Maximilian-Winter / llama-cpp-agent
The llama-cpp-agent framework is a tool designed for easy interaction with Large Language Models (LLMs). Allowing users to chat with LLM models, execute structured function calls and get structured output. Works also with models not fine-tuned to JSON output and function calls.
Why this job: says: agent framework; topics: llm-agent, llm-framework, function-calling, agents
What it does
- Simple Chat Interface. Engage in seamless conversations with LLMs.
- Structured Output. Generate structured output (objects) from LLMs.
- Single and Parallel Function Calling. Execute functions using LLMs.
- RAG. Retrieval Augmented Generation: Perform retrieval augmented generation with colbert reranking.
- Agent Chains. Process text using agent chains with tools, supporting Conversational, Sequential, and Mapping Chains.
Get started
pip install llama-cpp-agent- Maintenance
- Inactive
- Last commit 8 months ago
- Stars
- 664
- +2 this week
- Licence
- Custom
- Read before business use
- Downloads for
- None listed
- No release files
- Latest version
- 0.2.35
- Released 2 years ago
- Built with
- Python
- 100% of the code
Is it looked after?
- Contributors
- Not stated
- Last 90 days
- Issues
- 56% closed
- 22 still open
- Pull requests
- 27 merged
- 2 waiting
- Releases
- 62
- 0 in the last year
- No contributing guide
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| langroid / langroid | 4,146 | 3 days ago | MIT | No downloads |
| The-Pocket / PocketFlow-Tutorial-Codebase-Knowledge | 12,756 | 5 months ago | MIT | No downloads |
| patchy631 / ai-engineering-hub | 41,772 | 13 days ago | MIT | No downloads |
More: languages, topics, project record and preview image
Languages
- Python 100%
Topics
- agents
- llamacpp
- llm
- llms
- function-calling
- parallel-function-call
- llm-agent
- llm-framework
Project record
- JobAgent frameworks
- StatusListed
- Commits542
- Forks71
- Watching14
- Stars in 28 days+5
- CreatedDec 29, 2023
- First seen by usNov 7, 2026
- CheckedNov 8, 2026