de en es ja ko ru zh

Perenna

Name: Perenna
Author: scarletkc

by scarletkc

Overview Schema Source Related Servers Discussions Admin

Python

Hybrid

Perenna

Python PyPI Codecov CodeRabbit Pull Request Reviews License Ask DeepWiki

perenna MCP server

轻量级、基于 Git 的 AI 代理持久记忆。Claude Code、Codex、ChatGPT、Cursor 及其他 MCP 客户端可以共享持久记忆，无需共享同一个供应商账户或彼此的对话历史。

独立的 MCP 工具用于读取、写入和删除记忆
本地 stdio 与受 OAuth 保护的单用户 Streamable HTTP 传输
人类可读的 Markdown，存储于独立的 Git 仓库
本地 Vexor 检索索引，随时可从 Git 重建
跨进程锁定，供多个本地代理进程使用

为什么选择 Perenna？

你的记忆应该跟随你，而不是你碰巧使用的某个代理。

Claude Code、Codex、Cursor 和 ChatGPT 把记忆存留在各自的信息孤岛中。切换代理，你的记忆就会消失；切换机器，本地记忆也留在了原来的地方。

Perenna 为它们提供一份共享的 Git-backed 记忆。本地代理和 ChatGPT 可以接入同一个自托管的 Perenna 服务，而每一条持久记忆仍然保持为普通 Markdown，你可以自行检视、编辑、版本管理并备份。

Mem0 的自托管全栈明显更重，而其托管的免费计划目前允许将客户内容用于模型训练和产品改进。

Perenna 的设计与众不同：无需账户、不依赖专有记忆云、不受锁定。只有你的记忆，在你的 Git 仓库里，运行在你掌控的基础设施上。

Related MCP server: Hypermnesic

快速入门

随你的 AI 代理一同安装

将以下内容粘贴到 Claude Code、Codex、ChatGPT Desktop、Cursor 或另一个能够访问终端和本地 MCP 配置的编码代理中：

Install Perenna and connect it to this AI agent as a local stdio MCP server.
Work through the complete setup autonomously.

Use these as the source of truth:
- https://github.com/scarletkc/Perenna/blob/main/docs/getting-started.md
- https://github.com/scarletkc/Perenna/blob/main/docs/guides/client-setup.md

1. Detect the operating system, shell, and current MCP client.
2. Check for Python 3.12 or newer, Git, and uv. Install uv in user scope if it
   is missing. If Python or Git needs administrator approval, give me the exact
   command and stop there.
3. Install Perenna with `uv tool install perenna`. If Perenna is already
   installed, upgrade it with `uv tool upgrade perenna`.
   For Codex, also run `perenna skill install --agent codex`. For Claude Code,
   run `perenna skill install --agent claude-code`. Do not replace an existing
   modified copy or remove unrelated installed skills.
4. Check the effective Vexor embedding provider configuration. Reuse a working
   `~/.vexor/config.json` or inherited environment configuration. If none is
   available, ask me to choose between a remote provider and local embeddings.
   Explain that a remote provider receives memory text and search queries. For
   a remote provider, keep the provider and model in Vexor configuration and
   supply its secret through `VEXOR_API_KEY` or the provider-specific environment
   variable. For local embeddings, install `perenna[local]` and configure the
   local model according to the Perenna configuration reference. Verify the
   selected provider with `uvx vexor doctor` using the same environment that
   the Perenna process will inherit.
5. Ask whether I want to synchronize Perenna with a private Git repository. If
   I do, ask me to provide or approve its URL, run
   `perenna sync setup <repository-url>`, and verify it with
   `perenna sync status`. Treat repository creation, remote replacement, and
   reconciling diverged history as separate choices that require my explicit
   approval.
6. Register `perenna mcp --source <stable-client-name>` using the client-specific
   method in the setup guide. Preserve unrelated MCP servers and settings. Use
   a stable source such as `claude-code`, `codex`, or `cursor` for this client.
   For another client, use its official instructions for adding a local stdio
   MCP server. Make sure the Perenna process inherits `VEXOR_CONFIG_JSON`,
   `VEXOR_API_KEY`, or any provider-specific key used in step 4. Report only
   whether a secret is present.
7. Verify `perenna --help` and the saved MCP configuration. Reload MCP servers
   and call `memory_read` with `action: "list"` when the client supports it. If
   a restart is required, tell me the single restart step.
8. Report the commands run, files changed, and verification results. Keep API
   keys out of tracked configuration files.

