Maximilian-Winter/llama-cpp-agent
An agent framework enabling function calling, structured output, and RAG for LLMs via guided sampling.
Not currently ranked — collecting fresh signals.
star history
The llama-cpp-agent framework provides an interface for building LLM-powered agents with support for single and parallel function calling, structured output generation, and retrieval augmented generation with ColBERT reranking. It uses guided sampling via grammars and JSON schema to enable function calling even on models not fine-tuned for it. The framework integrates with llama.cpp, llama-cpp-python, TGI, and vllm servers, and offers conversational, sequential, and mapping agent chains.
Frequently asked
- What is Maximilian-Winter/llama-cpp-agent?
- An agent framework enabling function calling, structured output, and RAG for LLMs via guided sampling.
- Is llama-cpp-agent open source?
- Yes — Maximilian-Winter/llama-cpp-agent is an open-source project tracked on heatdrop.
- What language is llama-cpp-agent written in?
- Maximilian-Winter/llama-cpp-agent is primarily written in Python.
- How popular is llama-cpp-agent?
- Maximilian-Winter/llama-cpp-agent has 650 stars on GitHub.
- Where can I find llama-cpp-agent?
- Maximilian-Winter/llama-cpp-agent is on GitHub at https://github.com/Maximilian-Winter/llama-cpp-agent.