Back to directory

BotSharp

An open-source .NET framework for building AI agent and chatbot platforms, with a plugin-based pipeline that connects large language models to an existing business application.

Visit website (opens in a new tab)botsharp.readthedocs.io
BotSharp

BotSharp is an open-source machine learning framework for building an AI bot platform, aimed at connecting large language models to an existing application's business logic. It involves natural language understanding, computer vision and audio-processing technology, and aims to let ordinary programmers build AI applications faster using out-of-the-box machine learning algorithms.

It is written in C# on .NET Core, fully cross-platform, using a plug-in and pipeline execution design that decouples every part of the platform so a developer can swap in a different user interface or a different LLM provider behind a unified interface. It includes built-in multi-agent support with conversation state management, multiple LLM planning approaches for tasks of varying complexity, retrieval-augmented generation interfaces with memory-based vector search, support for multiple AI platforms including ChatGPT, Gemini, LLaMA, Claude and DeepSeek, cooperation between multiple agents with different responsibilities, tools to build, test, evaluate and audit an agent in one place, and a bundled UI written in SvelteKit.

It is released under the Apache 2.0 license.

More in Agent frameworks

See all 902
  • Recurse

    recurse.run

    A serverless harness that lets a coding agent design, test, and deploy its own specialist sub-agents as tools, MCP servers, or bots, defined by a schema-validated manifest.

  • ProofForge

    shulgin.is-a.dev

    An AI-agent pipeline that decomposes a mathematics problem, proves each piece, and formalizes the result in Lean 4 and Mathlib until the Lean kernel accepts it, with six of its proofs already merged into Google DeepMind's formal-conjectures repository.

  • local-coder

    github.com

    Builds a local coding-agent team on top of Ollama and OpenCode by detecting the machine's hardware, recommending models for seven specialist roles, and testing whether each assigned model can actually use tools, edit a repository and pass verification.