安装已发布版本

Perenna 需要 Python 3.12+、Git 和 uv。

uv tool install perenna

为本地客户端安装可选的内存行为技能：

perenna skill install --agent codex
# or
perenna skill install --agent claude-code

当两个客户端都应收到该技能时，在一条命令中重复 --agent。的配置参考说明了用户范围与项目范围、目标位置以及替换这门技能时的保护措施。

Codex 和 Claude Code 也可以改用 Perenna 的存储库 Marketplace 中捆绑安装的 Skill 与 MCP 连接。请按照插件设置指南操作，并为每个客户端选择一种设置路径。

Perrena 需要可用的 Vexor 嵌入模型提供程序。如需交互式选择并配置提供程序，请运行：

uvx vexor init

Perenna 会自动复用 ~/.vexor/config.json。如果使用进程级配置，请确保 MCP 服务器从宿主机环境中获得 VEXOR_CONFIG_JSON 以及 VEXOR_API_KEY 或所选提供程序的 API 密钥。远程提供程序会收到记忆文本和搜索查询。

如果你选择本地嵌入，请同时安装 Perenna 的本地扩展：

uv tool install "perenna[local]"

Vexor 提供程序配置覆盖了远程和本地设置。在启动 MCP 客户端的环境中，验证已选定的提供程序：

uvx vexor doctor

要配置一个 MCP 客户端并启动：

perenna mcp --source <client-name>

Per lore in its local data under ~/.perenna/；除非配置了其他 home 目录，否则默认创建于此。

要通过一个私有 Git 仓库导入、发布或执行快进兼容的历史，请运行：

perenna sync setup <repository-url>

从源码安装以进行开发

git clone https://github.com/scarletkc/Perenna.git
cd Perenna
uv tool install .

文档

请先浏览文档索引，再根据你的任务选择对应路径：

License

MIT

Available Tools

3 tools

memory_deleteA

Destructive

Delete exactly one committed memory by ID, expected title, and revision. The deletion removes it from current recall but remains recoverable from Git history.

ParametersJSON Schema

Name	Required	Description	Default
`memory_id`	Yes
`base_revision`	Yes
`expected_title`	Yes

Output Schema

ParametersJSON Schema

Name	Required	Description
`action`	Yes
`commit`	Yes
`memory`	Yes
`changed`	Yes
`sync_status`	Yes
`index_status`	Yes
`recoverable_via_git`	Yes

TDQS

A3.5/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare destructiveHint=true and idempotentHint=false. The description adds valuable non-obvious context: the deletion removes from recall but remains recoverable via Git history, and it deletes 'exactly one' memory. This goes beyond the annotations without contradicting them. It does not mention side effects like concurrency checks, but the added recoverability and scoping are meaningful.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is one compact sentence that leads with the action and core constraints, then adds the recoverability detail. There is no fluff or repetition; every word earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a destructive operation with three required parameters and an output schema, the description is thin. It omits behavior on mismatch (e.g., if expected_title or base_revision does not match), error semantics, or any guidance on when this tool should be chosen over siblings. The recoverability note is helpful (something the output schema won't reveal), but other important context is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. However, it only mentions parameters as 'ID, expected title, and revision' without explaining their purpose, format, or how they are used (e.g., what an expected title is for, what a base revision means, or how they act as safety checks). No examples or constraints are provided, leaving agents to infer semantics from names alone.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb ('Delete'), resource ('one committed memory'), and identifies the parameters by role (ID, expected title, revision). It clearly distinguishes from siblings memory_read and memory_write by the action it performs.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description does not provide explicit guidance on when to use this tool versus alternatives. It only implies deletion use case without mentioning conditions, prerequisites, or exclusions (e.g., 'use memory_read to view' or 'use memory_write to create'). No context is given for when a deletion is appropriate.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

memory_readA

Read-onlyIdempotent

Read permanent memory. List returns stable memory IDs and titles, search returns bounded ranked candidate passages, and get returns one complete committed memory with its revision.

