HKUDS/nanobotPublic

Your lightweight open-source personal agent.

AI summary: An ultra-lightweight, self-hosted Python framework for running persistent personal AI agents with native MCP support.

Stars
50.1K
+80 today
Forks
8.8K
Watchers
209
Open issues
229
Open PRs
643
Contributors
~505
Commits
5.3K
Branches
90
Views (30d)
7

PythonMITCreated Feb 1, 2026Last push 3d agoLatest release v0.4.1+170 stars this week+999 this month

Quick answers

What is nanobot?
An ultra-lightweight, self-hosted Python framework for running persistent personal AI agents with native MCP support.
What does nanobot do?
Nanobot provides a minimalist framework for building and running personal AI agents locally or on a private server. It features a built-in WebUI and terminal interface, allowing users to interact with their agents seamlessly. The framework deeply integrates the Model Context Protocol (MCP), enabling agents to securely access local files, shell environments, and web tools. It maintains persistent long-term memory and session history, ensuring context survives between interactions. With its OpenAI-compatible API and broad chat app integrations, it serves as a versatile, private alternative to commercial agent platforms.
Who is nanobot for?
Python developers and self-hosting enthusiasts who want a private, highly customizable AI agent framework. It is ideal for users needing deep local integrations via MCP and persistent memory without relying on third-party cloud platforms.
How do I get started with nanobot?
curl -fsSL https://raw.githubusercontent.com/HKUDS/nanobot/main/scripts/install.sh | sh
How popular is nanobot on GitHub?
HKUDS/nanobot has 50,148 stars and 8,755 forks on GitHub, and gained 170 stars in the last 7 days.
What license does nanobot use?
HKUDS/nanobot is released under the MIT license.

Star history

since Jul 28, 2026
020K40KJul 2026Sep 2026Oct 2026Nov 2026
50.1K stars as of Nov 17, 2026. Measured daily since Jul 28, 2026; GitHub no longer exposes earlier star timestamps.

Update history

2 recorded
  • Nov 6, 2026New release v0.4.1 (previously v0.3.5).
  • Oct 30, 2026Description changed from "Ultra-lightweight, open-source, self-hosted personal AI agent framework in Python with WebUI, tools, memory, MCP, multi-" to "Your lightweight open-source personal agent.".

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: 0 commits2026-02-01: 25 commits2026-02-02: 30 commits2026-02-03: 18 commits2026-02-04: 15 commits2026-02-05: 14 commits2026-02-06: 21 commits2026-02-07: 12 commits2026-02-08: 24 commits2026-02-09: 19 commits2026-02-10: 42 commits2026-02-11: 10 commits2026-02-12: 18 commits2026-02-13: 19 commits2026-02-14: 13 commits2026-02-15: 9 commits2026-02-16: 15 commits2026-02-17: 18 commits2026-02-18: 20 commits2026-02-19: 14 commits2026-02-20: 45 commits2026-02-21: 25 commits2026-02-22: 19 commits2026-02-23: 16 commits2026-02-24: 24 commits2026-02-25: 12 commits2026-02-26: 12 commits2026-02-27: 14 commits2026-02-28: 24 commits2026-03-01: 16 commits2026-03-02: 8 commits2026-03-03: 11 commits2026-03-04: 16 commits2026-03-05: 23 commits2026-03-06: 28 commits2026-03-07: 15 commits2026-03-08: 21 commits2026-03-09: 10 commits2026-03-10: 11 commits2026-03-11: 24 commits2026-03-12: 23 commits2026-03-13: 31 commits2026-03-14: 11 commits2026-03-15: 13 commits2026-03-16: 24 commits2026-03-17: 13 commits2026-03-18: 13 commits2026-03-19: 7 commits2026-03-20: 20 commits2026-03-21: 9 commits2026-03-22: 10 commits2026-03-23: 19 commits2026-03-24: 18 commits2026-03-25: 13 commits2026-03-26: 7 commits2026-03-27: 11 commits2026-03-28: 2 commits2026-03-29: 17 commits2026-03-30: 13 commits2026-03-31: 24 commits2026-04-01: 26 commits2026-04-02: 27 commits2026-04-03: 13 commits2026-04-04: 23 commits2026-04-05: 19 commits2026-04-06: 44 commits2026-04-07: 37 commits2026-04-08: 27 commits2026-04-09: 15 commits2026-04-10: 18 commits2026-04-11: 13 commits2026-04-12: 16 commits2026-04-13: 18 commits2026-04-14: 25 commits2026-04-15: 20 commits2026-04-16: 24 commits2026-04-17: 23 commits2026-04-18: 23 commits2026-04-19: 26 commits2026-04-20: 19 commits2026-04-21: 17 commits2026-04-22: 26 commits2026-04-23: 10 commits2026-04-24: 12 commits2026-04-25: 15 commits2026-04-26: 17 commits2026-04-27: 27 commits2026-04-28: 14 commits2026-04-29: 12 commits2026-04-30: 11 commits2026-05-01: 22 commits2026-05-02: 2 commits2026-05-03: 12 commits2026-05-04: 6 commits2026-05-05: 8 commits2026-05-06: 16 commits2026-05-07: 13 commits2026-05-08: 11 commits2026-05-09: 25 commits2026-05-10: 6 commits2026-05-11: 9 commits2026-05-12: 25 commits2026-05-13: 20 commits2026-05-14: 14 commits2026-05-15: 26 commits2026-05-16: 31 commits2026-05-17: 18 commits2026-05-18: 18 commits2026-05-19: 18 commits2026-05-20: 22 commits2026-05-21: 16 commits2026-05-22: 15 commits2026-05-23: 17 commits2026-05-24: 11 commits2026-05-25: 5 commits2026-05-26: 2 commits2026-05-27: 5 commits2026-05-28: 6 commits2026-05-29: 19 commits2026-05-30: 10 commits2026-05-31: 20 commits2026-06-01: 29 commits2026-06-02: 22 commits2026-06-03: 13 commits2026-06-04: 10 commits2026-06-05: 10 commits2026-06-06: 8 commits2026-06-07: 9 commits2026-06-08: 8 commits2026-06-09: 14 commits2026-06-10: 32 commits2026-06-11: 17 commits2026-06-12: 27 commits2026-06-13: 9 commits2026-06-14: 20 commits2026-06-15: 35 commits2026-06-16: 26 commits2026-06-17: 12 commits2026-06-18: 33 commits2026-06-19: 11 commits2026-06-20: 10 commits2026-06-21: 22 commits2026-06-22: 25 commits2026-06-23: 19 commits2026-06-24: 24 commits2026-06-25: 13 commits2026-06-26: 24 commits2026-06-27: 7 commits2026-06-28: 13 commits2026-06-29: 9 commits2026-06-30: 26 commits2026-07-01: 26 commits2026-07-02: 23 commits2026-07-03: 14 commits2026-07-04: 6 commits2026-07-05: 12 commits2026-07-06: 6 commits2026-07-07: 27 commits2026-07-08: 20 commits2026-07-09: 11 commits2026-07-10: 27 commits2026-07-11: 14 commits2026-07-12: 3 commits2026-07-13: 18 commits2026-07-14: 21 commits2026-07-15: 15 commits2026-07-16: 12 commits2026-07-17: 9 commits2026-07-18: 8 commits2026-07-19: 11 commits2026-07-20: 7 commits2026-07-21: 14 commits2026-07-22: 22 commits2026-07-23: 30 commits2026-07-24: 21 commits2026-07-25: 18 commits2026-07-26: 15 commits2026-07-27: 27 commits2026-07-28: 38 commits2026-07-29: 10 commits2026-07-30: 9 commits2026-07-31: 7 commits2026-08-01: 7 commits2026-08-02: 16 commits2026-08-03: 19 commits2026-08-04: 17 commits2026-08-05: 7 commits2026-08-06: 15 commits2026-08-07: 24 commits2026-08-08: 6 commits2026-08-09: 4 commits2026-08-10: 14 commits2026-08-11: 16 commits2026-08-12: 32 commits2026-08-13: 22 commits2026-08-14: 18 commits2026-08-15: 16 commits2026-08-16: 26 commits2026-08-17: 41 commits2026-08-18: 13 commits2026-08-19: 30 commits2026-08-20: 8 commits2026-08-21: 21 commits2026-08-22: 9 commits2026-08-23: 21 commits2026-08-24: 8 commits2026-08-25: 24 commits2026-08-26: 12 commits2026-08-27: 10 commits2026-08-28: 8 commits2026-08-29: 13 commits2026-08-30: 8 commits2026-08-31: 9 commits2026-09-01: 5 commits2026-09-02: 21 commits2026-09-03: 13 commits2026-09-04: 7 commits2026-09-05: 5 commits2026-09-06: 8 commits2026-09-07: 15 commits2026-09-08: 19 commits2026-09-09: 11 commits2026-09-10: 12 commits2026-09-11: 20 commits2026-09-12: 5 commits2026-09-13: 14 commits2026-09-14: 13 commits2026-09-15: 12 commits2026-09-16: 14 commits2026-09-17: 5 commits2026-09-18: 9 commits2026-09-19: 22 commits2026-09-20: 20 commits2026-09-21: 11 commits2026-09-22: 11 commits2026-09-23: 21 commits2026-09-24: 34 commits2026-09-25: 12 commits2026-09-26: 11 commits2026-09-27: 11 commits2026-09-28: 9 commits2026-09-29: 19 commits2026-09-30: 26 commits2026-10-01: 12 commits2026-10-02: 8 commits2026-10-03: 11 commits2026-10-04: 28 commits2026-10-05: 8 commits2026-10-06: 10 commits2026-10-07: 15 commits2026-10-08: 23 commits2026-10-09: 35 commits2026-10-10: 11 commits2026-10-11: 8 commits2026-10-12: 22 commits2026-10-13: 10 commits2026-10-14: 17 commits2026-10-15: 13 commits2026-10-16: 27 commits2026-10-17: 11 commits2026-10-18: 29 commits2026-10-19: 13 commits2026-10-20: 21 commits2026-10-21: 14 commits2026-10-22: 24 commits2026-10-23: 11 commits2026-10-24: 20 commits2026-10-25: 15 commits2026-10-26: 13 commits2026-10-27: 25 commits2026-10-28: 19 commits2026-10-29: 7 commits2026-10-30: 5 commits2026-10-31: 0 commits2026-11-01: 0 commits2026-11-02: 2 commits2026-11-03: 7 commits2026-11-04: 12 commits2026-11-05: 14 commits2026-11-06: 23 commits2026-11-07: 16 commits2026-11-08: 4 commits2026-11-09: 13 commits2026-11-10: 4 commits2026-11-11: 7 commits2026-11-12: 22 commits2026-11-13: 13 commits2026-11-14: 25 commits2026-11-15: 3 commits2026-11-16: 3 commits2026-11-17: 6 commits2026-11-18: 0 commits2026-11-19: 0 commits2026-11-20: 0 commits2026-11-21: 0 commits
4,699 commits in the last yearLessMore

Signals and awards

derived from tracked data
  • Landmark project

    50,148 stars

  • Very active

    4,699 commits in 52 weeks

  • Community-driven

    ~505 contributors

  • Permissive license

    MIT

  • Continuous integration

    Automated checks passing

  • Repeat trending

    25 trending appearances

What nanobot does

Nanobot provides a minimalist framework for building and running personal AI agents locally or on a private server. It features a built-in WebUI and terminal interface, allowing users to interact with their agents seamlessly. The framework deeply integrates the Model Context Protocol (MCP), enabling agents to securely access local files, shell environments, and web tools. It maintains persistent long-term memory and session history, ensuring context survives between interactions. With its OpenAI-compatible API and broad chat app integrations, it serves as a versatile, private alternative to commercial agent platforms.

Python developers and self-hosting enthusiasts who want a private, highly customizable AI agent framework. It is ideal for users needing deep local integrations via MCP and persistent memory without relying on third-party cloud platforms.

  • Ultra-lightweight core: Designed for fast, efficient execution on local hardware without the bloat of large commercial agent frameworks.
  • Native MCP integration: Connects securely to Model Context Protocol servers to access databases, APIs, and local files.
  • Persistent memory system: Utilizes long-term memory storage to ensure agents remember context and goals across multiple sessions.
  • Broad chat integrations: Connects seamlessly to Telegram, Discord, Slack, and WeChat for ubiquitous access to your personal agent.
  • OpenAI-compatible API: Exposes a standard API endpoint, allowing the agent to function as a drop-in replacement in existing AI pipelines.
  • Scheduled automations: Supports cron-based triggers for running long-horizon goals and automated tasks in the background.

Where teams use it

Private personal assistant

Deploy a self-hosted agent to manage local files and answer questions without sending sensitive data to external cloud providers.

Automated ChatOps

Connect the agent to Discord or Slack to autonomously manage server infrastructure and respond to team queries.

Scheduled data research

Configure cron-based tasks for the agent to scrape websites and generate daily summary reports automatically.

Local pipeline testing

Use the OpenAI-compatible API to test complex multi-agent applications locally before deploying expensive production models.

Getting started: curl -fsSL https://raw.githubusercontent.com/HKUDS/nanobot/main/scripts/install.sh | sh

README

main branch
nanobot README cover

nanobot

🐈 nanobot is an ultra-lightweight, open-source, self-hosted personal AI agent framework written in Python. Use it in a browser, terminal, or chat app to work with files, remember preferences, and schedule tasks. Connect a supported model provider or local model server to supply the AI.

Start Here

You want to... Go to
Install nanobot with no terminal/config background Start Without Technical Background
Install quickly and get your first reply Install and Quick Start
Open the bundled browser UI WebUI
Connect Telegram, Discord, WeChat, Slack, Email, Mattermost, Linear, or another channel Chat app guide
Configure providers, fallback models, Langfuse, MCP, web tools, or security Docs and Configuration
Develop the browser UI Install current source, then WebUI development and Contributing
Integrate from Python Python SDK
Understand or extend the internals Architecture, Contributing, and Provider extensions
Deploy to the cloud or keep nanobot running as a service Deployment

What can nanobot do?

nanobot can:

  • run in a browser WebUI or terminal
  • connect to Telegram, Discord, Slack, WeChat, Email, Mattermost, Linear, and other channels
  • read images, PDF, Word (.docx), Excel (.xlsx), and PowerPoint (.pptx) files with built-in file tools
  • use shell, web search/fetch, MCP integrations, cron, image generation, and multi-agent delegation
  • keep session history and use Dream to consolidate long-term memory
  • run long-horizon goals and scheduled automations
  • embed the agent with the Python SDK
  • deploy as a long-running local or server-side agent gateway

💡 Why nanobot

  • Persistent workflows: keep saved conversations, long-term memory, and task results for later work.
  • Chat-native reach: WebUI, Telegram, Feishu, Slack, Discord, Teams, email, Mattermost, and Linear.
  • Model freedom: OpenAI-compatible APIs, local LLMs, image generation, search, and fallbacks.
  • Small core: readable internals with MCP, memory, deployment, and automation built in.
  • Own your stack: inspect, customize, self-host, and extend without a giant platform.

📦 Install

You need Python 3.11 or newer and access to a supported model provider or local model server. Model fees or local hardware requirements depend on the service you choose; nanobot does not supply a model account.

Choose the stable release for everyday use or current source for development and the latest features. This README describes current source; published documentation covers the released version.

New to terminals or model credentials? Follow Start Without Technical Background. Updating an existing instance? Follow updates and recovery for your installation method, backup steps and restart checks.

Track Install with Update with What runs
Stable installer, uv, or pip WebUI when supported, otherwise the original package tool one released Python/WebUI/TUI version
Current source editable Git checkout git pull --ff-only + editable dependency sync Python, WebUI, and TUI from that checkout

Stable release: automatic setup (recommended)

The installer chooses an isolated Python environment and opens setup for you. The two commands below are the same installation method for different operating systems; run only the one for your system.

macOS / Linux
curl -fsSL https://raw.githubusercontent.com/HKUDS/nanobot/main/scripts/install.sh | sh
Windows PowerShell
irm https://raw.githubusercontent.com/HKUDS/nanobot/main/scripts/install.ps1 | iex
Installer details, preview, and script review

The default command installs or upgrades the stable PyPI release. Fresh installations use a dedicated environment under ~/.nanobot/venv. On a fresh local desktop it opens the WebUI for model setup. That gateway keeps running after the browser or terminal closes; use the printed gateway stop command to stop it. SSH, headless, existing-config and older-release installs use terminal setup when an interactive terminal is available; otherwise the installer prints the command to run later.

The installer uses the detected installation method when safe, or stops for manual review. Check existing extras and constraints with the original package manager. An active venv remains an explicit target, not an installer-managed environment. The installer avoids system-wide pip and prints the command to reuse if nanobot is not on PATH.

To preview the plan without changing your environment, pass --dry-run.

curl -fsSL https://raw.githubusercontent.com/HKUDS/nanobot/main/scripts/install.sh | sh -s -- --dry-run
& ([scriptblock]::Create((irm https://raw.githubusercontent.com/HKUDS/nanobot/main/scripts/install.ps1))) --dry-run

If you prefer to inspect the script first, open scripts/install.sh or scripts/install.ps1.

Already use uv or pip? Install the stable package yourself

Use this instead of the recommended installer when you already manage your own Python environment. These commands install the same stable nanobot-ai package; they do not launch setup.

uv: isolated CLI installation

uv tool install nanobot-ai

pip: activate your virtual environment first

python -m pip install nanobot-ai

Then run nanobot webui for browser setup, or nanobot onboard --wizard for terminal-only setup. For the Python SDK, install nanobot-ai in your application's virtual environment so the application can import it; a separate uv tool environment does not make the SDK importable there.

If pip reports externally-managed-environment, use the recommended installer, uv tool install nanobot-ai, pipx install nanobot-ai, or an activated virtual environment. Upgrade with the same method; for uv use uv tool upgrade nanobot-ai, and for pip use python -m pip install -U nanobot-ai.

Current source: development checkout

Install current source with Git and Bun

Clone the repository and install it in editable mode. A source install requires Git and Bun; Bun runs the matching TUI directly from the checkout instead of downloading an older release binary.

git clone https://github.com/HKUDS/nanobot.git
cd nanobot
python3 -m venv .venv

On Windows, use py -3 -m venv .venv instead of python3. Activate it with source .venv/bin/activate on macOS/Linux or .venv\Scripts\Activate.ps1 in Windows PowerShell, then run:

python -m pip install -e .

After that, the normal commands are identical to a stable install. nanobot runs the TUI from this checkout, and nanobot webui prompts to rebuild stale frontend assets, or warns in non-interactive sessions; --yes builds automatically. After stopping the old instance, git pull --ff-only updates the Python, TUI, and WebUI source together; rerun python -m pip install -e . when Python dependencies change, then restart the instance. Contributors should also read CONTRIBUTING.md.

