Repository Index

One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows.

• agentic-ai
• ai
• chats
• llm

Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings and DeepSeek Harness support.

• agent
• llm
• memory
• long-term-memory

Long-term memory runtime for AI agents — plain Markdown as the source of truth, local ranked retrieval, and an independent sleep-time Manage layer. Claude Code and Codex share one store. No API key.

• agent-memory
• ai-agents
• claude-code
• codex

Nosis is a lightweight personal agent runtime: per-session execution boundaries with OS-level sandboxing, computer use, a full built-in toolset, Skill / Plugin / MCP extensions, one runtime shared by GUI and TUI, and file-persisted sessions, plans, and memory.

• agent-framework
• agent-runtime
• agent-skills
• ai-agent

Outcome-based persistent memory MCP server for Claude Code and OpenCode. Good advice promoted, bad advice demoted. pip install roampal.

• ai-memory
• claude-code
• llm
• mcp

Persistent decision memory for AI agents: rationale, rejected approaches, and entity history. Connect any compatible agent through local MCP or the CLI.

• agent-memory
• agent-trace
• ai-agent-reasoning
• ai-agents

Go SDK for Dakera AI agent memory — self-hosted, 88.2% LoCoMo. Vectors, hybrid search, knowledge graphs, sessions.

• agent-memory
• ai-memory
• dakera
• go