Filesystem As Remote Memory - Agent memory storage system
Project description
FARM - Filesystem As Remote Memory
为 AI Agent 设计的持久化记忆系统。让 Agent 能够跨会话记住重要信息，并通过语义搜索快速检索。
核心功能
- 记忆存储: 保存对话摘要、用户偏好、学习到的知识
- 语义搜索: 基于 ChromaDB 向量搜索，用自然语言查询相关记忆
- 多接口: MCP Server (Claude)、REST API、CLI
快速开始
# 安装
uv sync
# 初始化存储
uv run farm init
# 添加记忆
uv run farm add "用户偏好 Vue 框架" --tag preference
# 搜索记忆
uv run farm search "前端框架" --semantic
# 启动 API 服务
uv run farm serve
Claude 集成
添加到 Claude 配置 (~/.claude.json):
{
"mcpServers": {
"farm": {
"command": "uv",
"args": ["run", "--directory", "/path/to/farm", "farm", "mcp"]
}
}
}
文档
License
MIT
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file farm_memory-0.1.0.tar.gz.
File metadata
- Download URL: farm_memory-0.1.0.tar.gz
- Upload date:
- Size: 142.8 kB
- Tags: Source
- Uploaded using Trusted Publishing? Yes
- Uploaded via: twine/6.1.0 CPython/3.13.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
7532607ee061d70e70c7e37a1fa4f47b5df2ee058d94a689cd6f36471ea2507e
|
|
| MD5 |
7abab7d72761450d98da64d9676b3e18
|
|
| BLAKE2b-256 |
34f45f7782b7416270d21b67cac20e2310466e871d8a4d8dc8b97154f7cc38c4
|
Provenance
The following attestation bundles were made for farm_memory-0.1.0.tar.gz:
Publisher:
release.yml on mmga-lab/farm
-
Statement:
-
Statement type:
https://in-toto.io/Statement/v1 -
Predicate type:
https://docs.pypi.org/attestations/publish/v1 -
Subject name:
farm_memory-0.1.0.tar.gz -
Subject digest:
7532607ee061d70e70c7e37a1fa4f47b5df2ee058d94a689cd6f36471ea2507e - Sigstore transparency entry: 832759228
- Sigstore integration time:
-
Permalink:
mmga-lab/farm@14f36a5f024e74b34116259320a143e1a4269e8c -
Branch / Tag:
refs/tags/v0.1.0 - Owner: https://github.com/mmga-lab
-
Access:
public
-
Token Issuer:
https://token.actions.githubusercontent.com -
Runner Environment:
github-hosted -
Publication workflow:
release.yml@14f36a5f024e74b34116259320a143e1a4269e8c -
Trigger Event:
push
-
Statement type:
File details
Details for the file farm_memory-0.1.0-py3-none-any.whl.
File metadata
- Download URL: farm_memory-0.1.0-py3-none-any.whl
- Upload date:
- Size: 17.0 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? Yes
- Uploaded via: twine/6.1.0 CPython/3.13.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
edea5606a922cd9f45f8b30b17eddfa0727aa7e9a8a2bf367323e435cb4acc42
|
|
| MD5 |
b7bc6cb1e70ba0367f6902cf2531c2f7
|
|
| BLAKE2b-256 |
a95d6f44f77244b9fac6326ee1c95f87f2b8608d4c82aef7b8f92223d016b698
|
Provenance
The following attestation bundles were made for farm_memory-0.1.0-py3-none-any.whl:
Publisher:
release.yml on mmga-lab/farm
-
Statement:
-
Statement type:
https://in-toto.io/Statement/v1 -
Predicate type:
https://docs.pypi.org/attestations/publish/v1 -
Subject name:
farm_memory-0.1.0-py3-none-any.whl -
Subject digest:
edea5606a922cd9f45f8b30b17eddfa0727aa7e9a8a2bf367323e435cb4acc42 - Sigstore transparency entry: 832759230
- Sigstore integration time:
-
Permalink:
mmga-lab/farm@14f36a5f024e74b34116259320a143e1a4269e8c -
Branch / Tag:
refs/tags/v0.1.0 - Owner: https://github.com/mmga-lab
-
Access:
public
-
Token Issuer:
https://token.actions.githubusercontent.com -
Runner Environment:
github-hosted -
Publication workflow:
release.yml@14f36a5f024e74b34116259320a143e1a4269e8c -
Trigger Event:
push
-
Statement type:
