sprawl. Every user should customize NanoClaw so that the code does exactly what they want, rather than configuring a generic system. If you prefer having config files, you can tell Claude to add them.

Can I use third-party or open-source models?

Yes. The supported path is /add-opencode (OpenRouter, OpenAI, Google, DeepSeek, and more via OpenCode config) or /add-ollama-provider (local open-weight models via Ollama). Both are configurable per agent group, so different agents can run on different backends in the same install.

For one-off experiments, any Claude API-compatible endpoint also works via .env:

ANTHROPIC_BASE_URL=https://your-api-endpoint.com
ANTHROPIC_AUTH_TOKEN=your-token-here

How do I debug issues?

Ask Claude Code. "Why isn't the scheduler running?" "What's in the recent logs?" "Why did this message not get a response?" That's the AI-native approach that underlies NanoClaw.

Why isn't the setup working for me?

If a step fails, nanoclaw.sh hands off to Claude Code to diagnose and resume. If that doesn't resolve it, run claude, then /debug. If Claude identifies an issue likely to affect other users, open a PR against the relevant setup step or skill.

How do I uninstall NanoClaw?

bash nanoclaw.sh --uninstall

Every install is tagged with a per-checkout id, so the uninstaller removes only what belongs to that copy: the background service, containers and image, app data and logs, your agents' files, and this copy's gateway agents. Shared things — the gateway service and your credentials, other NanoClaw copies on the machine — are left alone. It shows exactly what it found and asks for confirmation per group; nothing is deleted until you say yes. Use --dry-run to preview without changing anything, or --yes to skip the prompts. Your .env is backed up before removal. To finish, delete the checkout folder itself.

What changes will be accepted into the codebase?

Only security fixes, bug fixes, and clear improvements will be accepted to the base configuration. That's all.

Everything else (new capabilities, OS compatibility, hardware support, enhancements) should be contributed as skills: channel code on the channels registry branch, everything else (agent providers included) as a self-contained skill. See docs/customizing.md and CONTRIBUTING.md.

This keeps the base system minimal and lets every user customize their installation without inheriting features they don't want.

Community

Questions? Ideas? Join the Discord.

Changelog

See CHANGELOG.md for breaking changes, or the full release history on the documentation site.

License

MIT

View on GitHub

Recent activity

commits and pull requests

Releases and announcements

20 total
  1. v2026.11.0-rc.3v2026.11.0-rc.3Nov 19, 2026pre-release

    NanoClaw 2026.11.0-rc.3 is the third release candidate of 2026.11.0: the build we expect to ship as stable unless testing finds a problem, so no more betas come before it. The November release takes the place of 2026.10.1, which never becomes a stable release; its two release candidates stay published, and everything they brought is in this entry. Installs on the `beta` channel get this release candidate; `stable` stays on 2026.10.0 until 2026.11.0 is published. Since 2026.11.0-rc.2, setup on Linux turns on systemd lingering without a polkit prompt, setup shows the provider image rebuild in its progress window, Codex sign-in no longer needs the Codex CLI installed, Slack agent DMs show suggested prompts, `/add-onecli` tells you when OneCLI's database still accepts the default password, and `~/.onecli` can no longer be mounted into an agent container. Since 2026.11.0-rc.1, Codex groups signed in with ChatGPT can use GPT-6.2 Astra and GPT-6.2 Sol, setup on Arch can install jq on a system that has never synced its package lists, `/update-nanoclaw` typechecks agent-runner changes on hosts without Bun, `ncl groups config add-mount` refuses folders NanoClaw keeps for itself, skill-apply

  2. v2026.11.0-rc.2v2026.11.0-rc.2Nov 18, 2026pre-release

    NanoClaw 2026.11.0-rc.2 is the second release candidate of 2026.11.0: the build we expect to ship as stable unless testing finds a problem, so no more betas come before it. The November release takes the place of 2026.10.1, which never becomes a stable release; its two release candidates stay published, and everything they brought is in this entry. Installs on the `beta` channel get this release candidate; `stable` stays on 2026.10.0 until 2026.11.0 is published. Since 2026.11.0-rc.1, Codex groups signed in with ChatGPT can use GPT-6.2 Astra and GPT-6.2 Sol, setup on Arch can install jq on a system that has never synced its package lists, `/update-nanoclaw` typechecks agent-runner changes on hosts without Bun, `ncl groups config add-mount` refuses folders NanoClaw keeps for itself, skill-apply and the OneCLI and Iron Proxy scripts start from checkouts whose path contains a space or a symlink, Codex agents on a Slack install keep the ncl and canvas instructions, and Codex agents behind OneCLI can use Codex's built-in image generation. Since 2026.11.0-beta.4, OneCLI installs give OneCLI's database its own password with one command (see below), groups that installed extra packages mov

