Thanks to visit codestin.com
Credit goes to github.com

Skip to content

[自荐] TMF:记录代码链路理解,识别 AI 编程中的过期源码上下文 #1084

Description

@kyle641320

我是项目方,本次为自荐。安装与试用指南:https://github.com/kyle641320/true-memory-fragments/blob/master/docs/early-preview.md

rc4 试用入口(2026-09-13 更新)

现已发布 PyPI rc4,并登记至官方 MCP Registry。目录登记不代表平台对效果的背书。

安装 uv 后,可用下面的命令启动;将路径替换为当前任务的 Git 工作树绝对路径:

uvx --from 'true-memory-fragments[java]==0.1.0rc4' tmf mcp --repo /absolute/path/to/task-worktree

首次使用先确认 tmf_status.repo,再通过 tmf_warm 建立索引。代码变化后查询旧绑定,按 stale 提示实际重读当前源码,再继续开发。发布包与校验值

Activity

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions