{"data":{"slug":"hkuds-nanobot","name":"nanobot","tagline":"Lightweight, open-source AI agent for your tools, chats, and workflows.","github_url":"https://github.com/HKUDS/nanobot","owner":"HKUDS","repo":"nanobot","owner_avatar_url":"https://avatars.githubusercontent.com/u/118165258?v=4","primary_language":"Python","stars":47060,"forks":8312,"topics":["agent-framework","ai-agent","ai-agents","chatbot","chatops","discord-bot","llm-agents","llms","local-llm","mcp","model-context-protocol","multi-agent","openai-compatible","openclaw","personal-ai-assistant","python","self-hosted","telegram-bot-ai-assistant","webui","workflow-automation"],"archived":false,"github_pushed_at":"2026-08-16T08:38:45+00:00","maintenance_label":"Very active","stars_delta_30d":1303,"url":"https://www.graphcanon.com/tools/hkuds-nanobot","markdown_url":"https://www.graphcanon.com/tools/hkuds-nanobot.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/hkuds-nanobot","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=hkuds-nanobot","description":"Ultra-lightweight, open-source, self-hosted personal AI agent framework in Python with WebUI, tools, memory, MCP, multi-agent workflows, automation, and chat apps","homepage_url":"https://nanobot.wiki","license":"MIT","open_issues":706,"watchers":206,"ai_summary":"nanobot is a lightweight, open-source platform that facilitates the integration of various AI models such as Anthropic and OpenAI into different applications including chatbots and workflow automation tools. It supports interfacing with popular models like Claude and ChatGPT.","readme_excerpt":"## 📦 Install\n\n> [!IMPORTANT]\n> If you want the newest features and experiments, install from source.\n>\n> If you want the most stable day-to-day experience, install from PyPI or with `uv`.\n\nPick **one** install method:\n\nPrerequisites: Python 3.11 or newer. Git is only needed for a source install. Published packages already include the WebUI; a current-source install needs `bun` or `npm` to build it.\n\nIf terminals, API keys, or config files are new to you, use the guided zero-background walkthrough in [Start Without Technical Background](./docs/start-without-technical-background.md) instead of this compact README path.\n\n**One-command setup**\n\nmacOS / Linux:\n\n```bash\ncurl -fsSL https://raw.githubusercontent.com/HKUDS/nanobot/main/scripts/install.sh | sh\n```\n\nWindows PowerShell:\n\n```powershell\nirm https://raw.githubusercontent.com/HKUDS/nanobot/main/scripts/install.ps1 | iex\n```\n\nThe default command installs or upgrades `nanobot-ai` from PyPI. On a fresh local desktop, it then starts `nanobot webui` so you can configure the first provider and model in **Settings → Models**. SSH, headless, existing-config, and older-release paths keep the terminal setup wizard. The installer avoids system-wide pip installs by using an active virtual environment, `uv`, `pipx`, or a managed venv under `~/.nanobot/venv`. It also prints the exact command it used to run nanobot; reuse that full command below if `nanobot` is not on `PATH`.\n\nTo preview the plan without changing your environment, pass `--dry-run`; combine it with `--dev` when you want to preview the main-branch install.\n\n```bash\ncurl -fsSL https://raw.githubusercontent.com/HKUDS/nanobot/main/scripts/install.sh | sh -s -- --dry-run\n```\n\n```powershell\n& ([scriptblock]::Create((irm https://raw.githubusercontent.com/HKUDS/nanobot/main/scripts/install.ps1))) --dry-run\n```\n\nTo install the current `main` branch instead, pass `--dev`:\n\n```bash\ncurl -fsSL https://raw.githubusercontent.com/HKUDS/nanobot/main/scripts/install.sh | sh -s -- --dev\n```\n\n```powershell\n& ([scriptblock]::Create((irm https://raw.githubusercontent.com/HKUDS/nanobot/main/scripts/install.ps1))) --dev\n```\n\nIf you prefer to inspect the script first, open [`scripts/install.sh`](./scripts/install.sh) or [`scripts/install.ps1`](./scripts/install.ps1).\n\n**Install with `uv`**\n\n```bash\nuv tool install nanobot-ai\n```\n\n**Install from PyPI with pip**\n\n```bash\npython -m pip install nanobot-ai\n```\n\nIf pip reports `externally-managed-environment` on macOS or Linux, use the one-command installer, `uv tool install nanobot-ai`, `pipx install nanobot-ai`, or install inside a virtual environment.