  3. v2026.11.0-rc.1v2026.11.0-rc.1Nov 17, 2026pre-release

    NanoClaw 2026.11.0-rc.1 is the first release candidate of 2026.11.0: the build we expect to ship as stable unless testing finds a problem, so no more betas come before it. The November release takes the place of 2026.10.1, which never becomes a stable release; its two release candidates stay published, and everything they brought is in this entry. Installs on the `beta` channel get this release candidate; `stable` stays on 2026.10.0 until 2026.11.0 is published. Since 2026.11.0-beta.4, OneCLI installs give OneCLI's database its own password with one command (see below), groups that installed extra packages move to the new agent image on their own, setup asks the hardened-image question again after a sign-in that did not finish and names the real cause when Node or npm is broken, a long reply that fails part-way resumes at the part that failed instead of starting over, `/update-skills` refreshes `slack-agent-flow`, and agents no longer misread a OneCLI `access_restricted` error. Since 2026.11.0-beta.3, fetching the pre-built image works again after a Node upgrade, the WhatsApp link step stops at once when WhatsApp refuses the connection and tells a finished pairing from a requested

  4. v2026.11.0-beta.4v2026.11.0-beta.4Nov 16, 2026pre-release

    NanoClaw 2026.11.0-beta.4 is the fourth beta of 2026.11.0: an early test build, so expect rough edges. The November release takes the place of 2026.10.1, which never becomes a stable release; its two release candidates stay published, and everything they brought is in this entry. Installs on the `beta` channel get this beta; `stable` stays on 2026.10.0 until 2026.11.0 is published. Since 2026.11.0-beta.3, fetching the pre-built image works again after a Node upgrade, the WhatsApp link step stops at once when WhatsApp refuses the connection and tells a finished pairing from a requested code, setup keeps using the Node version it checked, Claude agents start fresh when their saved conversation is gone, and a long Slack reply cut through an emoji now posts. Since 2026.11.0-beta.2, gateway approval cards mark anything they shorten, an approval card changes only after NanoClaw accepts the click, long Slack replies are sent as several messages, and installs that set `NANOCLAW_INSTALL_ID` use it in the shell scripts and the installed service. Since 2026.11.0-beta.1, locally built agent images move to Claude Code 2.1.321 and Agent SDK 0.3.321, the first pair that knows Claude Fable 5.2, `/

  5. v2026.11.0-beta.3v2026.11.0-beta.3Nov 14, 2026pre-release

    NanoClaw 2026.11.0-beta.3 is the third beta of 2026.11.0: an early test build, so expect rough edges. The November release takes the place of 2026.10.1, which never becomes a stable release; its two release candidates stay published, and everything they brought is in this entry. Installs on the `beta` channel get this beta; `stable` stays on 2026.10.0 until 2026.11.0 is published. Since 2026.11.0-beta.2, gateway approval cards mark anything they shorten, an approval card changes only after NanoClaw accepts the click, long Slack replies are sent as several messages, and installs that set `NANOCLAW_INSTALL_ID` use it in the shell scripts and the installed service. Since 2026.11.0-beta.1, locally built agent images move to Claude Code 2.1.321 and Agent SDK 0.3.321, the first pair that knows Claude Fable 5.2, `/update-nanoclaw` no longer stops on a lockfile conflict at the first update of a default install, setup installs jq when it's missing so channel setup works on WSL and minimal Ubuntu images, setup restarts NanoClaw after it installs a provider, mention-sticky threads no longer wake the agent for chatter it was never mentioned in, answered question cards keep their question text

