by zilliztech · Codex 技能 · ★ 2.8k
memsearch Cross-platform semantic memory for AI coding agents. Why memsearch? 🌐 All Platforms, One Memory — memories flow across Claude Code, OpenClaw, OpenCode, and Codex CLI. A conversation in one agent becomes searchable context in all others — no extra setup 👥 For Agent Users, install a plugin and get persistent memory with zero effort; for Agent Developers, use the full CLI and Python API to build memory and harness engineering into your own agents 📄 Markdown is the source of truth — inspired by OpenClaw.
| Stars | 2,762 |
| Forks | 268 |
| Language | Python |
| Category | Codex 技能 |
| License | MIT |
| Quality Score | 64.1861151149996/100 |
| Open Issues | 273 |
| Last Updated | 2026-10-19 |
| Created | 2026-02-09 |
| Platforms | claude-code, codex, python |
| Est. Tokens | ~18k |
Explore other popular codex 技能 tools:
memsearch is A persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex, DSH), backed by Markdown and Milvus.. It is categorized as a Codex 技能 with 2.8k GitHub stars.
memsearch is primarily written in Python. It covers topics such as agent, agent-memory, claude-code.
You can find installation instructions and usage details in the memsearch GitHub repository at github.com/zilliztech/memsearch. The project has 2.8k stars and 268 forks, indicating an active community.
memsearch is released under the MIT license, making it free to use and modify according to the license terms.