Junyan Chin 8e558ad3a1 Feat/saas sandbox adaptation (#2234)
* fix(box): trust Box-reported skill paths when filesystem is not shared

In separated deployments (Docker Compose, k8s sidecar, --standalone-box,
remote runtime.endpoint) the Box runtime owns its own filesystem, so the
skill package_root it reports via list_skills is not resolvable on the
LangBot side. LangBot's reload_skills and build_skill_extra_mounts
validated those paths with os.path.isdir() against its own filesystem,
which silently dropped every skill in such deployments — breaking the
sandbox skill feature for the nsjail/SaaS backend.

Add BoxService.shares_filesystem_with_box, derived from the connector
transport (stdio = shared, WebSocket = separated), with an explicit
override seam for tests/embedders. Gate both isdir() guards on it: keep
local validation in shared-fs stdio mode, trust Box-reported paths
otherwise. The Box runtime only reports skills found on its own
filesystem, so those paths are valid there by construction.

Adds topology-derivation tests (real connector, no mocks) and
skill-retention tests for both shared and separated filesystems.

* build(docker): ship a self-contained nsjail sandbox backend in the image

Compile nsjail 3.6 from source in a dedicated multi-stage build and carry
only the binary plus its runtime libs (libprotobuf32, libnl-route-3-200)
into the final image. This lets the Box runtime isolate sandboxed code via
nsjail user/mount/pid/net namespaces without a host Docker socket — the
prerequisite for running Box on LangBot Cloud (k8s), where mounting
docker.sock would grant node root and is not acceptable for multi-tenant.

The build toolchain (build-essential/bison/flex/protobuf-dev/libnl-dev)
stays in the nsjail-build stage and is not present in the shipped image.

Verified: image builds (583MB), nsjail --help exits 0, libraries resolve,
and the real NsjailBackend executes an isolated command end-to-end on a
v6.1/cgroup2 host matching LangBot Cloud prod (rlimit fallback path, since
container /sys/fs/cgroup is read-only; PID-namespace isolation confirmed).

* feat(box): SaaS guard to force a single global sandbox scope

Add system.limitation.force_box_session_id_template: when non-empty it
overrides every pipeline's box-session-id-template at resolve time, pinning
all queries to one shared sandbox (e.g. {global}). This is the authoritative,
unbypassable guard — it runs on every exec call, so editing the pipeline
config via API cannot escape it. The web UI locks the Sandbox Scope selector
via a combined box_scope_editable flag (box available AND not forced).

* build(deps): pin langbot-plugin==0.4.2b1 (nsjail cgroup container-safety beta)

* fix(web): show forced sandbox scope + make disabled tooltip tap-friendly

When a SaaS deployment pins every pipeline to a fixed sandbox scope via
system.limitation.force_box_session_id_template, the Sandbox Scope selector was
correctly locked but still displayed the pipeline's stored value (e.g. the
per-chat default), misrepresenting the scope that the runtime actually enforces
on every exec. Coerce the displayed/saved value to the forced template so the
locked selector truthfully shows the active scope (e.g. Global).

Also fix the disabled_tooltip being invisible on touch devices: hover-only Radix
tooltips never open without a pointer, so the explanation of why the field is
locked could not be read on mobile. Wrap the info icon so a tap toggles the
tooltip while desktop hover still works.

* feat(web): hide sidebar new-version prompt for edition=cloud

Cloud instances are upgraded centrally by the operator, so surfacing a GitHub
'new version available' badge to tenants is misleading and actionable only by
the operator. Skip the release check entirely when edition=cloud.

* style(web): prettier formatting for DisabledTooltipIcon ternary

* chore(deps): bump langbot-plugin to 0.4.2b2

Picks up the SDK fix that creates a read-write host_path before the
nsjail bind-mount, fixing the SaaS MCP shared-workspace sandbox failure
(exec exit 255 with empty output when host_path didn't exist).

* chore(deps): bump langbot-plugin to 0.4.2b3

Picks up the nsjail /dev-node fix so stdio MCP servers (uvx-launched) can
start under force_global_sandbox instead of failing with 'Connection closed
/ please check URL'.

* fix(web): show real MCP runtime status on installed extensions list

The installed-extensions list badge keyed solely off the enable flag, so a
server that was still CONNECTING (or in ERROR) was shown as 'Connected'.
Reflect the actual runtime_info.status (connecting/connected/error/disabled)
with matching colors, and poll quietly every 3s while any MCP server is
connecting so the badge transitions without a manual refresh.

* chore(deps): bump langbot-plugin to 0.4.2b4

Picks up the 30s start_managed_process timeout so cold uvx MCP bootstraps
don't get torn down mid-install.

* style(web): satisfy prettier — parenthesize nullish-coalescing in ternary

* fix(mcp): isolate transient test sessions from the shared Box session

A config-page 'test' (server_name='_', no persisted UUID) ran in the same
shared 'mcp-shared' Box session as live MCP servers. A failing test (e.g.
empty args) churned that shared session and tore down healthy, already-
connected servers — leaving them stuck after exhausting their retries.

Mark UUID-less sessions as transient, give them their own isolated Box
session ('mcp-test-<uuid>'), and fully delete that session on cleanup so
tests can never disturb live servers and don't leak sessions.