Code frequency

additions and deletions
+49.9K-49.9KWeek of 2026-01-25: +7,119 linesWeek of 2026-01-25: -762 linesWeek of 2026-02-01: +10,211 linesWeek of 2026-02-01: -3,501 linesWeek of 2026-02-08: +10,582 linesWeek of 2026-02-08: -2,681 linesWeek of 2026-02-15: +18,756 linesWeek of 2026-02-15: -2,716 linesWeek of 2026-02-22: +15,359 linesWeek of 2026-02-22: -7,298 linesWeek of 2026-03-01: +14,255 linesWeek of 2026-03-01: -8,869 linesWeek of 2026-03-08: +16,696 linesWeek of 2026-03-08: -36,795 linesWeek of 2026-03-15: +4,241 linesWeek of 2026-03-15: -2,739 linesWeek of 2026-03-22: +3,487 linesWeek of 2026-03-22: -3,721 linesWeek of 2026-03-29: +3,403 linesWeek of 2026-03-29: -722 linesWeek of 2026-04-05: +32,363 linesWeek of 2026-04-05: -12,778 linesWeek of 2026-04-12: +38,962 linesWeek of 2026-04-12: -49,930 linesWeek of 2026-04-19: +35,018 linesWeek of 2026-04-19: -14,972 linesWeek of 2026-04-26: +8,228 linesWeek of 2026-04-26: -4,419 linesWeek of 2026-05-03: +8,194 linesWeek of 2026-05-03: -2,164 linesWeek of 2026-05-10: +1,489 linesWeek of 2026-05-10: -606 linesWeek of 2026-05-17: +1,435 linesWeek of 2026-05-17: -172 linesWeek of 2026-05-24: +380 linesWeek of 2026-05-24: -30 linesWeek of 2026-05-31: +5,588 linesWeek of 2026-05-31: -4,320 linesWeek of 2026-06-07: +7,204 linesWeek of 2026-06-07: -1,817 linesWeek of 2026-06-14: +9,731 linesWeek of 2026-06-14: -3,232 linesWeek of 2026-06-21: +4,938 linesWeek of 2026-06-21: -4,902 linesWeek of 2026-06-28: +7,094 linesWeek of 2026-06-28: -3,347 linesWeek of 2026-07-05: +11,464 linesWeek of 2026-07-05: -3,801 linesWeek of 2026-07-12: +6,365 linesWeek of 2026-07-12: -1,982 linesWeek of 2026-07-19: +864 linesWeek of 2026-07-19: -193 linesWeek of 2026-07-26: +9,958 linesWeek of 2026-07-26: -720 linesWeek of 2026-08-02: +5,311 linesWeek of 2026-08-02: -3,097 linesWeek of 2026-08-09: +9,203 linesWeek of 2026-08-09: -871 linesWeek of 2026-08-16: +36,525 linesWeek of 2026-08-16: -13,811 linesWeek of 2026-08-23: +15,572 linesWeek of 2026-08-23: -2,705 linesWeek of 2026-08-30: +9,527 linesWeek of 2026-08-30: -247 linesWeek of 2026-09-06: +8,699 linesWeek of 2026-09-06: -492 linesWeek of 2026-09-13: +29,232 linesWeek of 2026-09-13: -6,342 linesWeek of 2026-09-20: +3,613 linesWeek of 2026-09-20: -1,267 linesWeek of 2026-09-27: +6,833 linesWeek of 2026-09-27: -787 linesWeek of 2026-10-04: +11,316 linesWeek of 2026-10-04: -1,457 linesWeek of 2026-10-11: +5,183 linesWeek of 2026-10-11: -576 linesWeek of 2026-10-18: +25,196 linesWeek of 2026-10-18: -4,685 linesWeek of 2026-10-25: +193 linesWeek of 2026-10-25: -52 linesWeek of 2026-11-01: +1,800 linesWeek of 2026-11-01: -1,847 linesWeek of 2026-11-08: +12,232 linesWeek of 2026-11-08: -1,910 linesWeek of 2026-11-15: +13,563 linesWeek of 2026-11-15: -1,274 linesJan 25, 2026Nov 15, 2026
+487.4K lines added, -220.6K removed over the last year.

