AI memory

An open standard for portable, interoperable AI memory across tools, sessions, and devices.

Let your AI agents search each other's past sessions.

AI-powered scam honeypot with Sara"

A universal external memory and tool-governance gateway for coding agents, with FAME route memory, knowledge graph, guardrails, and local-first workbench.

One local memory layer for Codex, Claude Code, opencode, Gemini CLI, Cursor, and MCP-capable coding agents.

Sync Claude Code global rules (CLAUDE.md) and memory across machines via your own private git repo. Agent-installable.

Self-Improvement-Plugin gives an agent memory-aware startup, safer tool use, session closeout, verification hooks, and fresh-context delegation. It is built for long agent sessions where the agent needs to remember prior work, avoid repeated mistakes, recover from drift, and capture lessons before the context disappears. WIP, Open-Source, Free

whoami: a Claude Code skill that scans your machine + interviews you to build a portable profile, giving any AI coding agent (Claude, Cursor, Codex) instant context about who you are.

Git for Agent Memory: Copy-On-Write vector branching for embedded multi-agent memory (83x faster, 3000x smaller snapshots)

A memory layer for your Claude Code work. It captures every session and writes your daily notes into files you own.

An autonomous AI code review agent that uses cascadeflow to route PR diff chunks by risk (saving LLM costs) and Hindsight to remember architectural lessons across sessions. It extracts, retains, and recalls feedback from past reviews, ensuring consistent and adaptive code reviews without breaking the LLM budget.

Remembers every PR, bug, and arch decision your team ever made

Built with Hindsight (persistent memory) + cascadeflow (budget control) + Groq AI. An AI Chief of Staff that remembers every investor, task, and decision for startup founders.

Built with Hindsight (persistent memory) + cascadeflow (budget control) + Groq AI. An AI Chief of Staff that remembers every investor, task, and decision for startup founders.

Built with Hindsight (persistent memory) + cascadeflow (budget control) + Groq AI. An AI Chief of Staff that remembers every investor, task, and decision for startup founders.

An open benchmark for the failure modes of agent memory systems: retraction, collision, recall, conflict. Offline, zero-dependency, reproducible.

Trustworthy memory system for LLM companions. Prevents memory fabrication with provenance tracking, write gates, and grounding audits.

Epistemic State Interface — your agent's memory should know what it forgot

Decision Brain: AI Investment Committee for trading agents. Bitget Hackathon S1 entry (Trading Agent track). Memory + multi-agent research + valuation + disciplined recommendations. No auto-trading.