BotSharp for .NET
A modular .NET framework for multi-agent applications, RAG, and model-provider integration.
- Source repo
- SciSharp/BotSharp
- Stars
- ★ 3.1k
- Last updated
- 3d ago
- License
- Apache-2.0
- Primary language
- C#
- FA score
- 40/100 · Major gaps
At a glance
- How it runs
- Works with
- Universal · cross-platformChatGPT · OpenAI API · Claude API
- Cost
- Free software; you pay for model usage
- Setup effort
- Medium · a few setup steps
- You'll need
- Typical use
- A C# team maintaining an enterprise information system that needs to add agents with distinct responsibilities to an existing workflow.
- Not a fit if
- Teams unwilling to install the .NET 6+ SDK and build the backend from source
- Users wanting an all-in-one product without separately installing the SvelteKit admin UI
- Source review
- 40/100 · Major gaps 2 safety controls not found
What does this agent do, and when should you use it?
BotSharp is an open-source C# and .NET Core framework for connecting language models to existing business applications. Its plugin and pipeline-flow design separates platform concerns into components such as Agent Profile, Conversation & State, Routing & Planning, LLM Provider, caching, file repository, and Rich Content. Built-in plugins cover providers including OpenAI, Anthropic, Google, DeepSeek, Meta, and HuggingFace, along with knowledge-base, Qdrant, channel, and handler extensions. The framework exposes RESTful Open API and WebSocket communication, while a separate SvelteKit project supplies the BotSharp UI. It fits teams that want to self-host and compose multi-agent workflows inside a .NET application rather than adopt a single-provider runtime.
The backend can be started with dotnet run --project ./src/WebStarter/WebStarter.csproj -p SolutionName=BotSharp. Plugin Loader and Hooking load external components, while Agent Profile, Conversation & State, and Routing & Planning organize agent responsibilities, session state, and coordination. Provider plugins such as BotSharp.Plugin.OpenAI, BotSharp.Plugin.AnthropicAI, and BotSharp.Plugin.GoogleAI call supported model platforms. BotSharp.Plugin.KnowledgeBase and BotSharp.Plugin.Qdrant supply RAG-related interfaces and vector search, and BotSharp.OpenAPI plus WebSocket provide application-facing communication. Channel plugins including ChatHub, TelegramBots, WeChat, and Twilio can connect the application to messaging services; built-in MCP integration provides visual MCP management for model-initiated external calls.
- A C# team maintaining an enterprise information system that needs to add agents with distinct responsibilities to an existing workflow.
- A .NET application team that needs persisted conversation state and routing/planning for coordinated multi-agent tasks.
- Developers who need to integrate OpenAI, Anthropic, Gemini, DeepSeek, or HuggingFace through plugins in one application.
- An internal-assistant team building retrieval-augmented answers with a knowledge base and Qdrant vector search.
- A product team exposing conversational functionality through RESTful Open API, WebSocket, or Telegram, WeChat, and Twilio channels.
How do you install or deploy this agent?
Install the .NET 6+ SDK. Clone the repository, enter its directory, and run:
dotnet run --project ./src/WebStarter/WebStarter.csproj -p SolutionName=BotSharpOn Windows, use:
dotnet run --project .\src\WebStarter\WebStarter.csproj -p SolutionName=BotSharpFor the administration UI, separately clone https://github.com/SciSharp/BotSharp-UI, enter that directory, then run npm install and npm run dev. Before using a model plugin, configure the selected provider's API key in appsettings.json. If dependencies fail at startup, run dotnet restore.
How do you use this agent?
Start the backend and open http://localhost:5015/. Define an Agent Profile and its responsibilities, then select the needed plugins: for example, BotSharp.Plugin.OpenAI or BotSharp.Plugin.AnthropicAI for model access, and BotSharp.Plugin.KnowledgeBase or BotSharp.Plugin.Qdrant for retrieval. Connect a custom frontend through the RESTful Open API or WebSocket, or use channel plugins such as ChatHub, MetaMessenger, TelegramBots, Twilio, or WeChat. If you use the separate administration UI, run npm run dev in the BotSharp-UI project.
What are this agent's strengths and limitations?
- C# and .NET Core implementation with plugin and pipeline-flow execution is well aligned with existing .NET business applications.
- Agent Profile, conversation state, routing, and planning are explicit core modules for multi-agent orchestration.
- It combines multiple provider plugins with knowledge-base, Qdrant, messaging, RESTful Open API, and WebSocket integration points.
- Built-in MCP integration includes visual management for connecting model calls to external capabilities.
- It requires .NET 6+ and API-key configuration in
appsettings.jsonfor the chosen model provider. - The administration UI is maintained in a separate BotSharp-UI repository and adds npm installation and development steps.
- The supplied material mentions reverse proxies, Nginx/IIS, and separate UI deployment but does not provide concrete production configuration examples.
- A2A, Computer Use, and Browser Use remain unchecked on the documented roadmap.
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 for .NET This agent | 40 · Major gaps | Self-hosted serviceFree + model costs | ★ 3.1k | 3d ago | C# | ChatGPT · OpenAI API · Claude API |
| Neuron AI — Agentic Framework for PHP | 69 · Some gaps | Library / SDKFree + model costs | ★ 2.2k | 2d ago | PHP | OpenAI API · Claude API |
| Agentica | 69 · Some gaps | CLIFree + model costs | ★ 360 | today | Python | OpenAI API · Claude API |
| AI Agent Engineering Textbook | 60 · Some gaps | FrameworkFree | ★ 656 | 15d ago | HTML | — |
How does FollowAgents rate this agent?
