- Conduid
- Marketplace
- #reinforcement-learning
MCP servers tagged reinforcement-learning
30 live MCP servers tagged "reinforcement-learning", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with reinforcement-learning.
Klavis-AI/YouTube
Klavis AI — independent third-party profile of a public API surface, by API Evangelist. Klavis AI is an open-source MCP integration platform that lets AI agents reliably use exter…
Awesome AI In Finance
🔬 A curated list of awesome LLMs & deep learning strategies & tools in financial market.
AI Agent Book
《深入理解 AI Agent：设计原理与工程实践》（李博杰 著）开源主仓库：全书正文、编译版 PDF 与按章配套代码
Unsloth
Unsloth is a local UI for training and running Gemma 4, Qwen3.6, DeepSeek, Kimi, GLM and other models.
Awesome Artificial Intelligence
A curated list of Artificial Intelligence (AI) courses, books, video lectures and papers.
AI Engineering From Scratch
Learn it. Build it. Ship it for others.
ML University
Machine Learning Open Source University
Agentenv Framework
Creating realistic RL environments requires collaboration between researchers, engineers, and domain experts across many dimensions: artifacts, environments tools, dynamism of the…
Omnisim
Open-source robotics simulator for coding agents: HTTP/JSON + MCP control, Newton physics, wgpu rendering, ROS 2, and reproducible benchmarks.
Smart Study Agent
The AI study agent that learns how you learn — RL picks the action, FSRS picks the timing, the LLM only writes the quizzes. Chrome extension · Anki export · MCP server · runs on O…
Howto
2937 everyday how-to recipes across 17 domains (incl. software-engineering and AI/LLM-engineering tracks for coding agents) — structured, verifiable procedures for training agents…
Agentic AI Engineering
This repository is dedicated to exploring and developing agentic AI systems that exhibit autonomous decision-making capabilities. Here, you will find resources including algorithm…
Mark Heartflow Skill
HeartFlow — AI cognitive engine: multi-path judgment, self-correcting RL, 3-layer memory, U/D/A/H field tracking, self-introspection with dream consolidation.
Tuneforge
An MCP server for dataset generation, fine-tuning, RL, and evaluation of LLMs — directly from your coding agent.
Openclaw Hackathon
Apollo Labs RL run orchestrator: FastAPI PPO training, eval baselines, rollout GIFs, canonical RunReports, AgentMail delivery, Nia lessons, Next.js dashboard, and MCP tools.
Awesome Workplace Agent Environments
A curated list of environments, benchmarks, datasets, and RL training resources for workplace AI agents: email, chat, calendar, docs, and enterprise apps.
Openexp
Q-learning memory for Claude Code — your AI learns from experience. 16 MCP tools, hybrid retrieval, closed-loop rewards.
Codex Issue Memory
Self-learning issue memory for Codex using MCP. Automatically captures reusable bug fixes and reuses them across sessions with local-first, low-token SQLite storage.
AI Engineering Production
AI Engineering Roadmap 2026 🚀 | Build & Deploy AI Apps from Scratch
Self Learning Browser Automation
Browser automation that learns from every interaction. Uses AI memory and reinforcement learning to get 27-122% better over time automatically. 🧠
Chuk Speccy
A deterministic ZX Spectrum emulator that's also an agent research environment and a Rust→Z80 toolchain: play classic games, let AI agents observe/drive/rewind them, and compile r…
App Harness
Reference FastMCP server that integrates an app into a sandbox, with populate/snapshot/restore state hooks for RL episodes.
Apollo Project
A locally-running evaluation environment that simulates knowledge-work tools (like Slack and task managers) to rigorously test and audit AI agents on complex, multi-step tasks.
Ontological GraphRAG Recommender
a knowledge-graph and RAG system that extracts requirements into neo4j, queryable through an ollama and MCP chat client with RL tuned retrieval strategies.
Software Engineering Rl Lab
Reproducible MCP tool-discovery environments for evaluating coding-agent engineering work.
Competitive Pricing Agent
Always-on autonomous e-commerce pricing agent on AWS — a 14-tool Amazon Bedrock ReAct agent that senses sales & competitor data, reasons, acts, and learns (epsilon-greedy). Includ…
Datalox Gated Runtime
Stateful, resettable, verifiable API worlds for tool-using agents.
AI Engineer Frontier
🔭 AI Engineer Track 3 of 4 — open-weight frontier models, Hermes and the Nous stack, post-training, GRPO, inference engineering, MCP. ~88 hours, 9 phases.
Swe Gym
Reproducible RL environments for evaluating coding agents on real software-engineering tasks through MCP tools. Deterministic verification, golden reference solutions, and CI that…
AgentGym
A verifiable Kubernetes incident gym for post-training and serving tool-using agents. Real control plane, deterministic workload simulator, executable rewards.