AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Home/
Multi-Agent/
BotSharp
BotSharp logo

BotSharp

Active·★ 3.1k·Apache-2.0·Updated 2026-10-27
★ Essential★ Trending

BotSharp is an open-source AI agent application framework written in C# on .NET, meant to connect LLMs to an existing business application. The README lists built-in multi-agent support with conversation and state management, several LLM planning approaches, RAG interfaces with memory-based vector search, agents with different responsibilities cooperating on a task, building, testing, evaluating and auditing agents in one place, a SvelteKit admin UI, rich-content integration with channels such as Facebook Messenger, Slack and Telegram, a REST API plus WebSocket, and MCP integration with visual management.

The kernel is kept small and most functions are plugins. Core modules include a plugin loader, hooks, authentication, agent profiles, conversation and state, routing and planning, templating, caching and LLM providers. Plugins cover data storage (MongoDB, LiteDB), LLMs (OpenAI, Azure OpenAI, Anthropic, Google, DeepSeek, Meta, HuggingFace, LLamaSharp, Semantic Kernel and others), messaging (ChatHub, Messenger, Twilio, Telegram, WeChat), RAG (knowledge base, Qdrant) and vision (PaddleSharp). To try it, run the WebStarter project with `dotnet run` and start the separate BotSharp UI with npm, then open localhost:5015. It is Apache-2.0 licensed.

This write-up is based on the project's README and public repository data. We have not hand-tested the tool. Data as of 2026-10-25.

License
Apache-2.0
Latest release
r5.2-image-composition · 2025-10-17
Last commit
2026-10-23
Contributors
93
Forks
655
Open issues and PRs
50
First published
2017-12-17

Source: GitHub, npm and PyPI public APIs.

#AI Agent#LLM Framework#NLU#.NET#Multi-Agent
$ Install
$ dotnet run --project .\src\WebStarter\WebStarter.csproj -p SolutionName=BotSharp
↗ Visit site★ GitHub
01

Features

01Built-in multi-agents and conversation with state management.
02Support multiple LLM Planning approaches for diverse tasks.
03Built-in RAG interfaces and memory-based vector searching.
04Compatibility with multiple AI platforms (e.g., ChatGPT, Gemini, LLaMA, Claude, DeepSeek, HuggingFace).
05Enables cooperation between multiple agents with distinct responsibilities.
02

Why choose it

+One of the few full agent frameworks for the .NET ecosystem, with a plugin architecture
+Many LLM providers as plugins, including local models through LLamaSharp
+Includes an admin UI, REST API and WebSocket, and chat-channel integrations
+Built-in RAG interfaces, multi-agent routing and planning, and MCP management
03

Trade-offs

!Aimed at .NET developers; teams on other stacks get little from it
!Quick start needs two repositories (backend and UI) and separate runtimes (dotnet and npm)
!The README is a feature and plugin list, with few worked examples
!Part of the README still describes a general machine-learning framework for bot platforms, which can confuse newcomers
04

Maintenance check

ActiveChecked: 2026-10-27
Last commit
2026-10-27
Commits, last 90 days
100+
Releases, last 90 days
0
Latest release
r5.2-image-composition (2025-10-17)
Open issues
51
Recent issues with at least one comment
0/2
Commits per week, last 12 weeks
Commits per week, last 12 weeks: 6, 18, 7, 17, 18, 13, 13, 2, 6, 3, 11, 3

Oldest week on the left; the latest four weeks are orange. Source: GitHub commit activity.

Status rule: archived on GitHub = Archived; last commit within 90 days = Active; 91 to 365 days = Slowing; older = Stale. All figures come from the GitHub API on the date shown.

Most discussed open issues

  • #100 Some project structure suggestions7 comments · 2023-08-14
  • #253 Newly Created Agent Speaks Chinese5 comments · 2024-01-15
  • #589 Conversation Message Exception4 comments · 2024-08-12
  • #556 MongoDbContext.cs GetDatabaseName Function Not Working Well2 comments · 2024-07-21
  • #216 Update the conversation status as closed2 comments · 2023-11-22

Issue titles are quoted from GitHub. Open the link to check whether a problem still applies to the version you use.

05

Compatibility

ChatGPT
Supported
Verified via docs
Gemini
Supported
Verified via docs
LLaMA
Supported
Verified via docs
Claude
Supported
Verified via docs
DeepSeek
Supported
Verified via docs
HuggingFace
Supported
Verified via docs
06

Quick start

1
$ dotnet run --project .\src\WebStarter\WebStarter.csproj -p SolutionName=BotSharp
07

Use cases

↳Developing intelligent robot assistants for information systems.
↳Integrating AI capabilities into existing enterprise business applications.
↳Building custom conversational AI platforms (CaaP) with flexible LLM choices.
08

Alternatives

⚡Top VS:
VSOpenRath★960→VSdeer-flow★84.5k→VSCrewAI★60.2k→VSAgenvoy★597→
OpenRath logo
OpenRath★ 960
An open-source, PyTorch-like runtime for dynamic multi-agent and multi-session workflows.
VSCompare→
deer-flow logo
deer-flow★ 84.5k
DeerFlow is a community-driven Deep Research framework, combining language models with tools like web search, crawling, and Python execution, while contributing back to the open-source community.
VSCompare→
CrewAI logo
CrewAI★ 60.2k
Framework for orchestrating role-playing, autonomous AI agents. By working together, your Crew can tackle complex tasks.
VSCompare→
Agenvoy logo
Agenvoy★ 597
Make AI actually work for you - A personal agent that writes its own tools and repairs itself.
VSCompare→
agent-framework logo
agent-framework★ 14.3k
A framework for building, orchestrating and deploying AI agents and multi-agent workflows with support for Python and .NET.
VSCompare→
PocketFlow logo
PocketFlow★ 11.3k
Pocket Flow: 100-line LLM framework. Let Agents build Agents!
VSCompare→
intentkit logo
intentkit★ 6.5k
An open and fair framework for everyone to build AI agents equipped with powerful skills. Launch your agent, improve the world, your wallet, or both!
VSCompare→
harness-sdk logo
harness-sdk★ 9.0k
Build an agent harness and control it end-to-end. Open-source SDK for production AI agents in Python & TypeScript - any model, any cloud.
VSCompare→
See all alternatives →

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Why choose it03Trade-offs04Maintenance check05Compatibility06Quick start07Use cases08Alternatives
SciSharp /
BotSharp
↗

Open-source .NET framework for building AI agent applications

3.1k655Apache-2.0
Last commit1d ago
StatusActive
CategoryMulti-Agent
Contributors93
Latest releaser5.2-image-composition
Links
Documentation↗Discussion↗Issues↗Releases↗
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit
© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

MCP ServersCode AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.