loom-mcp
AI 编程的肌肉记忆 —— 一个持续学习的代码组装 MCP server。
把你写过的代码自动收录为可复用组件，下次碰到类似需求，AI 直接从你自己的组件库里挑着用，越用越强。
安装
需要 uv。在 Claude Code / Cursor 等 MCP agent 里配：
// .mcp.json
{ "mcpServers": { "loom": { "command": "uvx", "args": ["loom-mcp"] } } }
或：claude mcp add loom -- uvx loom-mcp
首次运行自动在 ~/.loom/ 初始化个人组件库（内置种子候选）。
工具
loom_propose(idea_json)— 对想法返回每个能力 seam 的 2-3 个候选 + 架构取舍loom_plan_from_choices(idea_json, choices_json)— 选择 → 装配计划loom_get_files(plan_json)— 物化成完整 create-t3-app 项目文件loom_ingest(paths, seam_hint?, description?)— 收录你写的代码进组件库
工作流
说想法 → propose 给候选梯度（agent 帮你挑，不确定才问）→ get_files 返回完整项目
→ 写盘 + pnpm install + 填 .env + pnpm dev。写完新代码 loom_ingest 收录，越用越强。
全程本地、零网络、零 key（检索/物化不调 LLM）。信任飞轮：常用的候选浮顶，久不用的沉底。
详见 项目主页。
许可
MIT
1 maintainer
Metadata
1 maintainer
Release files for loom-memory-mcp 0.2.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| loom_memory_mcp-0.2.1.tar.gz | 209.8 kB | Without provenance | Details for loom_memory_mcp-0.2.1.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| loom_memory_mcp-0.2.1-py3-none-any.whl | Python 3 | none | any | Details for loom_memory_mcp-0.2.1-py3-none-any.whl |
Total release size: 450.5 kB
Release files / loom_memory_mcp-0.2.1.tar.gz
| Download URL | loom_memory_mcp-0.2.1.tar.gz |
|---|---|
| Size | 209.8 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
e062364150b417f31865d5b52334590e7b7469fc3e5ef23ded165e5b41179907
|
|
BLAKE2b-256 checksum How to use checksums |
50973e7cdb29dc9dc7bd2347e006b7c24a1fea78ae07e58e4abb7330864ba7d5
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.12.13
|
Release files / loom_memory_mcp-0.2.1-py3-none-any.whl
| Download URL | loom_memory_mcp-0.2.1-py3-none-any.whl |
|---|---|
| Size | 240.7 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
0c6e13494cf6d104f2f0e696ea6837a1e1396334898c59b40a1c73fb155ed852
|
|
BLAKE2b-256 checksum How to use checksums |
b30858bdb3e16245ea45cd4c044f1d9b47af14af96bff72f878957e52ea0fe68
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.12.13
|
Security for loom-memory-mcp 0.2.1
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.
