totem
Active·★ 13·Apache-2.0·Updated 2026-05-27
★ Trending★ Memory & Context★ Dev Tooling
The persistent memory and context layer for AI agents.
Totem is a set of CLI tools that provides persistent memory and enforcement layer for AI agents. It uses deterministic hooks to remember lessons the AI forgets, catching architectural mistakes before they become permanent. Totem runs entirely offline and completes linting in under 2 seconds.
#ai-agents#ast-grep#cli#code-review#codebase-governance#developer-tools#git-hooks#human-in-the-loop
01
Features
01Offline linting in under 2 seconds
02Convert plain-English lessons into enforceable rules
03Git hooks for pre-push enforcement
04Cross-repo semantic memory via local knowledge base
05MCP server for agent context retrieval
02
Compatibility
Node.js
Node.js
Verified via docs
Linux
Linux x64
Verified via docs
macOS
macOS ARM64
Verified via docs
Windows
Windows
Verified via docs
03
Quick start
1
$ pnpm dlx @mmnto/cli init
04
Use cases
↳Prevent AI agents from repeating architectural mistakes
↳Enforce project-specific coding conventions and lessons
↳Provide persistent context to AI agents across sessions
05
Alternatives
letta★ 23.0k
Letta is the platform for building stateful agents: open AI with advanced memory that can learn and self-improve over time.
DesktopCommanderMCP★ 6.1k
This is MCP server for Claude that gives it terminal control, file system search and diff file editing capabilities
agents-best-practices★ 1.1k
Provider-neutral Agent Skill for Codex, Claude Code, and agentic harness design.
dagu★ 3.4k
Lightweight workflow engine built in a single binary with Web UI. Define workflows in a declarative YAML format. Linux, macOS, and Windows. Use your favorite AI agents to manage your workflows.
Related searches
Comments
Log in to leave a comment
- CCameron AndersonMay 22, 2026
Works as a context backbone that other agent capabilities build on.
- OOakley NguyenMay 13, 2026
Good for agent systems where accumulated context should persist across deployments.
- CCameron WilsonApr 11, 2026
Persistent memory and context layer for AI agents — the tribal knowledge metaphor is apt.
- Rebel LeeApr 11, 2026
Memory layer is designed for agents, not adapted from human-facing storage.