on-policy
★ 2.1k
vs
conduit
★ 96
on-policy vs conduit
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.; conduit: Conduit acts as a local Model Context Protocol (MCP) gateway, designed to drastically reduce token overhead when AI agents utilize multiple tools by consolidating server tools into a few meta-tools. It simplifies the setup and authentication of various services, allowing them to be configured once and used across all connected AI clients.
01
TL;DR
Choose on-policy if…Research and experimentation in cooperative multi-agent reinforcement learning
Choose conduit if…Reducing token costs and improving context window efficiency for AI agents using many tools.
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
conduit01~90% fewer tokens by using lazy-discovery mode for tools.
02Single setup and authentication for all AI clients.
03Per-agent scoping to control tool access for different clients.
04Built-in governance to toggle tools on/off and audit calls.
05A built-in playground to test tools before integration.
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
conduit↳Reducing token costs and improving context window efficiency for AI agents using many tools.
↳Managing and authenticating multiple external services (e.g., Stripe, Supabase, GitHub) for various AI clients from a single gateway.
↳Providing granular control over which tools different AI clients or agents can access, enhancing security and compliance.
↳Testing and validating AI tools (e.g., from an MCP server) using a built-in playground before deploying them to agents.
05
Best For
on-policyTrendingReinforcement LearningMulti-Agent AI
conduit—
FAQ
FAQ
What is the difference between on-policy and conduit?
Both on-policy and conduit are in the LLM Infra category. on-policy has 2.1k stars, while conduit has 96 stars.
Which is better, on-policy or conduit?
The best choice depends on your use case. Choose on-policy if Research and experimentation in cooperative multi-agent reinforcement learning, and conduit if Reducing token costs and improving context window efficiency for AI agents using many tools..
Is on-policy free or open source?
Yes, on-policy is open source on GitHub (MIT).
Is conduit free or open source?
Yes, conduit is open source on GitHub (MIT).
→