Commits per week

last 52 weeks
2000Week of 2025-11-23: 0 commitsWeek of 2025-11-30: 0 commitsWeek of 2025-12-07: 0 commitsWeek of 2025-12-14: 0 commitsWeek of 2025-12-21: 0 commitsWeek of 2025-12-28: 0 commitsWeek of 2026-01-04: 0 commitsWeek of 2026-01-11: 0 commitsWeek of 2026-01-18: 0 commitsWeek of 2026-01-25: 18 commitsWeek of 2026-02-01: 69 commitsWeek of 2026-02-08: 21 commitsWeek of 2026-02-15: 38 commitsWeek of 2026-02-22: 58 commitsWeek of 2026-03-01: 51 commitsWeek of 2026-03-08: 62 commitsWeek of 2026-03-15: 52 commitsWeek of 2026-03-22: 111 commitsWeek of 2026-03-29: 33 commitsWeek of 2026-04-05: 75 commitsWeek of 2026-04-12: 130 commitsWeek of 2026-04-19: 200 commitsWeek of 2026-04-26: 112 commitsWeek of 2026-05-03: 150 commitsWeek of 2026-05-10: 52 commitsWeek of 2026-05-17: 30 commitsWeek of 2026-05-24: 6 commitsWeek of 2026-05-31: 24 commitsWeek of 2026-06-07: 58 commitsWeek of 2026-06-14: 50 commitsWeek of 2026-06-21: 32 commitsWeek of 2026-06-28: 83 commitsWeek of 2026-07-05: 87 commitsWeek of 2026-07-12: 52 commitsWeek of 2026-07-19: 4 commitsWeek of 2026-07-26: 26 commitsWeek of 2026-08-02: 20 commitsWeek of 2026-08-09: 52 commitsWeek of 2026-08-16: 111 commitsWeek of 2026-08-23: 63 commitsWeek of 2026-08-30: 12 commitsWeek of 2026-09-06: 27 commitsWeek of 2026-09-13: 28 commitsWeek of 2026-09-20: 26 commitsWeek of 2026-09-27: 43 commitsWeek of 2026-10-04: 41 commitsWeek of 2026-10-11: 20 commitsWeek of 2026-10-18: 81 commitsWeek of 2026-10-25: 3 commitsWeek of 2026-11-01: 19 commitsWeek of 2026-11-08: 49 commitsWeek of 2026-11-15: 62 commitsNov 23, 2025Nov 15, 2026
2.3K commits in the last 52 weeks.