Why each dimension lost points
The docs describe modular plugins, API key configuration, and an authentication flow; LLamaSharp also offers a local-model option, giving limited evidence of permission and data controls. Deductions: the packet does not show tool permission boundaries, confirmation before calls, data retention or deletion rules, secret protection, or rollback for side effects. Listed tools include HTTP, SQL, file, and Python capabilities. CI uses checkout@v1, and no dependency security review or mitigation is shown. License and project links provide limited provenance evidence, but publisher identity is unverified and maintenance responsibility is unclear.
The packet shows a cross-platform build and test workflow and gives .NET and configuration guidance, supporting a limited reliability assessment. Deductions: README and installation guidance are not fully consistent on ports, run commands, and supported versions; the setup depends on NuGet, LLM services, or local models without showing availability strategies; troubleshooting covers only dependency errors and LLM timeouts, not broader error handling or recovery.
The material targets .NET developers and describes multiple LLMs, plugins, UI/API options, messaging channels, and local models, with Windows, Linux, macOS, and .NET 6+ guidance. Deductions: capability boundaries and unsupported scenarios are sparse, and feature descriptions are often broad; examples do not clearly specify when particular agents, tools, or planning flows are triggered.
The README, installation guide, and topic-specific docs are organized by function and include a quick start, configuration example, FAQ, and deployment guidance; the LICENSE contains Apache 2.0 terms. Deductions: examples and instructions have inconsistencies in versions, commands, and wording; known limitations are thin, and the packet provides no changelog or clear compatibility policy; maintenance responsibility and update path are also unclear.
The framework combines agents, planning, state management, RAG, plugins, and several interfaces, while the installation guide provides actionable build and configuration steps. Deductions: benefits are primarily asserted in project documentation, with no packet evidence about costs, resource use, or return on effort; several key capabilities remain high-level descriptions whose implementation details require more documentation.
Some claims have corresponding material in the README, installation guide, LLamaSharp guide, and CI configuration. Deductions: cross-file corroboration is limited, and many Agent, MCP, and provider claims remain documentation assertions; the packet does not consistently distinguish implemented behavior, roadmap items, and broad claims. This review does not include runtime verification.
- 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.
- Before deployment, verify tool-plugin permissions and external side effects, and establish confirmation, audit, and recovery controls; the supplied material does not adequately describe them.
- Before configuring real LLM credentials, confirm how secrets are stored and access-controlled; the example only shows an empty API key field.
- Check the target revision's .NET, port, and dependency requirements; some instructions in the packet are inconsistent.
Maintain this project? Add the FARS badge to your README
[](https://followagents.com/en/agents/botsharp)<a href="https://followagents.com/en/agents/botsharp"><img src="https://followagents.com/badge/botsharp.svg" alt="FARS review"></a>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 * fix fork conversation by @iceljc in https://github.com/SciSharp/BotSharp/pull/1082 * fix realtime toolcall by @iceljc in https://github.com/SciSharp/BotSharp/pull/1087 * refine side car states by @iceljc in https://github.com/SciSharp/BotSharp/pull/1089 * temp revert by @iceljc in https://github.com/SciSharp/BotSharp/pull/1090 * revert by @iceljc in https://github.com/SciSharp/BotSharp/pull/1091 * optimize twilio by @yileicn in https://github.com/SciSharp/BotSharp/pull/1092 * detour rate limit by @iceljc in https://github.com/SciSharp/BotSharp/pull/1094 …View on GitHub ↗ -
Release notes excerpt
What's Changed * feat: Added Google Multimodal Live APIs by @gunpal5 in https://github.com/SciSharp/BotSharp/pull/993 * Clean code for GeminiLive by @hchen2020 in https://github.com/SciSharp/BotSharp/pull/997 * realtime-hub-refactor by @Oceania2018 in https://github.com/SciSharp/BotSharp/pull/999 * Add InterruptResponse in RealtimeModelSettings by @hchen2020 in https://github.com/SciSharp/BotSharp/pull/1000 * InputAudioTranscribe by @hchen2020 in https://github.com/SciSharp/BotSharp/pull/1001 * rename WaveStreamChannel by @yileicn in https://github.com/SciSharp/BotSharp/pull/1003 …View on GitHub ↗ -
Release notes excerpt
What's Changed * util-twilio-transfer_phone_call by @hchen2020 in https://github.com/SciSharp/BotSharp/pull/948 * hotfix twilio stream conversationId is null by @yileicn in https://github.com/SciSharp/BotSharp/pull/950 * add missing template by @iceljc in https://github.com/SciSharp/BotSharp/pull/951 * Hang up phone with audio by @hchen2020 in https://github.com/SciSharp/BotSharp/pull/952 * Update web driver functionalities by @visagang in https://github.com/SciSharp/BotSharp/pull/953 * Append dialogs into model context by @hchen2020 in https://github.com/SciSharp/BotSharp/pull/954 …View on GitHub ↗
FAQ
Is BotSharp free for commercial use?
Which model providers are supported?
Do I have to use BotSharp UI?
What should I check if model calls time out?
appsettings.json, network connectivity to the model provider, and whether the configured model name is correct.Thanks — we use this to improve the page.