🧠 Make your agents learn from experience. Now available as a hosted solution at kayba.ai
The living ecosystem where AI agents complete tasks through workflow loops, improve through iterative execution, are evaluated by mentor agents or humans in the loop, and turn completed work into reusable work experience and data to improve future agents.
Search, understand, reproduce, and improve an idea with ease
A systematic AI Agent development tutorial covering LLM agents, RAG, tool use, memory systems, multi-agent systems, LangChain, LangGraph, MCP, and agentic RL.｜从零开始学 AI Agent 开发 | 系统、全面、实战导向的 Agent 开发教程 | 每日自动追踪 arXiv 最新论文 | Learn AI Agent Development from Scratch
Correction-first persistent memory for AI agents. MCP server + SDK + CLI. Compounds across sessions.
This repository hosts a customized PPO based agent for Carla. The goal of this project is to make it easier to interact with and experiment in Carla with reinforcement learning based agents -- this, by wrapping Carla in a gym like environment that can handle custom reward functions, custom debug output, etc.
[NAACL 2025] KnowAgent: Knowledge-Augmented Planning for LLM-Based Agents
一站式Agent开发学习平台: Agent开发学习路线资料、智能刷题、面经题库
[ACL 2024] AutoAct: Automatic Agent Learning from Scratch for QA via Self-Planning
🪞 Make your agents recursively self-improve
[ACL 2024] Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology View
Self improving agents through iterations
The lightest CLI agent for Python. No heavy deps, no complex chains. pip install, set your API key, and run AI tasks anywhere.
Beginner-friendly introduction to multi-agent systems, agent interaction, coordination, and core concepts.
Codex plugin that exports local Codex learning signals into Hermes Agent
continuous-learning - Claude Code Skill
A quick intro to using Unity's MLAgents for MArch'20 students in University College London
Agent Learning Protocol — the fourth pillar of agent-native content. An open standard for structured learning pathways that AI agents can follow. Like MCP for learning.
A PyTorch re-implementation of World Models (Ha & Schmidhuber, 2018) for CarRacing-v3. The agent solves the track by "dreaming"—using a VAE for perception, an MDN-RNN for memory, and CMA-ES for controller evolution.
A governed learning control plane for Pi
Add a description, image, and links to the agent-learning topic page so that developers can more easily learn about it.
To associate your repository with the agent-learning topic, visit your repo's landing page and select "manage topics."