The best-benchmarked open-source AI memory system. And it's free.
Memori is agent-native memory infrastructure. A LLM-agnostic layer that turns agent execution and conversation into structured, persistent state for production systems.
A persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex), backed by Markdown and Milvus.
Universal memory layer for AI Agents
Open-source cross-agent memory layer for coding agents via MCP. Compatible with Cursor, Claude Code, Codex, Windsurf, Gemini CLI, GitHub Copilot, Kiro, OpenCode, Antigravity, and Trae.
Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
10 captures since 2026-05-23
pyproject.toml
· python · 21 dependencies
uv.lock
· python · 0 dependencies
website/package.json
· javascript · 5 dependencies
website/bun.lock
· javascript · 0 dependencies
AI agent config detected
Key config paths
.agents
AGENTS.md
CLAUDE.md
website/concepts/agents.md
.agents
.agents/plugins
.agents/plugins/marketplace.json
AGENTS.md
CLAUDE.md
website/concepts/agents.md