ParametersJSON Schema

Name	Required	Description	Default
No parameters

Output Schema

ParametersJSON Schema

Name	Required	Description
No output parameters

TDQS

A4.3/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover read-only, non-destructive, idempotent, and open-world behavior. The description adds useful context beyond annotations: search results are 'bounded ranked candidate passages,' list returns only IDs/titles, and get returns a 'complete committed memory with its revision.' No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence that front-loads the core purpose and uses parallel clauses to describe each action without redundancy or filler. It is compact yet informative.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's three modes and the existence of an output schema, the description is complete: it explains the behavior of each action and what kind of result to expect. Annotations cover safety and side-effect concerns, and sibling names make the read/write/delete division clear.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema fully documents the action variants, required fields, and limit bounds through its oneOf structure and const values. The description does not add parameter-level detail such as query format or memory_id semantics, but with schema coverage effectively complete, the baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource ('Read permanent memory') and enumerates three distinct modes—list, search, get—with their concrete outcomes. This distinguishes the tool from memory_write and memory_delete without relying on the name alone.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description tells an agent what each mode returns, which is clear guidance for choosing list vs search vs get. It does not explicitly say 'use this instead of memory_write or memory_delete,' but 'Read' and the sibling names make the intended usage obvious.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

memory_writeA

Destructive

Create or modify permanent memory. Summary is a stable one-line description of what a memory covers. Patch applies exact all-or-nothing edits; replace overwrites the complete summary and body. Existing memories require a current base revision.

ParametersJSON Schema

Name	Required	Description	Default
No parameters

Output Schema

ParametersJSON Schema

Name	Required	Description
`action`	Yes
`commit`	Yes
`memory`	Yes
`changed`	Yes
`sync_status`	Yes
`index_status`	Yes

TDQS

A4.2/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the annotations (destructiveHint=true, readOnlyHint=false), the description discloses valuable behavioral details: patch is all-or-nothing, replace overwrites the complete summary/body, and existing memories require a current base revision, implying optimistic concurrency. This does not contradict any annotation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is three dense sentences with no filler. The purpose is front-loaded, and each sentence addresses a distinct aspect: overall behavior, summary semantics, and modifications semantics.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers the key operational facts an agent needs: the three modes, the summary convention, patch atomicity, and the base-revision requirement. Since an output schema exists, return-value details are not needed here. A minor gap is not pointing agents to memory_read to retrieve the current base revision.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description adds meaning beyond the schema by defining summary as a 'stable one-line description', explaining the exact semantics of patch and replace, and mentioning the base revision requirement. This is useful context that the bare schema types do not convey, though title and project are left to the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific action ('Create or modify') on a clear resource ('permanent memory') and further differentiates the three operational modes: create, patch, and replace. This makes the tool unmistakably the write counterpart to memory_read and memory_delete.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides internal guidance on when to use patch vs replace and notes the base-revision prerequisite for modifying existing memories. However, it does not explicitly mention memory_read or memory_delete or state when to prefer this tool over those siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

2 tool updatesv0.1.1Aug 29, 2026

Changedmemory_read5 fields changed

removedInput schema / additionalProperties
```
Removed value: -false
```

addedInput schema / oneOf

Added value: +[
+  {
+    "additionalProperties": false,
+    "properties": {
+      "action": {
+        "const": "list"
+      },
+      "project": {
+        "type": "string"
+      }
+    },
+    "required": [
+      "action"
+    ],
+    "type": "object"
+  },
+  {
+    "additionalProperties": false,
+    "properties": {
+      "action": {
+        "const": "search"
+      },
+      "limit": {
+        "maximum": 5,
+        "minimum": 1,
+        "type": "integer"
+      },
+      "project": {
+        "type": "string"
+      },
+      "query": {
+        "type": "string"
+      }
+    },
+    "required": [
+      "action",
+      "query"
+    ],
+    "type": "object"
+  },
+  {
+    "additionalProperties": false,
+    "properties": {
+      "action": {
+        "const": "get"
+      },
+      "memory_id": {
+        "type": "string"
+      }
+    },
+    "required": [
+      "action",
+      "memory_id"
+    ],
+    "type": "object"
+  }
+]