Supported platforms, bundled UIs, and release tracks

Published packages include the WebUI, and supported platform wheels also include the native TUI. A source-distribution install can fetch a checksummed, version-matched TUI archive—with its licenses, notices, corresponding application source, source offer, and relinking instructions—on first use.

Platform wheels include both the WebUI and the native terminal UI: macOS 13+ (Apple Silicon and Intel), glibc 2.17+ Linux (ARM64 and x64), and Windows x64. The x64 runtime requires SSE4.2. Pip selects the matching wheel; opening the TUI does not need a separate GitHub download or Bun installation. A source-distribution install on a supported target can use the matching checksummed GitHub release archive. On other platforms, use nanobot --classic or the WebUI.

Verify the installation or locate the nanobot command

Verify the install:

nanobot --version

If nanobot is not on PATH, reuse the installer's printed command or run the Python executable from the existing installation with -I -m nanobot. For uv/pipx, locate that environment with the original manager. Do not use a temporary tool environment to manage an existing installation.

After installation, continue with Quick Start. Use the exact command printed by the installer if nanobot is not on PATH.

🚀 Quick Start

Open nanobot in your browser

If the installer already opened the WebUI, continue there. Otherwise run:

nanobot webui

Keep the launcher terminal open while using the browser. It starts or joins the shared local gateway and binds the first-run WebUI to localhost. If the browser does not open, copy the complete login link printed in the terminal, including everything after #; keep this credential private. For SSH or a headless host, use the remote-browser or terminal-only instructions below.

Your first three steps

  1. Open Settings → Models and save a provider/model preset with your credential or supported sign-in. See model setup if you need the full steps.
  2. Start a new topic and send Hello! to verify the model connection.
  3. To try file work, put a copy of notes.txt in a practice folder, select that folder and Default Permission (workspace-restricted access, not an OS sandbox), and ask: "Read notes.txt and write a short summary to summary.md." Open summary.md in that folder to check the result. See Your first file task.

A normal reply verifies the provider/model and browser connection. The file task separately checks the selected project and its file permissions. Attaching a file sends it to the conversation; it does not change the selected project folder.

Then describe your next goal in the same chat, for example: "I am already using the WebUI. Help me connect Telegram and allow only my account." An enabled nanobot-document skill can consult the documentation bundled with your installation; see Continue with nanobot for examples, explicit invocation, and availability.

Open the WebUI on a remote server through SSH

After installing nanobot on the server, start its WebUI without opening a server-side browser:

nanobot webui --no-open

Keep that server terminal running. In a second terminal on your own computer, forward the default WebUI port through SSH:

ssh -N -L 127.0.0.1:8765:127.0.0.1:8765 user@SERVER

Replace user@SERVER with your SSH login and leave the tunnel open. In your local browser, open the complete login link printed by the server launcher, preserving its # fragment. It uses http://127.0.0.1:8765, which now reaches the server through the tunnel. Complete Settings → Models and send Hello!. If local port 8765 is occupied, use another local port in the tunnel and change only the port in the browser link. Keep the server listener on localhost. For Docker, public endpoints, or service management, see Deployment.

Terminal-only setup, one-shot checks, and the TUI

If a model is not configured yet, use the terminal wizard:

nanobot onboard --wizard

Check one reply without opening the browser:

nanobot -m "Hello!"

For interactive work, open the terminal client:

nanobot

The native TUI uses the launch directory as its project workspace and shares saved conversations and the local gateway with the WebUI. The explicit nanobot agent form remains available for compatibility.

  • Type / to discover commands, /sessions to switch conversations, or @ to mention an app, MCP server, or saved session.
  • Paste clipboard images with Ctrl+V or Alt+V, and use $ to complete skill references.
  • Use /diff to inspect file changes, /context to inspect session context, or /branch to continue from a completed reply in a new session.
  • Press Enter to send. While nanobot is working, Enter sends now and Tab sends after the current response. Press Shift+Enter to add a newline (Ctrl+J works in terminals that cannot distinguish modified Enter keys).
  • Use /detach to promote the gateway to background mode and close the TUI while work continues.

Each launch starts a new session by default. Use --session to resume one and --workspace to choose another project workspace. See the CLI reference for session branching, diffs, history, shortcuts, gateway lifecycle, and compatibility options.

Save and check a preference

State a specific preference in your chat, for example: "For release notes, use concise bullet points." To consolidate it now, send /compact and then /dream, waiting for each to finish, and review /dream-log. Check the actual changes to USER.md or memory/MEMORY.md in the configured agent workspace, then test reuse in a new topic in the same instance. Dream may decide that no durable change is needed; a conversational acknowledgement alone does not prove the preference was saved. See Save and Check a Preference for file access, correction, and restoration steps.

Start and stop a sustained goal

Use a regular topic for a bounded objective with a clear completion condition, for example:

/goal Review this project's tests and list the smallest missing test case.

An active goal keeps nanobot working beyond the ordinary iteration limit until it records completion, cancellation, or a blocked state. This can use more model tokens; /stop interrupts the current work, while asking nanobot to cancel the goal abandons the objective. Execution errors can also stop the work. A scheduled automation instead starts work at specified times. Keep the gateway running for unattended work using the background or service options below.

After a gateway restart, reopen the original topic and review saved results before explicitly continuing any interrupted work. Recovery does not blindly replay uncertain tool actions. See the long-running agent guide for starting conditions and related automation options.

Keep the gateway running after closing interactive clients

After model setup, keep channels and automations running when interactive launchers close:

nanobot gateway --background

This starts or promotes the shared gateway to persistent background mode. Fresh official-installer environments already use that lifetime when you open nanobot webui; other Python installations can explicitly use nanobot webui --detach. Channels and automations remain active after local clients exit. Complete first-time model setup in the WebUI, and use the gateway commands below to manage the same instance.

From the TUI, /detach does the same before closing that client. Background mode does not configure startup after a machine reboot or restart after a crash; use an OS-managed service for that. Interrupted subagent tasks are not automatically relaunched after a restart, and missed scheduled times are not replayed; see subagent recovery and automation delivery.

Manage the background gateway with:

nanobot gateway status
nanobot gateway logs
nanobot gateway restart
nanobot gateway stop

To reopen the browser, run nanobot webui against the same instance and use its complete printed login link.

