BotSharp Agent Console
Create and manage AI assistants, agents, and conversations from one web interface.
- Source repo
- SciSharp/BotSharp-UI
- Stars
- ★ 160
- Last updated
- 7d ago
- License
- Apache-2.0
- Primary language
- Svelte
- FA score
- 48/100 · Major gaps
At a glance
- How it runs
- Works with
- Portable with changes
- Setup effort
- Medium · a few setup steps
- You'll need
- Typical use
- BotSharp users who need a browser interface for creating and managing AI assistants.
- Not a fit if
- Teams needing a fully local app with no backend service
- Developers seeking direct MCP or named model API integration
- Maintenance
- Commits in the last 30 dayslast commit 2026-11-10latest release r2.0-agent-utility (2024-07-23)
- Source review
- 48/100 · Major gaps 2 safety controls not found
What does this agent do, and when should you use it?
BotSharp UI is a web app for managing agents and conversations, including creating agents and managing existing ones. Its Node-based agent-building experience is intended to help users create an AI assistant quickly. The app is written in SvelteKit v2 and uses BotSharp for LLM services. The same interface also runs as a Tauri desktop app using the system WebView. The deployment guide describes Azure Static Web Apps; desktop builds require Rust, and Windows also requires the Desktop development with C++ workload from Visual Studio Installer.
After cloning the repository and installing npm dependencies, users can start the SvelteKit development server and use the UI to create agents, manage existing agents, and work with conversations. The app calls LLM services backed by BotSharp; the README does not specify concrete APIs, model providers, or agent configuration fields. Users can also launch the same web app through Tauri, whose desktop shell exposes no native commands to the page. A frontend production build can be deployed to Azure Static Web Apps using the documented CLI workflow.
- BotSharp users who need a browser interface for creating and managing AI assistants.
- Teams that need to review and manage conversations associated with existing agents.
- Developers who want to use the Node-based builder to create a new assistant quickly.
- Teams that want to run the same management interface as a Windows or macOS desktop app.
- Maintainers deploying the web interface to Azure Static Web Apps.
Key setup facts
Pulled from the install and usage notes below. The project README has the current values.
- Install / run
npm install -g @azure/static-web-apps-cli
- Config files
.env.env.local.env.development.env.production- Install notes cover
- Windows
How do you install or deploy this agent?
Node.js/npm are required; desktop builds also require Rust, and Windows requires the “Desktop development with C++” workload from Visual Studio Installer. The repository documents browser development and build commands:
git clone https://github.com/SciSharp/BotSharp-UI
cd BotSharp-UI
npm install
npm run devTo create a production build:
npm run buildFor Azure Static Web Apps deployment, the guide calls for a credential-verified build:
npm run build:verified -- --mode production
npm install -g @azure/static-web-apps-cli
swa deploy ./build/ --env production --deployment-token {token}The deployment token must be supplied by the deployment environment. The README does not explain how to deploy or configure the BotSharp backend.
How do you use this agent?
Start the development server, open the app in a browser, and use the UI to create agents and manage agents and conversations. To override .env values, create .env.local. To select an environment mode, run:
npm run dev -- --mode botsharpDesktop development and build commands are:
npm run tauri:dev
npm run tauri:dev -- --mode staging
npm run tauri:build -- --mode stagingWithout --mode, Tauri development looks for .env.development and builds look for .env.production; the committed .env supplies defaults. The README does not provide a standalone API usage method or first-time BotSharp service configuration steps.
What are this agent's strengths and limitations?
- One interface supports creating agents, managing agents, and handling conversations.
- Built with SvelteKit v2 and includes a Node-based agent-building experience.
- The browser and Tauri desktop versions use the same app interface, with no page-facing native commands.
- Documents Azure Static Web Apps deployment and uses build:verified to check that login credentials are absent from distributable output.
- LLM services depend on BotSharp; the README does not describe other backend or model-provider paths.
- The README omits BotSharp backend installation, configuration, and credential requirements, leaving the full deployment process unclear.
- Desktop development and builds require Rust; Windows also needs the Visual Studio C++ workload.
- npm run build does not perform credential cleanup and verification; the guide says to use build:verified for distribution.
How does this agent compare with similar options?
Key facts side by side with the most closely related agents.
| Agent | Source review | Form / cost | Stars | Updated | Language | Full support on |
|---|---|---|---|---|---|---|
| BotSharp Agent Console This agent | 48 · Major gaps | Web app | ★ 160 | 7d ago | Svelte | — |
| ArcReel Video Creation Workspace | 77 · Good | Self-hosted serviceFree + model costs | ★ 6.6k | today | Python | OpenAI API · Claude API |
| Taste-Skill: AI Frontend Aesthetic Upgrade | 72 · Some gaps | CLIFree + model costs | ★ 117k | 8d ago | JavaScript | ChatGPT · Codex · Claude Code |
| UIZZE · Better UI for Coding Agents | 69 · Some gaps | Agent plugin / skillFreemium | ★ 105 | 17d ago | JavaScript | Codex · Claude Code |
How does FollowAgents rate this agent?