* fix(mcp): tear down transient test session after test completes

A successful config-page test left its isolated 'mcp-test-<uuid>' Box
session running (the lifecycle task blocks until shutdown). Wrap the
transient test coroutine so it always shuts the session down afterward,
preventing isolated test sessions from leaking.
2026-06-09 19:30:17 +08:00
2026-06-03 11:12:39 +08:00
2026-06-03 11:12:39 +08:00
2026-05-16 12:05:54 +08:00
2026-06-09 19:30:17 +08:00
2025-11-06 21:34:02 +08:00
2025-10-07 00:15:56 +08:00
2025-05-20 09:39:46 +08:00
2025-09-13 09:44:18 +08:00
2026-05-16 12:05:54 +08:00
2026-05-16 12:05:54 +08:00
2026-06-03 11:12:39 +08:00
2026-06-09 19:30:17 +08:00

LangBot

LangBot - Production-grade IM bot made easy. | Product Hunt

Production-grade platform for building agentic IM bots.

Quickly build, debug, and ship AI bots to Slack, Discord, Telegram, WeChat, and more.

English / 简体中文 / 繁體中文 / 日本語 / Español / Français / 한국어 / Русский / Tiếng Việt

Discord Ask DeepWiki GitHub release (latest by date) python GitHub stars

Website Features Docs API Cloud Plugin Market Roadmap


What is LangBot?

LangBot is an open-source, production-grade platform for building AI-powered instant messaging bots. It connects Large Language Models (LLMs) to any chat platform, enabling you to create intelligent agents that can converse, execute tasks, and integrate with your existing workflows.

Key Capabilities

  • AI Conversations & Agents — Multi-turn dialogues, tool calling, multi-modal support, streaming output. Built-in RAG (knowledge base) with deep integration to Dify, Coze, n8n, Langflow, Deerflow, Weknora.
  • Universal IM Platform Support — One codebase for Discord, Telegram, Slack, LINE, QQ, WeChat, WeCom, Lark, DingTalk, KOOK.
  • Production-Ready — Access control, rate limiting, sensitive word filtering, comprehensive monitoring, and exception handling. Trusted by enterprises.
  • Plugin Ecosystem — Hundreds of plugins, event-driven architecture, component extensions, and MCP protocol support.
  • Web Management Panel — Configure, manage, and monitor your bots through an intuitive browser interface. No YAML editing required.
  • Multi-Pipeline Architecture — Different bots for different scenarios, with comprehensive monitoring and exception handling.

→ Learn more about all features

📍 Practical guides: deploy a multi-platform AI bot in 5 minutes, connect DeepSeek to WeChat, Discord, and Telegram, run a Dify Agent in Discord, Telegram, and Slack, and build an n8n-powered chatbot.


Quick Start

LangBot Cloud — Zero deployment, ready to use.

One-Line Launch

uvx langbot

Requires uv. Visit http://localhost:5300 — done.

Docker Compose

git clone https://github.com/langbot-app/LangBot
cd LangBot/docker
docker compose up -d

One-Click Cloud Deploy

Deploy on Zeabur Deploy on Railway

More options: Docker · Manual · BTPanel · Kubernetes


Supported Platforms

Platform Status Notes
Discord Official
Telegram Official
Slack Official
LINE Official
QQ Personal & Official API (Channel, DM, Group)
WeCom Enterprise WeChat, External CS, AI Bot
WeChat Personal & Official Account
Lark Official
DingTalk Official
KOOK Official
Satori
Email Matrix, Satori
Matrix Supports multiple bridged platforms such as Signal, WhatsApp, Messenger, iMessage, Mattermost, Google Chat, IRC, XMPP, Zulip, and more

Supported LLMs & Integrations

Provider Type Status
OpenAI LLM
Anthropic LLM
DeepSeek LLM
Google Gemini LLM
xAI LLM
Moonshot LLM
Zhipu AI LLM
Ollama Local LLM
LM Studio Local LLM
Dify LLMOps
MCP Protocol
SiliconFlow Gateway
Aliyun Bailian Gateway
Volc Engine Ark Gateway
ModelScope Gateway
GiteeAI Gateway
CompShare GPU Platform
PPIO GPU Platform
ShengSuanYun GPU Platform
接口 AI Gateway
302.AI Gateway
Qiniu Gateway

→ View all integrations


Why LangBot?

Use Case How LangBot Helps
Customer Support Deploy AI agents to Slack/Discord/Telegram that answer questions using your knowledge base
Internal Tools Connect n8n/Dify workflows to WeCom/DingTalk for automated business processes
Community Management Moderate QQ/Discord groups with AI-powered content filtering and interaction
Multi-Platform Presence One bot, all platforms. Manage from a single dashboard

Live Demo

Try it now: https://demo.langbot.dev/

  • Email: demo@langbot.app
  • Password: langbot123456

Note: Public demo environment. Do not enter sensitive information.


Community

Discord


Star History

Star History Chart


Contributors

Thanks to all contributors who have helped make LangBot better:

Languages
Python 63.3%
TypeScript 35.2%
JavaScript 0.9%
CSS 0.4%
Shell 0.1%