When work happens

weekday and hour
SunMonTueWedThuFriSat036912151821Sun 0:00 — 9 commitsSun 1:00 — 14 commitsSun 2:00 — 3 commitsSun 3:00 — 5 commitsSun 4:00 — 5 commitsSun 5:00 — 0 commitsSun 6:00 — 1 commitsSun 7:00 — 1 commitsSun 8:00 — 3 commitsSun 9:00 — 5 commitsSun 10:00 — 8 commitsSun 11:00 — 12 commitsSun 12:00 — 25 commitsSun 13:00 — 10 commitsSun 14:00 — 15 commitsSun 15:00 — 13 commitsSun 16:00 — 15 commitsSun 17:00 — 25 commitsSun 18:00 — 13 commitsSun 19:00 — 17 commitsSun 20:00 — 17 commitsSun 21:00 — 12 commitsSun 22:00 — 22 commitsSun 23:00 — 19 commitsMon 0:00 — 30 commitsMon 1:00 — 19 commitsMon 2:00 — 5 commitsMon 3:00 — 0 commitsMon 4:00 — 2 commitsMon 5:00 — 2 commitsMon 6:00 — 2 commitsMon 7:00 — 9 commitsMon 8:00 — 8 commitsMon 9:00 — 12 commitsMon 10:00 — 19 commitsMon 11:00 — 14 commitsMon 12:00 — 34 commitsMon 13:00 — 33 commitsMon 14:00 — 23 commitsMon 15:00 — 13 commitsMon 16:00 — 23 commitsMon 17:00 — 16 commitsMon 18:00 — 13 commitsMon 19:00 — 10 commitsMon 20:00 — 13 commitsMon 21:00 — 11 commitsMon 22:00 — 8 commitsMon 23:00 — 17 commitsTue 0:00 — 25 commitsTue 1:00 — 11 commitsTue 2:00 — 1 commitsTue 3:00 — 1 commitsTue 4:00 — 2 commitsTue 5:00 — 2 commitsTue 6:00 — 0 commitsTue 7:00 — 5 commitsTue 8:00 — 6 commitsTue 9:00 — 13 commitsTue 10:00 — 19 commitsTue 11:00 — 13 commitsTue 12:00 — 23 commitsTue 13:00 — 13 commitsTue 14:00 — 18 commitsTue 15:00 — 36 commitsTue 16:00 — 12 commitsTue 17:00 — 20 commitsTue 18:00 — 12 commitsTue 19:00 — 11 commitsTue 20:00 — 10 commitsTue 21:00 — 9 commitsTue 22:00 — 29 commitsTue 23:00 — 23 commitsWed 0:00 — 28 commitsWed 1:00 — 11 commitsWed 2:00 — 6 commitsWed 3:00 — 2 commitsWed 4:00 — 0 commitsWed 5:00 — 1 commitsWed 6:00 — 1 commitsWed 7:00 — 6 commitsWed 8:00 — 7 commitsWed 9:00 — 6 commitsWed 10:00 — 19 commitsWed 11:00 — 20 commitsWed 12:00 — 31 commitsWed 13:00 — 23 commitsWed 14:00 — 26 commitsWed 15:00 — 27 commitsWed 16:00 — 26 commitsWed 17:00 — 13 commitsWed 18:00 — 33 commitsWed 19:00 — 16 commitsWed 20:00 — 12 commitsWed 21:00 — 21 commitsWed 22:00 — 20 commitsWed 23:00 — 26 commitsThu 0:00 — 5 commitsThu 1:00 — 6 commitsThu 2:00 — 2 commitsThu 3:00 — 3 commitsThu 4:00 — 0 commitsThu 5:00 — 0 commitsThu 6:00 — 2 commitsThu 7:00 — 8 commitsThu 8:00 — 7 commitsThu 9:00 — 13 commitsThu 10:00 — 19 commitsThu 11:00 — 25 commitsThu 12:00 — 26 commitsThu 13:00 — 35 commitsThu 14:00 — 22 commitsThu 15:00 — 24 commitsThu 16:00 — 37 commitsThu 17:00 — 20 commitsThu 18:00 — 12 commitsThu 19:00 — 25 commitsThu 20:00 — 12 commitsThu 21:00 — 31 commitsThu 22:00 — 16 commitsThu 23:00 — 10 commitsFri 0:00 — 16 commitsFri 1:00 — 15 commitsFri 2:00 — 5 commitsFri 3:00 — 1 commitsFri 4:00 — 0 commitsFri 5:00 — 0 commitsFri 6:00 — 2 commitsFri 7:00 — 7 commitsFri 8:00 — 4 commitsFri 9:00 — 6 commitsFri 10:00 — 15 commitsFri 11:00 — 26 commitsFri 12:00 — 23 commitsFri 13:00 — 15 commitsFri 14:00 — 27 commitsFri 15:00 — 18 commitsFri 16:00 — 28 commitsFri 17:00 — 19 commitsFri 18:00 — 24 commitsFri 19:00 — 15 commitsFri 20:00 — 23 commitsFri 21:00 — 17 commitsFri 22:00 — 21 commitsFri 23:00 — 9 commitsSat 0:00 — 7 commitsSat 1:00 — 6 commitsSat 2:00 — 2 commitsSat 3:00 — 1 commitsSat 4:00 — 0 commitsSat 5:00 — 0 commitsSat 6:00 — 2 commitsSat 7:00 — 2 commitsSat 8:00 — 3 commitsSat 9:00 — 7 commitsSat 10:00 — 12 commitsSat 11:00 — 4 commitsSat 12:00 — 10 commitsSat 13:00 — 15 commitsSat 14:00 — 18 commitsSat 15:00 — 32 commitsSat 16:00 — 62 commitsSat 17:00 — 21 commitsSat 18:00 — 28 commitsSat 19:00 — 30 commitsSat 20:00 — 30 commitsSat 21:00 — 19 commitsSat 22:00 — 12 commitsSat 23:00 — 24 commits
Commit volume by weekday and hour (UTC). Larger dots mean more commits.
DateListRankStars gained
Mar 5, 2026daily#25+129
Feb 28, 2026daily#23+244
Feb 27, 2026daily#20+165
Feb 25, 2026daily#25+151
Feb 24, 2026daily#15+184
Feb 23, 2026daily#8+256
Feb 22, 2026daily#4+589
Feb 21, 2026daily#4+426
Feb 13, 2026daily#19+126
Feb 6, 2026daily#16+188
Feb 5, 2026daily#13+173
Feb 4, 2026daily#15+147
Feb 3, 2026daily#4+331
Feb 2, 2026daily#2+751
  • morluto/rea

    Reverse engineer anything with agents, from app behavior down to native binaries.

    471.6K stars · TypeScript

  • freeCodeCamp/freeCodeCamp

    freeCodeCamp.org's open-source codebase and curriculum. Learn math, programming, and computer science for free.

    459.4K stars · TypeScript

  • openclaw/openclaw

    The AI that really does things. Any OS. Any Platform. The lobster way. 🦞

    394.9K stars · TypeScript

  • awesome-selfhosted/awesome-selfhosted

    A list of Free Software network services and web applications which can be hosted on your own servers

    339K stars

  • affaan-m/ECC

    The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

    307.9K stars · JavaScript

  • NousResearch/hermes-agent

    The agent that grows with you

    265K stars · Python