llama-cpp-agent: llama-cpp-agent is a Python framework for interacting with LLMs running via llama.cpp. It provides a unified interface for chat, structured function calls, and JSON-formatted output — including models not explicitly fine-tuned for function calling. Developers can define tools and callable functions that the agent invokes directly, making it practical for building local agentic workflows without cloud dependencies.; Octopoda-OS: Octopoda is an open-source memory OS for AI agents that provides persistent memory, loop detection, audit trails, and real-time observability out of the box. It works automatically when you create an agent, and supports both local (SQLite) and cloud (PostgreSQL) storage. It integrates with popular frameworks like LangChain, CrewAI, AutoGen, and OpenAI Agents SDK, and offers an MCP server for Claude/Cursor.
Building local agentic pipelines with open-source LLMs
Building AI assistants with long-term memory