continual-learning

rsi-gear/gear

+169

Scikit-learn for Recursive Self-improvement (RSI). A modular framework for recursive harness evolution.

honcho

+73

Memory library for building stateful agents

letta-code

+46

Agents that self-improve with experience

reef

+11

Infrastructure for continually self‑improving agents

SkillClaw

+10

Let Skills Evolve Collectively with Agentic Evolver

Awesome-AI-Memory

+6

Awesome AI Memory | LLM Memory | A curated knowledge base on AI memory for LLMs and agents, covering long-term memory, reasoning, retrieval, and memory-native system design. Awesome-AI-Memory 是一个 集中式、持续更新的 AI 记忆知识库，系统性整理了与 大模型记忆（LLM Memory）与智能体记忆（Agent Memory） 相关的前沿研究、工程框架、系统设计、评测基准与真实应用实践。

test-model-thing

+1

A small proof-of-concept language model (not an LLM) that aims to incorporate latent-space prediction, internal state using recurrent trace units, and byte-by-byte output, built with MLX.