Why each dimension lost points
The Tauri source registers no native commands for the page, and the README says the desktop shell hosts the same web app. That supports a limited least privilege finding. The README and workflow say distributable builds use a path that blanks and checks embedded admin credentials; the workflow selects that path. The script implementation is not included, and ordinary build skips the check, so sensitive-data handling earns only partial credit. The packet provides little evidence of confirmation for consequential actions, detailed data flows, recovery, or dependency security review; it only identifies an external-link opener and a BotSharp backend. Repository links offer limited attribution, but publisher identity is unverified and maintenance responsibility is unclear.
The README, package scripts, and CI agree that deployment uses build:verified, and the source supports the stated boundary between the desktop shell and browser app. A Node version requirement and npm installation steps provide some dependency availability guidance, but the packet has no lockfile or dependency security evidence. In the Tauri source, missing windows, monitor lookup failures, and resize errors return silently or are ignored. CI build protection helps, but runtime failure messaging is thin.
The README describes building and managing Agents and conversations, and documents browser development, desktop use, deployment, and environment-file options. The source clearly bounds Tauri's page-facing capabilities by exposing no native commands. The product description does not precisely define Agent triggers, capability boundaries, or intended audiences, limiting those scores. Environment variables, modes, and desktop platform notes provide concrete evidence of environment fit.
The README is organized into installation, development, build, desktop, deployment, and customization sections, with commands and environment details. It has no FAQ, and its examples focus on startup and packaging rather than Agent workflows. It documents credential-build risks and the adapter requirement as limitations. The LICENSE contains the full Apache 2.0 terms, so that criterion earns full marks. package.json supplies a stable name and version, but the packet has no changelog. Maintenance responsibility is not clear; badges and community links do not establish who maintains the project.
The stated purpose and README's Agent, conversation, and building features suggest a usable management interface, while sharing the app across desktop and web has practical value. The packet lacks Agent UI details, output formats, concrete workflows, and cost information, so usability and marginal value receive moderate scores and cost-benefit evidence is especially limited.
Key claims can be traced to the README, package scripts, CI configuration, or Tauri source. The CI's selection of build:verified corroborates the documented deployment safeguard. The script itself is not included, so its exact verification behavior cannot be confirmed from this packet. The README distinguishes a configuration convention from an enforced check; this review likewise separates documented claims from directly visible source evidence, while remaining limited by the sampled files.
- Not found in source: confirmation before actingTurn on (or add) a confirmation step before it acts, and try it in a sandbox or test environment before real data.
- Not found in source: rollback or recovery pathBack up first, or work on a git branch or snapshot, so its changes can be undone.
- Credential blanking and verification are documented for distributable builds, but the script is not in the packet; the README also says ordinary build does not run the check.
- The packet does not establish Agent action confirmations, detailed data flows, recovery procedures, or dependency security review. Treat these capabilities as unverified.
Recent releases
Latest entries from the project's GitHub Releases. Notes are quoted from upstream as written, not rewritten or tested by FollowAgents.
-
Release notes excerpt
What's Changed * Features/refine chat window by @iceljc in https://github.com/SciSharp/BotSharp-UI/pull/133 * refine user login by @iceljc in https://github.com/SciSharp/BotSharp-UI/pull/134 * add user role limit by @iceljc in https://github.com/SciSharp/BotSharp-UI/pull/132 * Features/add user avatar by @iceljc in https://github.com/SciSharp/BotSharp-UI/pull/135 * center options by @iceljc in https://github.com/SciSharp/BotSharp-UI/pull/136 * refine chat image upload by @iceljc in https://github.com/SciSharp/BotSharp-UI/pull/137 …View on GitHub ↗ -
Release notes excerpt
What's Changed * Features/refine chat window by @iceljc in https://github.com/SciSharp/BotSharp-UI/pull/112 * refine file drop and gallery by @iceljc in https://github.com/SciSharp/BotSharp-UI/pull/113 * add message disclaimer by @iceljc in https://github.com/SciSharp/BotSharp-UI/pull/114 * Features/refine chat window by @iceljc in https://github.com/SciSharp/BotSharp-UI/pull/115 * refine chat attachment option by @iceljc in https://github.com/SciSharp/BotSharp-UI/pull/116 * refine content log style by @iceljc in https://github.com/SciSharp/BotSharp-UI/pull/117 …View on GitHub ↗ -
Release notes excerpt
What's Changed * remove svelte-chartjs by @hchen2020 in https://github.com/SciSharp/BotSharp-UI/pull/1 * Update UserStore. by @hchen2020 in https://github.com/SciSharp/BotSharp-UI/pull/2 * Allow more customization. by @hchen2020 in https://github.com/SciSharp/BotSharp-UI/pull/3 * add refresh agents by @iceljc in https://github.com/SciSharp/BotSharp-UI/pull/5 * refine alert by @iceljc in https://github.com/SciSharp/BotSharp-UI/pull/6 * Change default plugin icon. by @hchen2020 in https://github.com/SciSharp/BotSharp-UI/pull/7 …View on GitHub ↗
FAQ
Can this UI provide LLM services without a BotSharp backend?
Can agent management be accessed through an API or MCP?
Can the desktop app call native operating-system features?
How should login credentials be kept out of a deployment bundle?
npm run build:verified; it blanks the public login values used for local prefill and checks the build output. Running npm run build alone does not perform this check.Is BotSharp Agent Console open source?
Is BotSharp Agent Console safe to use?
Is BotSharp Agent Console still maintained?
Who makes BotSharp Agent Console?
Thanks — we use this to improve the page.