removedInput schema / properties

Removed value: -{
-  "action": {
-    "enum": [
-      "list",
-      "search",
-      "get"
-    ],
-    "type": "string"
-  },
-  "limit": {
-    "maximum": 5,
-    "minimum": 1,
-    "type": "integer"
-  },
-  "memory_id": {
-    "type": "string"
-  },
-  "project": {
-    "type": "string"
-  },
-  "query": {
-    "type": "string"
-  }
-}

removedInput schema / required
```
Removed value: -[
-  "action"
-]
```

changedOutput schema / oneOf

Previous value: -[
-  {
-    "additionalProperties": false,
-    "properties": {
-      "action": {
-        "const": "list"
-      },
-      "memories": {
-        "items": {
-          "additionalProperties": false,
-          "properties": {
-            "memory_id": {
-              "type": "string"
-            },
-            "scope": {
-              "type": "string"
-            },
-            "summary": {
-              "type": "string"
-            },
-            "title": {
-              "type": "string"
-            }
-          },
-          "required": [
-            "memory_id",
-            "title",
-            "scope",
-            "summary"
-          ],
-          "type": "object"
-        },
-        "type": "array"
-      },
-      "project": {
-        "type": [
-          "string",
-          "null"
-        ]
-      },
-      "projects": {
-        "items": {
-          "type": "string"
-        },
-        "type": "array"
-      }
-    },
-    "required": [
-      "action",
-      "project",
-      "memories",
-      "projects"
-    ],
-    "type": "object"
-  },
-  {
-    "additionalProperties": false,
-    "properties": {
-      "action": {
-        "const": "search"
-      },
-      "limit": {
-        "maximum": 5,
-        "minimum": 1,
-        "type": "integer"
-      },
-      "matches": {
-        "items": {
-          "additionalProperties": false,
-          "properties": {
-            "memory_id": {
-              "type": "string"
-            },
-            "passages": {
-              "items": {
-                "additionalProperties": false,
-                "properties": {
-                  "end_char": {
-                    "minimum": 1,
-                    "type": "integer"
-                  },
-                  "start_char": {
-                    "minimum": 0,
-                    "type": "integer"
-                  },
-                  "text": {
-                    "type": "string"
-                  }
-                },
-                "required": [
-                  "text",
-                  "start_char",
-                  "end_char"
-                ],
-                "type": "object"
-              },
-              "minItems": 1,
-              "type": "array"
-            },
-            "rank": {
-              "minimum": 1,
-              "type": "integer"
-            },
-            "revision": {
-              "type": "string"
-            },
-            "scope": {
-              "type": "string"
-            },
-            "summary": {
-              "type": "string"
-            },
-            "title": {
-              "type": "string"
-            }
-          },
-          "required": [
-            "memory_id",
-            "title",
-            "scope",
-            "summary",
-            "revision",
-            "rank",
-            "passages"
-          ],
-          "type": "object"
-        },
-        "type": "array"
-      },
-      "project": {
-        "type": [
-          "string",
-          "null"
-        ]
-      },
-      "truncated": {
-        "type": "boolean"
-      }
-    },
-    "required": [
-      "action",
-      "project",
-      "limit",
-      "matches",
-      "truncated"
-    ],
-    "type": "object"
-  },
-  {
-    "additionalProperties": false,
-    "properties": {
-      "action": {
-        "const": "get"
-      },
-      "memory": {
-        "additionalProperties": false,
-        "properties": {
-          "body": {
-            "type": "string"
-          },
-          "created_at": {
-            "type": "string"
-          },
-          "memory_id": {
-            "type": "string"
-          },
-          "revision": {
-            "type": "string"
-          },
-          "scope": {
-            "type": "string"
-          },
-          "source": {
-            "type": "string"
-          },
-          "summary": {
-            "type": "string"
-          },
-          "title": {
-            "type": "string"
-          },
-          "updated_at": {
-            "type": "string"
-          }
-        },
-        "required": [
-          "memory_id",
-          "title",
-          "scope",
-          "summary",
-          "source",
-          "created_at",
-          "updated_at",
-          "revision",
-          "body"
-        ],
-        "type": "object"
-      }
-    },
-    "required": [
-      "action",
-      "memory"
-    ],
-    "type": "object"
-  }
-]New value: +[
+  {
+    "additionalProperties": false,
+    "properties": {
+      "action": {
