Persistent learning memory for AI coding agents. Memory that compounds.

Pi extension for daily self-learning memory with monthly summaries and git-backed commits

Scaffold an AI-operated product monorepo workspace for Claude Code — agents, skills, self-learning memory, and a full Requirement → Build → Feedback loop.

Project intelligence, token tracking, and learning memory middleware for OpenCode

D-Moss Memory: context-aware memory selection and self-learning memory draft generation for agent runtime.

SNS-MyAgent — BYOK coding agent CLI. Multi-agent + Telegram + self-learning memory. ~120MB binary, zero forced cost.

Octocode Awareness: always-on workspace coordination — awareness, collaboration, learning, memory/wiki, bookkeeping, housekeeping, reflection — zero npm runtime deps.

🐺 A second brain for OpenCode — OpenWolf port with zero dependencies. File index, learning memory, token tracking, bug memory.

Token-saving multi-agent orchestration for Factory AI Droid CLI. Native Rust compactor, auto-rewrite hooks, 18 expert sub-droids, learning memory.

Self-learning memory system for Claude Code agents

Production-ready AI agent orchestration platform with 66 specialized agents, 213 MCP tools, ReasoningBank learning memory, quantum-resistant Jujutsu VCS, and autonomous multi-agent swarms. Built by @ruvnet with Claude Agent SDK, neural networks, memory pe

Letta Code is a CLI tool for interacting with stateful Letta agents from the terminal.

Production-grade AI coding toolkit — 70 agents (incl. devil-mode adversarial crew), 194 skills, 97 commands, parallel multi-agent commands, semantic intent routing, self-learning memory, and a built-in MCP server (16 tools / 6 prompts / 377 resources) tha

Codex CLI integration for Ruflo (claude-flow) - OpenAI Codex platform adapter

Persistent memory for Claude Code - Give Claude a brain that remembers and evolves. Features AIME compression, semantic search, auto-learning, memory evolution, and usefulness tracking.

Self-learning vector memory for AI agents — single-file .rvf cognitive container with HNSW search, episodic Reflexion memory, causal graph + Cypher, 9 RL algorithms, Thompson Sampling bandit, 41 MCP tools, hybrid (BM25 + dense) retrieval, GNN attention. 1

The memory plugin stores durable facts, recalls relevant facts into prompts, and learns candidates from completed sessions. SQL schemas, exported types, tools, and tests are authoritative.

Self-Optimizing Neural Architecture (SONA) - Runtime-adaptive learning with LoRA, EWC++, and ReasoningBank for LLM routers and AI systems. Sub-millisecond learning overhead, WASM and Node.js support.

Production-ready AI agent orchestration platform with 66 specialized agents, 213 MCP tools, ReasoningBank learning memory, and autonomous multi-agent swarms. Built by @ruvnet with Claude Agent SDK, neural networks, memory persistence, GitHub integration,

MCP server for AI agent memory that adapts to feedback