Skip to main content

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-memory
  • args: []

工具名引用方式是 tool name,例如:memory.searchworkflow.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 true
  • MCP_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.json
  • MCP_MEMORY_MAX_ITEMS:默认 500
  • MCP_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|false
  • options.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.json
  • workflow.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=medium
  • efficient:默认 effort=medium

Tools

  • capabilities.get
  • policy.get
  • memory.put
  • memory.search
  • memory.delete
  • workflow.ensure_spec
  • workflow.route
  • subagents.echo(示例)

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

agent_supervisor_memory-0.1.0.tar.gz (8.2 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

agent_supervisor_memory-0.1.0-py3-none-any.whl (11.2 kB view details)

Uploaded Python 3

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

Hashes for agent_supervisor_memory-0.1.0.tar.gz
Algorithm Hash digest
SHA256 fb40fadf2c7b07b4bc2d7f59e1a93c578249f29ba8ccaf3dd7fcbac032e7ad55
MD5 4d64d6d2e5318c4b4e7a325f1748aa3c
BLAKE2b-256 60f43d408f973ebc323f2737fb0d8895fbacc147894bb600866e6a0d54b305fd

See more details on using hashes here.

File details

Details for the file agent_supervisor_memory-0.1.0-py3-none-any.whl.

File metadata

File hashes

Hashes for agent_supervisor_memory-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 ec1ba47c80574d32c738b71b4928a02176961e135c69747e9de08517e8a2b8fa
MD5 b7328b6ebd6cb8f54e188a985e3d1845
BLAKE2b-256 4d97e91f2815f58c17dbd34e34002f7143ae466df5e9213762a8cc0d3e9c7c4c

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page