#141 · Primary category: LLM Application Frameworks
concierge
🚀 Universal SDK for building next-gen MCP servers
Project last updated:06/09/26
GitHub Stars
532
Forks
98
Contributors
5
License
Other
Why we included this project
Concierge sits at the MCP protocol level and changes which tools get advertised at each step of a workflow, rather than dumping every tool on every request. The result is more deterministic agent behavior and fewer calls to the wrong tool. Wrapping an existing FastMCP server takes two lines and gives you progressive disclosure immediately; when you want full workflow control you add explicit stages and transitions. It also keeps session-scoped state between steps without round-tripping through the LLM, and a semantic-search mode collapses very large tool surfaces behind two meta-tools. That's a practical fit for teams shipping production MCP servers who want cleaner tool surfaces without rewriting their tool definitions.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
langchain
The agent engineering platform.
dify
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.
headroom
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
litellm
The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]
llama_index
LlamaIndex is the leading document agent and OCR platform