Run a configured gateway directly

Use this once a model is configured and you want to run the gateway directly in the current terminal:

nanobot gateway

It skips guided WebUI setup and browser opening. The WebUI remains available when its channel is configured. Use nanobot gateway --background for a detached process, or follow Deployment for startup and supervision by the operating system.

Read task guides or look up configuration details

If nanobot worked for you, a star on GitHub is the simplest way to support the project.

☁️ Deploy

Render — one click

Deploy nanobot's gateway and bundled WebUI from the repository's ready-to-use Blueprint:

Deploy to Render

Render will ask for ANTHROPIC_API_KEY and a private NANOBOT_WEB_TOKEN, then provision persistent storage for sessions, memory, and WebUI history. Persistent disks require a paid Render service. Existing disk configuration is preserved on redeploy; check it when changing credentials.

Self-host

Prefer your own infrastructure? Follow the deployment guide for Docker, Docker Compose, Linux services, and macOS LaunchAgent setup.

🌐 WebUI

The WebUI ships inside the published wheel with no separate frontend build. It is the browser workbench for persistent topics, temporary chats, visible agent activity, workspace controls, Apps, Skills, Automations, and settings. Start it with nanobot webui. WebUI access grants administration of the same agent instance; share it only with trusted operators. See Sharing access.

The screenshots show example conversations, illustrative token counts, and paused schedules; the interface may change.

Three conversations in one WebUI workbench

Mobile WebUI · dark theme

Mobile WebUI in dark theme with a saved conversation, model controls, context usage, and Default Permission

Use it to:

  • keep separate topics for different tasks and projects;
  • fork a topic from an earlier reply, or use temporary chats outside saved history and memory;
  • inspect reasoning, tool calls, file edits, diffs, command output, and generated artifacts;
  • switch model presets and choose a project before starting a topic;
  • attach images, documents, or video, and use voice input with a configured transcription provider;
  • configure models in Settings, connect chat platforms in Channels, and manage Apps, Skills, and Automations.

Videos can be played in WebUI, but the agent cannot directly analyze their contents.

Keep related work side by side

Group up to four conversations and arrange them in columns, rows, a grid, or a main pane with supporting panes. Each topic keeps its own history. Select another topic from the @ menu, or drag it into the composer, to let the agent read its context and coordinate work across sessions.

Choose a project, access mode, and model for each task. Topics separate conversation history; project folders select where file work happens. Neither creates separate long-term memory: one instance shares its agent profile, memory, and skills across projects. Use separate instances when client data or preferences must stay isolated. Explore topics and panes →

Inspect the work and its context

Expand agent activity to see reasoning, tool calls, and file changes. Switch Settings → Appearance → Edit preview to Diff for inline patches. The composer's context indicator shows the current context size, input tokens by round, and cache reuse when the provider reports it.

An expanded file-edit diff above the context usage chart, with input tokens and cache reuse shown across four rounds

Context compaction also appears in the conversation timeline. Explore activity and context →

Bring your tools into the conversation

Use Apps to connect MCP servers, enable Agent Plugins, and manage local CLI App adapters. Add a preset or a custom server, then attach an available tool with @. Skills provide reusable instructions. Settings holds model, voice, image, and web setup; Channels handles chat-platform connections.

The Apps MCP catalog with searchable integration presets and Connect actions

Explore Apps → · Discover Skills → · Connect chat apps →

Before connecting a personal bot to shared channels, check the platform's DM pairing/allowlist and group-access policies separately. Approving a private sender does not restrict group access on every platform; see the channel reference.

Let recurring work run on a schedule

Ask for an automation from the topic that should receive its results. Use Tasks to review and manage schedules, or Calendar to scan completed and upcoming runs by date. Local triggers let a script start a saved task on demand.

The Automations calendar with example completed runs arranged by date

Keep the gateway running and the host awake for scheduled delivery. Missed scheduled times are not replayed after a gateway restart. See delivery and recovery rules. Explore Automations →

For a conversation that should stay out of saved topic history and long-term memory, use Temporary chat from the header. Temporary chats end when the connection closes and use the default workspace with workspace-only permissions. Requests still go to the configured model provider, and files created by tools remain after the chat closes.

See the WebUI guide for LAN access, background operation, workspace controls, and the full feature tour. Working on the frontend itself? Use webui/README.md.

Architecture

nanobot architecture

The Python gateway owns agent execution, sessions, tools, memory, and security policy for the WebUI, TUI, and chat apps. The clients share that runtime; the core agent loop builds context, calls the model, executes requested tools, and returns the result. Memory, skills, channels, and MCP integrations extend that loop.

The Python SDK embeds the agent runtime in your application process.

See Architecture for source ownership and extension points.

Docs

Browse the repo docs for current source documentation, or visit nanobot.wiki for the stable release. The task guide index groups walkthroughs by outcome.

Releases

Latest release: v0.4.1

v0.4.1 improves workspace permissions, sandboxed commands, connection recovery, file-context previews, and navigation. It retains legacy history and proxy migration through 0.4.x.

Back up the stopped instance and upgrade through its original installation method. v0.3.5 can upgrade directly to v0.4.1; in-app automatic installation is not enabled for this release. See upgrade notes and Updating nanobot.

For other changes, see GitHub releases and the release archive.

Open Source Partners

Kimi Open Source Friends MiniMax

🤝 Contribute

Everyone is welcome to open an issue with a bug, reproduction, use case, or suggestion. Discuss the problem first; pull requests are currently limited to repository collaborators. See CONTRIBUTING.md for the contribution process and recognition.

