PL

phasespace-labs/palinode

开发工具

本页由 AI 翻译,技术细节请以原文为准。 查看原文

46 stars 49 forks 质量 81 趋势 26MIT

AI代理和开发工具的内存基质。Git版本化,文件原生,MCP优先。

概览

代理内存正在变成一种商品。可审计的代理记忆则不是:Palinide是记忆层,记得的事实在这里表明人们对它的信念有多强烈,以及支持它的证据——每个事实都是git版本markdown文件中的一行,可读、可变、可归因于记录它的提交,错误时可还原。未标记的记忆是无标记的,绝不会被默默提升为事实。没有必须信任的黑盒向量存储。 你的代理内存是一个 markdown 文件文件夹。Palinode 用混合搜索索引它们,用大语言模型压缩,并通过 MCP 提供——所以同一内存可以在 Claude Code、Cursor、Windsurf、Zed、VS Code(Continue/Cline)以及其他兼容 MCP 的编辑器中工作。带上你自己的 Obsidian vault,或者把 Palinode 当作一个:palinode init ——obsidian /path/to/vault 架构完整 vault,包含图形默认值、每日笔记布线和 LLM 维护的维基合同。企业可以用管理和代码的方式来管理 AI 内存。

概述(AI 翻译)

可检查、可修正的项目内存,适用于跨会话、代理和工作树的重复工作。

上周,你们团队选择了SQLite作为缓存,因为它避免了运行 数据库。本周,一项更改的要求使 PostgreSQL 成为更好的选择。 没有决定及其理由,新的代理可能会重复旧方法。 使用 Palinode,你可以保存替换文件,检查原始文件及其历史, 并为下一次会议纠正记录。

Palinode 在 Markdown 文件中保存项目内存,并将 Git 历史记录保存在本地 控制。代理可以利用其工具保存、搜索和检查这些内存。 部分支持的客户端集成还支持执行配置化的捕获或回忆; 它们的自动行为、范围和控制因客户端和配置而异。 没有任何东西会被无声地从无标记的便条提升为事实。

帕利诺德是收回之前说过的话,表达得更好。这就是记忆压缩的效果。

由 Phasespace-labs 的 Paul Kyle 制作。参见作者。


从这里开始

请遵循经典的快速入门,完成一段完整的旅程: 安装→启动→连接MCP客户端→保存决策→开启新会话

本页由 AI 翻译,技术细节请以原文为准。

README

以下为原文 README 节选,完整内容请查看原文。

┌─ palinode ─┐
│ ░░░░░░░░░░ │
│ ▓▓▓▓▓▓▓▓▓▓ │
│ ██████████ │
└────────────┘

Inspectable, correctable project memory for repeated work across sessions, agents, and worktrees.

Last week, your team chose SQLite for a cache because it avoided operating a database. This week, a changed requirement makes PostgreSQL the better choice. Without the decision and its reason, a fresh agent can repeat the old approach. With Palinode, you can save the replacement, inspect the original and its history, and correct the record for the next session.

Palinode keeps project memory in Markdown files and Git history under your local control. An agent can use its tools to save, search, and inspect that memory. Some supported client integrations can also perform configured capture or recall; their automatic behavior, scope, and controls vary by client and configuration. Nothing is silently promoted from an unmarked note to a fact.

A palinode is a poem that retracts what was said before and says it better. That’s what memory compaction does.

Built by Paul Kyle at phasespace-labs. See AUTHORS.


Start here

Follow the canonical Quickstart for one complete journey: install → start → connect an MCP client → save a decision → open a fresh session → inspect its markdown/provenance → correct it. It keeps the private memory store separate from the code checkout and distinguishes the current release from source-checkout capabilities.

Inspect the retired decision

The screenshot shows the archived initial SQLite decision after the separate PostgreSQL replacement was saved and the original was retired. See the local provenance UI guide for the full read-only inspector and the correction lifecycle; the guide explains that the image is taken after retirement, not before the save steps.


Supported Platforms

Platform Session Skill Path MCP Config
Claude Code CLI ~/.claude/skills/ ~/.claude.json
Claude Desktop ~/.claude/skills/ claude_desktop_config.json
Cursor .cursor/skills/ .cursor/mcp.json
VS Code + Claude (Continue / Cline) ~/.claude/skills/ see MCP-INSTALL-RECIPES.md
JetBrains + Claude ~/.claude/skills/ ~/.claude.json
Antigravity IDE .agent/skills/ native 3-dot MCP menu
Codex CLI N/A (no skills) ~/.codex/config.toml
Pi N/A (native extension) plugins/pi/ — per-turn recall via lifecycle hooks
在 GitHub 查看完整 README

安装

This server does not publish a one-line install command.

Open the repository installation guide 新手?先看 mcpskill.org 教程 →

配置

{ "mcpServers": { "palinode": { "type": "http", "url": "http://your-server:6341/mcp/" } } }