on-policy
★ 2.0k
vs
llama-cpp-agent
★ 637
on-policy vs llama-cpp-agent
on-policy: This repository implements MAPPO, a multi-agent variant of PPO, widely used in cooperative multi-agent games and research. It provides robust implementations for various multi-agent environments like StarCraft II, Hanabi, and Google Research Football, along with detailed training scripts and hyperparameter guidance.; 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.
01
TL;DR
Choose on-policy if…Research and experimentation in cooperative multi-agent reinforcement learning
Choose llama-cpp-agent if…Building local agentic pipelines with open-source LLMs
02
Side-by-Side Comparison
03
Features
on-policy01Implementation of MAPPO (Multi-Agent PPO)
02Support for diverse multi-agent environments (e.g., StarCraft II, Hanabi)
03Ready-to-use training scripts for various scenarios
04Detailed hyperparameter guidance and updated results
05Default support for shared policy among agents
llama-cpp-agent01Structured function calls for models running via llama.cpp
02JSON-structured output even from non-function-call-finetuned models
03Chat interface with multi-turn conversation support
04Python-native tool/function definition and binding
05Compatible with local LLM deployments — no cloud required
04
Use Cases
on-policy↳Research and experimentation in cooperative multi-agent reinforcement learning
↳Benchmarking and evaluating PPO's effectiveness in MARL scenarios
↳Training AI agents for popular multi-agent games like StarCraft II and Hanabi
llama-cpp-agent↳Building local agentic pipelines with open-source LLMs
↳Extracting structured data from LLM responses without fine-tuning
↳Prototyping function-calling workflows on consumer hardware
05
Best For
on-policyTrendingReinforcement LearningMulti-Agent AI
llama-cpp-agentTrendingHidden Gem
FAQ
FAQ
What is the difference between on-policy and llama-cpp-agent?
Both on-policy and llama-cpp-agent are in the LLM Infra category. on-policy has 2.0k stars, while llama-cpp-agent has 637 stars.
Which is better, on-policy or llama-cpp-agent?
The best choice depends on your use case. Choose on-policy if Research and experimentation in cooperative multi-agent reinforcement learning, and llama-cpp-agent if Building local agentic pipelines with open-source LLMs.
Is on-policy free or open source?
Yes, on-policy is open source on GitHub (MIT).
Is llama-cpp-agent free or open source?
Yes, llama-cpp-agent is open source on GitHub.
→