houtini-lm
★ 91
vs
on-policy
★ 2.0k
houtini-lm vs on-policy
houtini-lm: Houtini LM connects Claude Code to a local LLM server or any OpenAI-compatible API, offloading bounded tasks to reduce token costs. It provides tools, performance tracking, and model routing for efficient delegation. Claude remains the orchestrator for complex reasoning, while cheap local models handle grunt work.; 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.
01
TL;DR
Choose houtini-lm if…Generate test stubs
Choose on-policy if…Research and experimentation in cooperative multi-agent reinforcement learning
02
Side-by-Side Comparison
03
Features
houtini-lm01Offload bounded tasks to local or cloud LLMs
02Model discovery with HuggingFace metadata enrichment
03Real-time performance tracking (TTFT, tokens/s)
04Structured JSON output via grammar-based sampling
05Think-block stripping for models like GLM and Nemotron
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
04
Use Cases
houtini-lm↳Generate test stubs
↳Code review and bug finding
↳Draft commit messages
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
05
Best For
houtini-lmTrendingLLM InfraAPI Integration
on-policyTrendingReinforcement LearningMulti-Agent AI
FAQ
FAQ
What is the difference between houtini-lm and on-policy?
Both houtini-lm and on-policy are in the LLM Infra category. houtini-lm has 91 stars, while on-policy has 2.0k stars.
Which is better, houtini-lm or on-policy?
The best choice depends on your use case. Choose houtini-lm if Generate test stubs, and on-policy if Research and experimentation in cooperative multi-agent reinforcement learning.
Is houtini-lm free or open source?
Yes, houtini-lm is open source on GitHub (MIT).
Is on-policy free or open source?
Yes, on-policy is open source on GitHub (MIT).
→