Local-first MCP tools: workflow routing/spec + keyword memory (JSON) with optional toggles.
Project description
MCP tools (workflow + memory)
本目录提供一个 单进程 的 Python MCP server,默认启用两组能力:
workflow.*: 生成最小化 spec(lite/spike/heavy)memory.*: 个人记忆(JSON 存储,关键词+tags+key 命名空间检索;无向量数据库/无 embedding)
MCP server 名称:agent-supervisor-memory(见 mcp-tools/agent-supervisor-memory/server.py)。
Quickstart
cd mcp-tools/agent-supervisor-memory
poetry env use python
poetry install
poetry run agent-supervisor-memory
默认存储文件(安装后):~/.local/share/agent-supervisor-memory/memory.json(可用 MCP_MEMORY_PATH 覆盖)。
默认策略文件(安装后):~/.config/agent-supervisor-memory/agent-policy.json(可用 MCP_AGENT_POLICY_PATH 覆盖)。
说明:Poetry 会统一管理虚拟环境与依赖,避免你本机 shell 的 python/pip alias 干扰。
如何引用(MCP client 注册)
不同 MCP client 的配置方式不同,但核心信息通常是:
command:agent-supervisor-memoryargs:[]
工具名引用方式是 tool name,例如:memory.search、workflow.route。
参考配置片段(TOML 风格)
如果你的 client 支持类似下面这种配置(你贴的 exa 例子就是这种风格),可以这样写:
[mcp_servers.codex_tools]
command = "agent-supervisor-memory"
args = []
建议同时设置工作目录到仓库根目录(不同 client 字段名可能是 cwd/workdir/root),并按需加环境变量:
[mcp_servers.codex_tools]
command = "agent-supervisor-memory"
args = []
# cwd = "/path/to/k3s-test"
# env = { MCP_MEMORY_ENABLED = "true", MCP_SUBAGENTS_ENABLED = "true" }
安装方式(发布后)
- 推荐:
pipx install agent-supervisor-memory,MCP client 用command="agent-supervisor-memory". - 零安装:
uvx agent-supervisor-memory,MCP client 用command="uvx" args=["agent-supervisor-memory"].
配置
环境变量(均为可选):
MCP_MEMORY_ENABLED:默认trueMCP_SUBAGENTS_ENABLED:默认true(当前仅暴露示例subagents.echo,便于后续扩展)MCP_MEMORY_PATH:默认~/.local/share/agent-supervisor-memory/memory.jsonMCP_MEMORY_MAX_ITEMS:默认500MCP_MEMORY_MAX_BYTES:默认2000000(约 2MB)MCP_AGENT_POLICY_PATH:默认~/.config/agent-supervisor-memory/agent-policy.json
每次 tool 调用也可传:
options.enable_memory:true|falseoptions.enable_subagents:true|false
模型与模式(跨模型路由)
本 server 不直接调用模型;它只提供“建议路由”,由你的 Supervisor/Client 负责真正使用什么模型去执行。
policy.get: 读取.codex/agent-policy.jsonworkflow.route: 根据任务文本 +mode/effort/auto给出建议的supervisor_model/coder_model/effort
默认配置:
- Supervisor:
codex-5.2 - Coder:
codex-5.1-codex-max saving:默认effort=mediumefficient:默认effort=medium
Tools
capabilities.getpolicy.getmemory.putmemory.searchmemory.deleteworkflow.ensure_specworkflow.routesubagents.echo(示例)
Project details
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 agent_supervisor_memory-0.1.0.tar.gz.
File metadata
- Download URL: agent_supervisor_memory-0.1.0.tar.gz
- Upload date:
- Size: 8.2 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: poetry/2.2.1 CPython/3.14.2 Darwin/24.6.0
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
fb40fadf2c7b07b4bc2d7f59e1a93c578249f29ba8ccaf3dd7fcbac032e7ad55
|
|
| MD5 |
4d64d6d2e5318c4b4e7a325f1748aa3c
|
|
| BLAKE2b-256 |
60f43d408f973ebc323f2737fb0d8895fbacc147894bb600866e6a0d54b305fd
|
File details
Details for the file agent_supervisor_memory-0.1.0-py3-none-any.whl.
File metadata
- Download URL: agent_supervisor_memory-0.1.0-py3-none-any.whl
- Upload date:
- Size: 11.2 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: poetry/2.2.1 CPython/3.14.2 Darwin/24.6.0
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
ec1ba47c80574d32c738b71b4928a02176961e135c69747e9de08517e8a2b8fa
|
|
| MD5 |
b7328b6ebd6cb8f54e188a985e3d1845
|
|
| BLAKE2b-256 |
4d97e91f2815f58c17dbd34e34002f7143ae466df5e9213762a8cc0d3e9c7c4c
|