claude-mem vs ruflo

Two of the top projects in Skills, plugins and prompts, side by side: who leads on each score part and who each one suits, then setup, license, activity and what each review found.

11st of 389 in Skills, plugins and prompts

claude-mem

Persistent cross-session memory plugin for Claude Code and other coding agents

#44th of 389 in Skills, plugins and prompts

ruflo

Agent harness adding swarms, memory and hooks to Claude Code and Codex

Verdict

claude-mem ranks higher, 97 to 96. Of the 4 score parts we measure for both, claude-mem leads on 2, ruflo on none and 2 are even.

  • Adoptionclaude-mem leads by 2 points, 98 to 96: close to even.
  • FreshnessEven at 100.
  • Maintenanceclaude-mem leads by 2 points, 96 to 94: close to even.
  • Agent-readyEven at 85.

Pick claude-mem if you are

Claude Code users who want session memory that persists across runs

  • Local SQLite plus Chroma storage with a worker HTTP API and web viewer
  • Three-step search/timeline/get_observations flow filters before fetching full details, cutting tokens

Pick ruflo if you are

Claude Code and Codex users wanting multi-agent swarms and persistent memory

  • One command, `npx ruflo@latest init`, sets up agents, hooks, memory and MCP server
  • Plugin-only install route adds no files to the project workspace
claude-mem vs ruflo: score parts and facts
What we compareclaude-memruflo
Score parts, out of 100
Adoption98, widely used96, widely used
MomentumNot scored for this kindNot scored for this kind
Freshness100, active100, active
Maintenance96, healthy94, healthy
Agent-ready85, ready85, ready
Facts from GitHub and the README
Stars116.1k81.5k
LicenseApache-2.0 (permissive)MIT (permissive)
Last commitNov 2026Nov 2026
Last releaseNov 2026Nov 2026
LanguageTypeScriptTypeScript
DockerYesNo
GPUNot neededNot stated
arm64 or Apple SiliconNot statedMentioned

claude-mem

Claude-mem hooks into Claude Code's lifecycle events (SessionStart, UserPromptSubmit, PreToolUse, PostToolUse, Stop, SessionEnd) to capture tool-usage observations, summarize them, and inject relevant context into later sessions. Data is stored in SQLite with FTS5 and Chroma for hybrid search, served by a local Bun-managed worker with a web viewer. Search is exposed through three MCP tools (search, timeline, get_observations). Installers also exist for OpenCode, T3 Code, Antigravity, OMP, Pi and OpenClaw.

Who it is for: Claude Code users who want session memory that persists across runs

Strengths

  • Local SQLite plus Chroma storage with a worker HTTP API and web viewer
  • Three-step search/timeline/get_observations flow filters before fetching full details, cutting tokens
  • Installers for several harnesses besides Claude Code, including OpenCode, T3 Code and OpenClaw
  • `<private>` tags exclude sensitive content from storage

Weaknesses

  • Installer prompts for sign-in to a hosted observer with a 30-day trial; opt-out needs flags
  • Depends on Node 20+, Bun and uv, auto-installed if missing
  • `npm install -g claude-mem` gives only the SDK, not the hooks or worker
  • Some features, such as TeamBrain and cloud sync, rely on the hosted cmem.ai service
  • no GPU
  • Docker + Compose
  • Needs Node.js >=20, Bun, uv, SQLite, Chroma
  • Models: Anthropic plan, OpenRouter, Gemini, claude-mem observer

ruflo

Ruflo is a TypeScript layer around Claude Code and Codex. `npx ruflo@latest init` adds agent definitions, hooks, a memory store and an MCP server to the project, and the same pieces are also published as 48 Claude Code plugins. It also ships a console UI for inspecting agent runs, plus federation between machines.

Who it is for: Claude Code and Codex users wanting multi-agent swarms and persistent memory

Strengths

  • One command, `npx ruflo@latest init`, sets up agents, hooks, memory and MCP server
  • Plugin-only install route adds no files to the project workspace
  • Works with Codex and other MCP clients via `npx -y ruflo@latest mcp start`
  • Console limits Claude control to read/write/manage/full levels, default read with ask approval

Weaknesses

  • Very large surface: 406 MCP tools, 61 CLI commands and 48 plugins to understand
  • Full loop needs the CLI install, which writes .claude/, .claude-flow/ and CLAUDE.md
  • Mods are not sandboxed and run with your account's permissions
  • Plugin route requires Claude Code 2.1.287 or later
  • Needs Node.js (npx), Claude Code 2.1.287+ for plugin install
  • Models: Claude Code, Codex, Grok Build, DeepSeek, Ollama

More in Skills, plugins and prompts

Building with these?

We help teams pick an open-source AI stack and run it in production. Client work never changes a rank.