Maintainers

Xubin Ren
Xubin Ren

Xubin Ren on X
Yongru Cheng
Yongru Cheng

Yongru Cheng on X

Community Contributors

Athemis axelray-dev yorkhellen yu-xin-c 04cb santhreal xcosmosbox KDB-Wind kunalk16 chaohuang-ai zayfod nikolasdehor JiajunBernoulli flobo3 hamb1y SergioSV96 morandot michaelxer coldxiangyu163 boogieLing aiguozhi123456 pinhua33 pixan-ai hussein1362 alekwo haosenwang1018 IlyaGusev T3chC0wb0y VITOHJL KailBug macroadster Hinotoi-agent kingassune goodtiding5 kiplangatkorir elkaix KimGLee m11y LingaoM DaryeDev CJWTRUST xzq-xu pikaxinge arcdrake22 JackLuguibin HaisamAbbas anunay999 flaviovs dajiaohuang C-Li Ho1yShif pjhoberman nghiahsgs Bahtya ZhouJ-sh bingqilinweimaotai Shizoqua tangtaizong666 XJPeng12 yanghan-cyber Yuxin-Lou LeoFYH claude chris-alexander benlenarts wzrayyy outlook84 Mrart ramonpaolo huhu-tiger tangjiabin yeyitech Flinn-X Qinnnnnn HengWeiBin waelantar tanishra olgagaga masterlyj xgzlucario dzydzydzy7 concertypin WangCheng0116 yarikoptic lukemilby gongpx20069 tobrien Shiniese zpljd258 FanouZeng-TT shawnWXN sbyinin nne998 lahuman hlgone franciscomaestre fat-operator shixi-li who96 cyzlmh zhuzhh cms19859230182-lang amplifierplus LZDQ wb213 shaun0927 LHMQ878 Michael-lhh Mizarka rick2047 kuchazi-yy Protocol-zero-0 subalkum vystartasv ZJUCQR ZegWe ZhangYuanhan-AI chtangwin dxtime ethanclaw

Recent activity

commits and pull requests

Releases and announcements

22 total
  1. v0.4.1v0.4.1Nov 6, 20261K downloads

    ## Changes - Fix TLS certificate verification, sandboxed shell execution and workspace permissions for queued inputs. - Keep idle maintenance from blocking active work or incorrectly refusing an update. Improve retry, reconnection and recovery behavior, and preserve native provider state through compaction. - Add a file-context graph with file previews, local Markdown links and recent context snapshots. Switching topics keeps each conversation's context separate. - Share syntax highlighting across code, source previews and read-only diffs, with complete source copying and plain-text fallbacks. - Reduce unnecessary memory copies in file reads, session history and provider requests. Improve navigation, context-usage display, history loading and skill-source identification. - Retain legacy history and proxy migration throughout 0.4.x, including original workspace ownership for unmigrated conversations. ## Upgrade notes - Stop affected processes and back up configuration and conversations before an external upgrade. Use the original installer, package manager or container workflow, then verify the running version, old conversations, a new message and another restart. See [Updating n

  2. v0.4.0v0.4.0Oct 28, 2026805 downloads

    🐈 **nanobot `v0.4.0`** makes everyday work easier to continue — with durable conversation history, a more capable workbench, and a clearer path to the next update. **Keep moving.** The gateway now stores model history and browser transcripts in SQLite, imports existing conversations, and coordinates updates around saved state. Stable and opt-in Preview releases share one update flow, with explicit confirmation before installation and restart. The browser workbench is easier to navigate and connect: complete prompt-history navigation, remote instances, clearer delegated-task details, richer attachments, and more consistent mobile controls. The terminal gains Mermaid diagram viewing and target-specific native bundles. Both clients continue to use the same Python gateway. This release also makes installation ownership explicit. Supported managed installations can update and recover the program through the app; other installations receive instructions for their original package manager or deployment. Recovery does not mean restoring an old copy of your chats. Please read the upgrade notes before replacing an existing installation. ## Highlights - **One update flow, with your conf

  3. v0.3.5v0.3.5Sep 15, 20262.4K downloads

    🐈 **nanobot `v0.3.5`** brings the workbench to the terminal — and makes conversations easier to continue across the browser, terminal, and chat apps. The headline is **one agent, more places to work**. Run `nanobot` for the native terminal client or `nanobot webui` for the browser. Both use the same gateway and saved WebSocket conversations. Terminal sessions can be resumed, forked, inspected, and detached without building a separate agent runtime. The browser workbench has grown around real multitasking: grouped conversation panes, temporary chats, persistent sidebar ordering, session mentions, a skills marketplace, portable Agent Plugins, and browser OAuth for remote MCP servers. Automations now have task and calendar views, clearer scheduling controls, and per-run replies. Mobile composition, settings, context charts, app logos, and branded mentions received another round of focused polish. The other story is **continuity you can inspect**. Context usage and compaction are visible, interrupted work has clearer recovery controls, and session history is more durable across pagination, reconnects, and upgrades. This release also tightens attachment, process, workspace, and emai

  4. v0.3.0v0.3.0Jul 25, 2026

    🐈 **nanobot `v0.3.0`** is here: **260 PRs merged and 38 new contributors**. The agent gained agency. The fastest way to experience the release is one command: ```bash nanobot webui ``` It prepares the local WebUI, starts the gateway, and opens the browser workbench. On a fresh install, guided setup helps you choose a provider and configure access without beginning in a JSON file. The published package already includes the WebUI, so there is no separate frontend build. The product story is **a WebUI that now feels like the front door to nanobot**. Chats read as topics; documents, quoted follow-ups, multimodal tool results, file diffs, code previews, and model fallback are visible in the conversation. Model presets can be switched from the composer, native desktop hosts can open a system folder picker, settings work better across narrow screens and dark mode, and the interface now includes Brazilian Portuguese plus substantially improved Traditional Chinese. Underneath that experience is **agency with boundaries**. nanobot can consult inline subagents, carry explicitly authorized work through verification, route turn state through a clearer runtime context, and swit

  5. v0.2.2v0.2.2Jun 23, 2026

    🐈 **nanobot `v0.2.2`** is here — 140 PRs merged, 21 new contributors. The agent got sturdier! The headline is **durability**. WebUI conversations now survive more of real life: transcripts are segmented instead of living in one fragile file, forked chats preserve replies more reliably, active turns scroll and replay more predictably, startup paths block less, and gateway shutdown is much calmer. Long sessions, stale providers, slow routes, broken config files, malformed history, stream stalls, and empty provider responses all got less likely to derail the work. The second story is **nanobot becoming a real Python runtime**. The SDK is no longer just a thin convenience layer around the agent loop: concurrent `run()` calls are isolated, hooks are cleaner, MCP lifecycle handling is safer, runtime controls are broader, and the docs now teach the SDK from first principles. If you want to embed nanobot inside your own application, `v0.2.2` is the first release where that path feels intentional. The third story is **the workbench getting broader and easier to live in**. The WebUI gained automation management, prompt navigation, token usage visibility, mobile polish, better updat

