on-policy
★ 2.0k
vs
llmcore
★ 24
on-policy vs llmcore
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.; llmcore: LLMCore is a Qt/C++ library that provides a unified streaming API for multiple LLM providers (Claude, OpenAI, Ollama, Google AI, llama.cpp) and implements client and server for the MCP 2025-11-25 specification. It supports streaming chat, tool calling, and MCP transports like stdio and HTTP.
01
TL;DR
Choose on-policy if…Research and experimentation in cooperative multi-agent reinforcement learning
Choose llmcore if…Build custom LLM chat applications
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
llmcore01Unified streaming API for six LLM providers
02Full MCP client and server implementation (2025-11-25)
03Streaming chat and tool calling
04MCP transports: stdio and Streamable HTTP
05Support for tools, resources, prompts, and more in MCP
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
llmcore↳Build custom LLM chat applications
↳Integrate MCP tools into LLM clients
↳Expose tools and resources via MCP protocol
05
Best For
on-policyTrendingReinforcement LearningMulti-Agent AI
llmcoreTrendingDev Tooling
FAQ
FAQ
What is the difference between on-policy and llmcore?
Both on-policy and llmcore are in the LLM Infra category. on-policy has 2.0k stars, while llmcore has 24 stars.
Which is better, on-policy or llmcore?
The best choice depends on your use case. Choose on-policy if Research and experimentation in cooperative multi-agent reinforcement learning, and llmcore if Build custom LLM chat applications.
Is on-policy free or open source?
Yes, on-policy is open source on GitHub (MIT).
Is llmcore free or open source?
Yes, llmcore is open source on GitHub (MIT).
→