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
kayba-ai/agentic-context-engine
Agentic Context Engine (ACE) is an innovative AI framework designed to enable AI agents to learn from their experiences and improve autonomously over time. The core idea behind ACE is to allow agents to remember their successes and failures during task execution and use this feedback to enhance their future performance without requiring additional training data or fine-tuning. This self-improving capability leads to significant performance gains, with reported improvements of 20-35% on complex tasks and reductions in token usage by nearly half in some scenarios. ACE is built around a research-backed framework that employs three specialized roles within the same language model: the Agent, which plans and executes tasks using learned skills; the Reflector, which analyzes the outcomes to identify what worked and what didn't; and the SkillManager, which updates the agent's skillbook with new knowledge derived from reflection. This approach ensures continuous learning and adaptation, preserving valuable context and avoiding knowledge loss over time. The framework offers multiple integration options to suit different use cases, including ACELiteLLM for simple self-improving agents, ACELangChain for wrapping existing LangChain agents, ACEAgent for enhancing browser-based agents, and ACEClaudeCode for autonomous coding agents using Claude Code. These integrations make it easy to plug ACE into various AI workflows, from coding assistants to browser automation. ACE supports asynchronous learning, allowing agents to respond instantly while learning happens in the background. It is compatible with over 100 LLM providers, including OpenAI, Anthropic, and Google, and includes production-grade observability features for enterprise use. The framework also incorporates smart deduplication to consolidate similar skills and maintain an efficient skillbook. Demonstrations showcase ACE's ability to correct common AI errors, optimize online shopping tasks, and autonomously improve coding projects over time. Overall, ACE represents a significant advancement in creating AI agents that continuously learn and adapt, making them more effective and efficient in real-world applications.
https://github.com/kayba-ai/agentic-context-engine
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.
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.
ghostwright/phantom
Self-hosted persistent AI co-worker built on the Claude Agent SDK that runs on its own machine with long-term memory, self-evolution, an MCP server and Slack, Telegram, email and web channels.