\n\n**Install from source**\n\n`bun` or `npm` must be available. From an activated virtual environment:\n\n```bash\ngit clone https://github.com/HKUDS/nanobot.git\ncd nanobot\npython -m pip install .\n```\n\nOn Windows, if pip reports that it cannot launch `npm`, run `cd webui`, `npm.cmd install --package-lock=false`, `npm.cmd run build`, and `cd ..` in order, then retry the install. Contributors who need an editable checkout should follow [`CONTRIBUTING.md`](./CONTRIBUTING.md) and [`webui/README.md`](./webui/README.md).\n\nVerify the install:\n\n```bash\nnanobot --version\n```\n\nIf `nanobot` is not on `PATH`, invoke it through the method that installed it: reuse the recommended installer's command, use `uv tool run --from nanobot-ai nanobot ...` or `pipx run --spec nanobot-ai nanobot ...`, or use the Python executable from the environment where pip installed the package.\n\n---\n\n## 🚀 Quick Start\n\n**Open nanobot in your browser**\n\n```bash\nnanobot webui\n```\n\nThis is the recommended first run. The launcher creates the config and workspace when needed, safely enables the local WebSocket channel after confirmation, starts the gateway, and opens [`http://127.0.0.1:8765`](http://127.0.0.1:8765). A fresh install can open before a model is configured, so setup continues in the browser instead of beginning in a JSON file. The first-run WebUI binds to localhost by default and is not","github_created_at":"2026-02-01T07:16:15+00:00","created_at":"2026-07-07T17:31:26.790806+00:00","updated_at":"2026-08-16T12:01:32.748309+00:00","categories":[{"slug":"ai-agents","name":"AI Agents","url":"https://www.graphcanon.com/categories/ai-agents","markdown_url":"https://www.graphcanon.com/categories/ai-agents.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/ai-agents"},{"slug":"developer-tools","name":"Developer Tools","url":"https://www.graphcanon.com/categories/developer-tools","markdown_url":"https://www.graphcanon.com/categories/developer-tools.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/developer-tools"}],"tags":[{"slug":"ai-agent","name":"ai-agent"},{"slug":"anthropic","name":"anthropic"},{"slug":"chatgpt","name":"chatgpt"},{"slug":"claude","name":"claude"},{"slug":"openai","name":"openai"}],"trust":{"provenance":{"is_fork":false,"github_id":1147094660,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-08-16T12:01:31.581Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":3,"days_since_push":0,"last_release_at":"2026-07-25T08:08:47Z","stars_delta_30d":1303,"open_issues_delta_30d":-167},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T10:57:15.005Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-08-16T12:01:32.055Z"},"deploy":{"source":"dockerfile:Dockerfile","self_host":true,"observed_at":"2026-08-16T12:01:32.055Z","managed_saas":false},"has_cli":{"value":true,"source":"pyproject.toml:[project.scripts]","observed_at":"2026-08-16T12:01:32.055Z"},"languages":{"value":["python"],"source":"github.language+pyproject.toml","observed_at":"2026-08-16T12:01:32.055Z"},"has_docker":{"value":true,"source":"dockerfile:Dockerfile","observed_at":"2026-08-16T12:01:32.055Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-08-16T12:01:32.055Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":{"min_ram_gb":1,"requires_docker":false},"constraints":{"min_ram_gb":1,"requires_docker":false},"when_to_use":["When you need to integrate lightweight and open-source AI functionalities in your existing Python projects, especially when leveraging models like Claude or ChatGPT.","For seamless development where interoperability between different AI tools and workflows is critical to maintain the efficiency of your applications."],"when_not_to_use":["If your project requirements demand a high level of customization and complex functionality beyond simple chatbots and straightforward workflow automation, as nanobot's lightweight architecture may be"],"source":"enrich:decision_facts","observed_at":"2026-07-11T12:30:46.252Z"},"constraint_facets":{"min_ram_gb":1,"requires_docker":false},"decision_summary":[{"label":"Requirements","value":"Min 1 GB RAM"},{"label":"Adopt for","value":"nanobot is a lightweight AI framework that eases integration of various AI models into specific applications such as chatbots and workflow automation."},{"label":"License detail","value":"nanobot operates under the MIT license, allowing for broad usage in both commercial and personal projects."}]}}