cavemem

About cavemem

cavemem why agent forget when agent can remember Install • How it works • CLI • MCP • Settings 🪨 Caveman Ecosystem  ·  caveman talk less  ·  cavemem remember more (you are here)  ·  cavekit build better Cross-agent persistent memory for coding assistants. Hooks fire at session boundaries, compress observations with the caveman grammar (75% fewer prose tokens, code and paths preserved byte-for-byte), and write to local SQLite. Agents query their own history through three MCP tools. No network. No cloud.

Quick Facts

Compatible Skills

These tools work well together with cavemem for enhanced workflows:

• Ori-Mnemos — semantic(0.27)+complementary+same_lang+similar_pop+shared_platform (59%)
• DeepWideResearch — semantic(0.28)+complementary+rare_topics+same_lang+similar_pop+shared_platform (59%)
• cortex-hub — semantic(0.16)+complementary+same_lang+similar_pop+shared_platform (56%)
• codemem — semantic(0.29)+complementary+same_lang+similar_pop+shared_platform (55%)

More Claude Skill Tools

Explore other popular claude skill tools:

• skills ⭐ 157.3k
• claude-code ⭐ 136.8k
• claude-mem ⭐ 86.4k
• caveman ⭐ 82.6k
• Understand-Anything ⭐ 71.9k
• oh-my-openagent ⭐ 65.3k
• get-shit-done ⭐ 63.8k
• Pake ⭐ 59.6k
• codegraph ⭐ 58.3k
• Understand-Anything ⭐ 49.9k

Popular TypeScript Agent Tools

• openclaw ⭐ 382.2k · Codex Skill
• n8n ⭐ 195.7k · MCP Server
• dify ⭐ 148.2k · MCP Server
• gstack ⭐ 120.5k · Agent Tool
• gemini-cli ⭐ 105.8k · MCP Server

Frequently Asked Questions