thedotmack/claude-mem
Claude-Mem is a plugin for Claude Code that captures, compresses, and preserves coding session context to enable persistent memory and continuity across sessions.
Awesome AI Agents › Continual Learning Agents
shobrook/saplings
Saplings is a library designed to build AI agents that reason using tree search algorithms. It combines the concept of tree-of-thoughts with tool use, allowing agents to explore and evaluate different tool-use trajectories before selecting the optimal path. This multi-step lookahead and backtracking capability helps reduce mistakes and enhances reasoning compared to traditional chain-of-thought or ReAct-style agents. The library supports state-of-the-art performance on various tasks such as coding, question answering, and web navigation by employing search algorithms like Monte Carlo Tree Search (MCTS), A*, and greedy best-first search. Key features of Saplings include plug-and-play functionality for building smarter agents with minimal code, support for popular search algorithms, function calling under the hood, and customization options for value functions, prompts, and search parameters. It also supports over 100 large language models (LLMs) through LiteLLM integration. The library provides a straightforward way to create tools that agents use to perform tasks or answer queries. Tools extend a base class and define their name, description, parameters, and execution method. Agents can be configured by selecting a model, setting up an evaluator to score search trajectories, and choosing an agent type based on the desired search algorithm. Saplings offers multiple agent implementations including MonteCarloAgent (MCTS), AStarAgent (A* search), GreedyAgent (greedy best-first search), and COTAgent (chain-of-thought without search). Saplings is designed to improve AI agent reasoning by enabling them to plan and evaluate multiple steps ahead, reducing errors and improving task performance. It is suitable for developers looking to build advanced AI agents that leverage tree search techniques for enhanced decision-making and problem-solving capabilities.
https://github.com/shobrook/saplings
Also in Continual Learning Agents
vectorize-io/hindsight
Hindsight is an agent memory system designed to create smarter, learning AI agents, addressing limitations of traditional memory techniques like RAG and knowledge graphs.
langchain-ai/langchainjs
LangChain.js is a TypeScript framework for building context-aware, reasoning applications powered by large language models, offering modular components, chains, agents, and tools for production and deployment.
aden-hive/hive
Hive is an outcome-driven agent development framework designed for evolving agents with AI evaluation, human-in-the-loop, and self-improvement capabilities.
aiming-lab/MetaClaw
Proxy-based layer that turns everyday conversations with a personal agent into learning signals, injecting skills per turn and running scheduled reinforcement learning updates without a local GPU.
kayba-ai/agentic-context-engine
Agentic Context Engine (ACE) is a framework that enables AI agents to autonomously learn from their successes and failures, continuously improving their performance across various tasks without additional training data or fine-tuning.
AgentDock/AgentDock
AgentDock is an open-source framework for building sophisticated AI agents with configurable determinism, enabling reliable and creative AI applications through a node-based architecture and multi-stage workflows.
modelscope/AgentEvolver
Self-evolving agent training framework from ModelScope that combines automatic task generation, experience-guided exploration and attribution-based credit assignment into one reinforcement learning stack.