by JuliusBrussee · Claude Skill · ★ 385
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.
| Stars | 385 |
| Forks | 29 |
| Language | TypeScript |
| Category | Claude Skill |
| License | MIT |
| Quality Score | 58.958/100 |
| Open Issues | 32 |
| Last Updated | 2026-05-17 |
| Created | 2026-04-18 |
| Platforms | claude-code, node |
| Est. Tokens | ~22k |
These tools work well together with cavemem for enhanced workflows:
Explore other popular claude skill tools:
cavemem is Cross-agent persistent memory for coding assistants. Stored compressed. Retrieved fast. Local by default.. It is categorized as a Claude Skill with 385 GitHub stars.
cavemem is primarily written in TypeScript. It covers topics such as ai, caveman, claude.
You can find installation instructions and usage details in the cavemem GitHub repository at github.com/JuliusBrussee/cavemem. The project has 385 stars and 29 forks, indicating an active community.
cavemem is released under the MIT license, making it free to use and modify according to the license terms.