Code frequency

additions and deletions
+92.6K-92.6KWeek of 2026-02-01: +18,542 linesWeek of 2026-02-01: -7,580 linesWeek of 2026-02-08: +14,599 linesWeek of 2026-02-08: -7,778 linesWeek of 2026-02-15: +4,473 linesWeek of 2026-02-15: -3,038 linesWeek of 2026-02-22: +4,410 linesWeek of 2026-02-22: -3,748 linesWeek of 2026-03-01: +7,176 linesWeek of 2026-03-01: -2,783 linesWeek of 2026-03-08: +13,828 linesWeek of 2026-03-08: -6,068 linesWeek of 2026-03-15: +8,070 linesWeek of 2026-03-15: -2,282 linesWeek of 2026-03-22: +22,876 linesWeek of 2026-03-22: -15,922 linesWeek of 2026-03-29: +19,723 linesWeek of 2026-03-29: -5,509 linesWeek of 2026-04-05: +18,246 linesWeek of 2026-04-05: -3,952 linesWeek of 2026-04-12: +18,841 linesWeek of 2026-04-12: -1,794 linesWeek of 2026-04-19: +24,646 linesWeek of 2026-04-19: -5,236 linesWeek of 2026-04-26: +9,987 linesWeek of 2026-04-26: -1,600 linesWeek of 2026-05-03: +19,294 linesWeek of 2026-05-03: -8,922 linesWeek of 2026-05-10: +24,923 linesWeek of 2026-05-10: -8,015 linesWeek of 2026-05-17: +33,042 linesWeek of 2026-05-17: -6,237 linesWeek of 2026-05-24: +33,314 linesWeek of 2026-05-24: -8,131 linesWeek of 2026-05-31: +27,366 linesWeek of 2026-05-31: -6,788 linesWeek of 2026-06-07: +21,989 linesWeek of 2026-06-07: -8,224 linesWeek of 2026-06-14: +11,901 linesWeek of 2026-06-14: -3,721 linesWeek of 2026-06-21: +14,076 linesWeek of 2026-06-21: -3,673 linesWeek of 2026-06-28: +16,908 linesWeek of 2026-06-28: -3,857 linesWeek of 2026-07-05: +16,450 linesWeek of 2026-07-05: -6,734 linesWeek of 2026-07-12: +26,504 linesWeek of 2026-07-12: -4,068 linesWeek of 2026-07-19: +92,623 linesWeek of 2026-07-19: -59,525 linesWeek of 2026-07-26: +40,984 linesWeek of 2026-07-26: -10,498 linesWeek of 2026-08-02: +22,111 linesWeek of 2026-08-02: -8,074 linesWeek of 2026-08-09: +62,650 linesWeek of 2026-08-09: -26,756 linesWeek of 2026-08-16: +42,673 linesWeek of 2026-08-16: -20,513 linesWeek of 2026-08-23: +21,149 linesWeek of 2026-08-23: -7,656 linesWeek of 2026-08-30: +11,945 linesWeek of 2026-08-30: -5,308 linesWeek of 2026-09-06: +43,364 linesWeek of 2026-09-06: -15,678 linesWeek of 2026-09-13: +13,603 linesWeek of 2026-09-13: -3,895 linesWeek of 2026-09-20: +27,751 linesWeek of 2026-09-20: -11,205 linesWeek of 2026-09-27: +41,563 linesWeek of 2026-09-27: -20,424 linesWeek of 2026-10-04: +38,900 linesWeek of 2026-10-04: -19,725 linesWeek of 2026-10-11: +47,833 linesWeek of 2026-10-11: -20,282 linesWeek of 2026-10-18: +87,390 linesWeek of 2026-10-18: -20,887 linesWeek of 2026-10-25: +15,240 linesWeek of 2026-10-25: -14,862 linesWeek of 2026-11-01: +27,214 linesWeek of 2026-11-01: -7,197 linesWeek of 2026-11-08: +25,580 linesWeek of 2026-11-08: -15,314 linesWeek of 2026-11-15: +6,752 linesWeek of 2026-11-15: -2,597 linesFeb 1, 2026Nov 15, 2026
+1.1M lines added, -426.1K removed over the last year.

Commits per week

last 52 weeks
1730Week 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: 0 commitsWeek of 2026-02-01: 135 commitsWeek of 2026-02-08: 145 commitsWeek of 2026-02-15: 146 commitsWeek of 2026-02-22: 121 commitsWeek of 2026-03-01: 117 commitsWeek of 2026-03-08: 131 commitsWeek of 2026-03-15: 99 commitsWeek of 2026-03-22: 80 commitsWeek of 2026-03-29: 143 commitsWeek of 2026-04-05: 173 commitsWeek of 2026-04-12: 149 commitsWeek of 2026-04-19: 125 commitsWeek of 2026-04-26: 105 commitsWeek of 2026-05-03: 91 commitsWeek of 2026-05-10: 131 commitsWeek of 2026-05-17: 124 commitsWeek of 2026-05-24: 58 commitsWeek of 2026-05-31: 112 commitsWeek of 2026-06-07: 116 commitsWeek of 2026-06-14: 147 commitsWeek of 2026-06-21: 134 commitsWeek of 2026-06-28: 117 commitsWeek of 2026-07-05: 117 commitsWeek of 2026-07-12: 86 commitsWeek of 2026-07-19: 123 commitsWeek of 2026-07-26: 113 commitsWeek of 2026-08-02: 104 commitsWeek of 2026-08-09: 122 commitsWeek of 2026-08-16: 148 commitsWeek of 2026-08-23: 96 commitsWeek of 2026-08-30: 68 commitsWeek of 2026-09-06: 90 commitsWeek of 2026-09-13: 89 commitsWeek of 2026-09-20: 120 commitsWeek of 2026-09-27: 96 commitsWeek of 2026-10-04: 130 commitsWeek of 2026-10-11: 108 commitsWeek of 2026-10-18: 132 commitsWeek of 2026-10-25: 84 commitsWeek of 2026-11-01: 74 commitsWeek of 2026-11-08: 88 commitsWeek of 2026-11-15: 12 commitsNov 23, 2025Nov 15, 2026
4.7K commits in the last 52 weeks.

