Cross-agent 持久记忆为 coding assistants. Stored compressed. Retrieved fast. 本地由 default.GitHub 594 ⭐ / 52 Fork，主要使用 TypeScript 开发。标签：ai,caveman,claude,claude-code,compress。访问项目：https://github.com/JuliusBrussee/cavemem
项目介绍
Cross-agent 持久记忆为 coding assistants. Stored compressed. Retrieved fast. 本地由 default.
核心功能
- Persistent memory across sessions. Hooks capture what happened; the store keeps it. - Compressed at rest. Deterministic caveman grammar, round-trip-guaranteed expansion for humans. - Progressive MCP retrieval. `search`, `timeline`, `get_observations` — agents filter before fetching. - Hybrid search. SQLite FTS5 keyword + local vector index, combined with a tunable ranker. - Local by default. No network calls. Optional remote embedding providers via config. - Web viewer. Read-only UI at `http://localhost:37777` for browsing sessions in human-readable form. Token-protected: the worker generates a local bearer token on first start and injects it into the served page, so `cavemem viewer` still opens with zero friction while `/api/*` rejects requests without it.
使用指南
</div> <p align="center"> <strong>🪨 Caveman Ecosystem</strong> · <a href="https://github.com/JuliusBrussee/caveman">caveman</a> <em>talk less</em> · <strong>cavemem</strong> <em>remember more</em> <sub>(you are here)</sub> · <a href="https://github.com/JuliusBrussee/cavekit">cavekit</a> <em>build better</em> · <a href="https://github.com/JuliusBrussee/finetune-caveman">cavegemma</a> <em>weights remember</em> </p>
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. Supports: Claude Code · OpenCode · Codex · GitHub Copilot · Augment Code · Cursor (query-only) · Gemini CLI (query-only) · Antigravity (query-only) · IBM Bob (query-only) - Persistent memory across sessions. Hooks capture what happened; the store keeps it. - Compressed at rest. Deterministic caveman grammar, round-trip-guaranteed expansion for humans. - Progressive MCP retrieval. `search`, `timeline`, `get_observations` — agents filter before fetching. - Hybrid search. SQLite FTS5 keyword + local vector index, combined with a tunable ranker. - Local by default. No network calls. Optional remote embedding providers via config. - Web viewer. Read-only UI at `http://localhost:37777` for browsing sessions in human-readable form. Token-protected: the worker generates a local bearer token on first start and injects it into the served page, so `cavemem viewer` still opens with zero friction while `/api/*` rejects requests without it. - Privacy-aware. `<private>...</private>` stripped at write boundary. Path globs exclude whole directories.
项目信息
| 项目 | 信息 |
|---|---|
| 项目名称 | JuliusBrussee/cavemem |
| Star 数 | 594 |
| Fork 数 | 52 |
| 编程语言 | TypeScript |
| 开源协议 | MIT |
| 创建时间 | 2026-04-18 |
| 最近更新 | 2026-07-03 |
| 主题标签 | ai、caveman、claude、claude-code、compress |
项目地址
GitHub 仓库：<https://github.com/JuliusBrussee/cavemem>
> 完整 URL：[https://github.com/JuliusBrussee/cavemem](https://github.com/JuliusBrussee/cavemem)
如需查看完整源码、安装命令、使用示例、API 文档，请直接访问上方项目地址。所有信息均以 GitHub 仓库为准。