#persistent-memory

Hermes-style persistent memory and learning loop for Pi coding agent

El repositorio no publica descripción.

vMLX - Use MLX models easily - JANGQ (GGUF for MLX) - Not dependant on mlx_vlm

CPersona — persistent memory for AI agents over MCP. One SQLite file you own, hybrid vector + full-text + keyword search, no LLM in the loop, and honest reporting when recall degrades. MIT licensed.

Memory security for AI agents. Scan native memory writes, gate tools on bound hosts, inspect what was stored. Not a second brain.

CLI for managing AI agent squads. Status, memory, goals, feedback, and dashboard for your autonomous agents.

Shared, persistent memory for AI assistants, built on the Zettelkasten method

Persistent graph-native memory for coding agents — works with any MCP agent. SQLite + FTS5, model-agnostic.

Persistent memory for AI agents

Agentic AI memory with Ebbinghaus forgetting curve decay. +16pp better recall than Mem0 on LoCoMo.

Correction-first persistent memory for AI agents. MCP server + SDK + CLI. Compounds across sessions.

Yadgar (یادگار) — Persian for "memento, keepsake." A persistent memory engine for AI coding agents that survives sessions and /clears: it decays what you stop touching, promotes what recurs, filters recall to the git branch you're on, and pairs every memory with a curated wiki searched through the same ranking pipeline. Works with any MCP client.