When work happens

weekday and hour
SunMonTueWedThuFriSat036912151821Sun 0:00 — 41 commitsSun 1:00 — 15 commitsSun 2:00 — 16 commitsSun 3:00 — 11 commitsSun 4:00 — 6 commitsSun 5:00 — 7 commitsSun 6:00 — 7 commitsSun 7:00 — 10 commitsSun 8:00 — 8 commitsSun 9:00 — 15 commitsSun 10:00 — 10 commitsSun 11:00 — 11 commitsSun 12:00 — 23 commitsSun 13:00 — 32 commitsSun 14:00 — 24 commitsSun 15:00 — 57 commitsSun 16:00 — 45 commitsSun 17:00 — 45 commitsSun 18:00 — 37 commitsSun 19:00 — 34 commitsSun 20:00 — 39 commitsSun 21:00 — 43 commitsSun 22:00 — 35 commitsSun 23:00 — 48 commitsMon 0:00 — 34 commitsMon 1:00 — 26 commitsMon 2:00 — 14 commitsMon 3:00 — 12 commitsMon 4:00 — 9 commitsMon 5:00 — 15 commitsMon 6:00 — 18 commitsMon 7:00 — 8 commitsMon 8:00 — 19 commitsMon 9:00 — 22 commitsMon 10:00 — 37 commitsMon 11:00 — 60 commitsMon 12:00 — 26 commitsMon 13:00 — 36 commitsMon 14:00 — 40 commitsMon 15:00 — 59 commitsMon 16:00 — 51 commitsMon 17:00 — 49 commitsMon 18:00 — 32 commitsMon 19:00 — 19 commitsMon 20:00 — 13 commitsMon 21:00 — 37 commitsMon 22:00 — 21 commitsMon 23:00 — 20 commitsTue 0:00 — 37 commitsTue 1:00 — 13 commitsTue 2:00 — 11 commitsTue 3:00 — 18 commitsTue 4:00 — 7 commitsTue 5:00 — 9 commitsTue 6:00 — 6 commitsTue 7:00 — 16 commitsTue 8:00 — 34 commitsTue 9:00 — 22 commitsTue 10:00 — 31 commitsTue 11:00 — 58 commitsTue 12:00 — 33 commitsTue 13:00 — 51 commitsTue 14:00 — 57 commitsTue 15:00 — 65 commitsTue 16:00 — 60 commitsTue 17:00 — 59 commitsTue 18:00 — 40 commitsTue 19:00 — 23 commitsTue 20:00 — 11 commitsTue 21:00 — 29 commitsTue 22:00 — 31 commitsTue 23:00 — 35 commitsWed 0:00 — 40 commitsWed 1:00 — 28 commitsWed 2:00 — 20 commitsWed 3:00 — 11 commitsWed 4:00 — 11 commitsWed 5:00 — 4 commitsWed 6:00 — 7 commitsWed 7:00 — 14 commitsWed 8:00 — 13 commitsWed 9:00 — 35 commitsWed 10:00 — 46 commitsWed 11:00 — 39 commitsWed 12:00 — 17 commitsWed 13:00 — 45 commitsWed 14:00 — 65 commitsWed 15:00 — 66 commitsWed 16:00 — 53 commitsWed 17:00 — 48 commitsWed 18:00 — 40 commitsWed 19:00 — 17 commitsWed 20:00 — 21 commitsWed 21:00 — 25 commitsWed 22:00 — 27 commitsWed 23:00 — 41 commitsThu 0:00 — 37 commitsThu 1:00 — 19 commitsThu 2:00 — 18 commitsThu 3:00 — 12 commitsThu 4:00 — 11 commitsThu 5:00 — 9 commitsThu 6:00 — 13 commitsThu 7:00 — 7 commitsThu 8:00 — 9 commitsThu 9:00 — 17 commitsThu 10:00 — 42 commitsThu 11:00 — 51 commitsThu 12:00 — 14 commitsThu 13:00 — 42 commitsThu 14:00 — 48 commitsThu 15:00 — 52 commitsThu 16:00 — 51 commitsThu 17:00 — 53 commitsThu 18:00 — 34 commitsThu 19:00 — 17 commitsThu 20:00 — 14 commitsThu 21:00 — 28 commitsThu 22:00 — 23 commitsThu 23:00 — 28 commitsFri 0:00 — 33 commitsFri 1:00 — 22 commitsFri 2:00 — 9 commitsFri 3:00 — 19 commitsFri 4:00 — 10 commitsFri 5:00 — 9 commitsFri 6:00 — 8 commitsFri 7:00 — 13 commitsFri 8:00 — 21 commitsFri 9:00 — 34 commitsFri 10:00 — 36 commitsFri 11:00 — 57 commitsFri 12:00 — 26 commitsFri 13:00 — 51 commitsFri 14:00 — 64 commitsFri 15:00 — 64 commitsFri 16:00 — 53 commitsFri 17:00 — 55 commitsFri 18:00 — 47 commitsFri 19:00 — 19 commitsFri 20:00 — 7 commitsFri 21:00 — 26 commitsFri 22:00 — 27 commitsFri 23:00 — 29 commitsSat 0:00 — 26 commitsSat 1:00 — 23 commitsSat 2:00 — 11 commitsSat 3:00 — 10 commitsSat 4:00 — 8 commitsSat 5:00 — 9 commitsSat 6:00 — 8 commitsSat 7:00 — 12 commitsSat 8:00 — 24 commitsSat 9:00 — 7 commitsSat 10:00 — 12 commitsSat 11:00 — 40 commitsSat 12:00 — 28 commitsSat 13:00 — 20 commitsSat 14:00 — 28 commitsSat 15:00 — 37 commitsSat 16:00 — 27 commitsSat 17:00 — 44 commitsSat 18:00 — 21 commitsSat 19:00 — 25 commitsSat 20:00 — 18 commitsSat 21:00 — 30 commitsSat 22:00 — 31 commitsSat 23:00 — 39 commits
Commit volume by weekday and hour (UTC). Larger dots mean more commits.
DateListRankStars gained
Mar 9, 2026daily#22+151
Feb 26, 2026daily#23+170
Feb 24, 2026daily#17+178
Feb 23, 2026daily#24+123
Feb 22, 2026daily#16+210
Feb 21, 2026daily#19+166
Feb 20, 2026daily#23+111
Feb 19, 2026daily#18+137
Feb 18, 2026daily#20+144
Feb 17, 2026daily#15+170
Feb 16, 2026daily#8+227
Feb 15, 2026daily#15+225
Feb 14, 2026daily#11+202
Feb 13, 2026daily#12+155
Feb 12, 2026daily#6+233
  • public-apis/public-apis

    A collective list of free APIs

    500.5K stars · Python

  • morluto/rea

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

    471.6K stars · TypeScript

  • openclaw/openclaw

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

    394.9K stars · TypeScript

  • donnemartin/system-design-primer

    Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.

    378.7K stars · Python

  • 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