llmtrim
★ 171
vs
on-policy
★ 2.1k
llmtrim vs on-policy
llmtrim: llmtrim is a local proxy that intelligently compresses LLM API requests by removing wasted tokens, significantly reducing billing costs without impacting the quality of the LLM's responses. It offers versatile deployment options, including a proxy, CLI, MCP server, or library for various programming languages.; 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 llmtrim if…Reducing LLM API costs for AI agents (e.g., Claude Code, Cursor, Aider).
Choose on-policy if…Research and experimentation in cooperative multi-agent reinforcement learning
02
Side-by-Side Comparison
03
Features
llmtrim01Transparent LLM API Request Compression via Local Proxy
02Intelligent Content Optimization for Various Data Types (logs, code, context, JSON)
03Guaranteed Answer Quality and Cost Savings with Automatic Reversion of Ineffective Compression
04Flexible Integration Options: CLI, Library (Python, Ruby, Swift, Kotlin), and MCP Server
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
llmtrim↳Reducing LLM API costs for AI agents (e.g., Claude Code, Cursor, Aider).
↳Optimizing token usage in custom LLM applications and SDKs.
↳Compressing large context windows (e.g., pasted docs, conversation history) for RAG systems.
↳Shrinking verbose tool outputs like build logs, diffs, or large JSON arrays sent to LLMs.
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
llmtrimHidden GemEssential
on-policyTrendingReinforcement LearningMulti-Agent AI
FAQ
FAQ
What is the difference between llmtrim and on-policy?
Both llmtrim and on-policy are in the LLM Infra category. llmtrim has 171 stars, while on-policy has 2.1k stars.
Which is better, llmtrim or on-policy?
The best choice depends on your use case. Choose llmtrim if Reducing LLM API costs for AI agents (e.g., Claude Code, Cursor, Aider)., and on-policy if Research and experimentation in cooperative multi-agent reinforcement learning.
Is llmtrim free or open source?
Yes, llmtrim is open source on GitHub (AGPL-3.0).
Is on-policy free or open source?
Yes, on-policy is open source on GitHub (MIT).
→