+        "const": "list"
+      },
+      "memories": {
+        "items": {
+          "additionalProperties": false,
+          "properties": {
+            "memory_id": {
+              "type": "string"
+            },
+            "scope": {
+              "type": "string"
+            },
+            "summary": {
+              "type": "string"
+            },
+            "title": {
+              "type": "string"
+            }
+          },
+          "required": [
+            "memory_id",
+            "title",
+            "scope",
+            "summary"
+          ],
+          "type": "object"
+        },
+        "type": "array"
+      },
+      "project": {
+        "type": [
+          "string",
+          "null"
+        ]
+      },
+      "projects": {
+        "items": {
+          "type": "string"
+        },
+        "type": "array"
+      }
+    },
+    "required": [
+      "action",
+      "project",
+      "memories",
+      "projects"
+    ],
+    "type": "object"
+  },
+  {
+    "additionalProperties": false,
+    "properties": {
+      "action": {
+        "const": "search"
+      },
+      "limit": {
+        "maximum": 5,
+        "minimum": 1,
+        "type": "integer"
+      },
+      "matches": {
+        "items": {
+          "additionalProperties": false,
+          "properties": {
+            "memory_id": {
+              "type": "string"
+            },
+            "passages": {
+              "items": {
+                "additionalProperties": false,
+                "properties": {
+                  "end_char": {
+                    "minimum": 1,
+                    "type": "integer"
+                  },
+                  "start_char": {
+                    "minimum": 0,
+                    "type": "integer"
+                  },
+                  "text": {
+                    "type": "string"
+                  }
+                },
+                "required": [
+                  "text",
+                  "start_char",
+                  "end_char"
+                ],
+                "type": "object"
+              },
+              "minItems": 1,
+              "type": "array"
+            },
+            "rank": {
+              "minimum": 1,
+              "type": "integer"
+            },
+            "revision": {
+              "type": "string"
+            },
+            "scope": {
+              "type": "string"
+            },
+            "summary": {
+              "type": "string"
+            },
+            "title": {
+              "type": "string"
+            }
+          },
+          "required": [
+            "memory_id",
+            "title",
+            "scope",
+            "summary",
+            "revision",
+            "rank",
+            "passages"
+          ],
+          "type": "object"
+        },
+        "type": "array"
+      },
+      "project": {
+        "type": [
+          "string",
+          "null"
+        ]
+      },
+      "truncated": {
+        "type": "boolean"
+      }
+    },
+    "required": [
+      "action",
+      "project",
+      "limit",
+      "matches",
+      "truncated"
+    ],
+    "type": "object"
+  },
+  {
+    "additionalProperties": false,
+    "properties": {
+      "action": {
+        "const": "get"
+      },
+      "memory": {
+        "additionalProperties": false,
+        "properties": {
+          "body": {
+            "type": "string"
+          },
+          "created_at": {
+            "type": "string"
+          },
+          "memory_id": {
+            "type": "string"
+          },
+          "revision": {
+            "type": "string"
+          },
+          "scope": {
+            "type": "string"
+          },
+          "summary": {
+            "type": "string"
+          },
+          "title": {
+            "type": "string"
+          },
+          "updated_at": {
+            "type": "string"
+          }
+        },
+        "required": [
+          "memory_id",
+          "title",
+          "scope",
+          "summary",
+          "created_at",
+          "updated_at",
+          "revision",
+          "body"
+        ],
+        "type": "object"
+      }
+    },
+    "required": [
+      "action",
+      "memory"
+    ],
+    "type": "object"
+  }
+]

Changedmemory_write4 fields changed

removedInput schema / additionalProperties
```
Removed value: -false
```

addedInput schema / oneOf

Added value: +[
+  {
+    "additionalProperties": false,
+    "properties": {
+      "action": {
+        "const": "create"
+      },
+      "body": {
+        "type": "string"
+      },
+      "project": {
+        "type": "string"
+      },
+      "summary": {
+        "type": "string"
+      },
+      "title": {
+        "type": "string"
+      }
+    },
+    "required": [
+      "action",
+      "title",
+      "summary",
+      "body"
+    ],
+    "type": "object"
+  },
+  {
+    "additionalProperties": false,
+    "properties": {
+      "action": {
+        "const": "patch"
+      },
+      "base_revision": {
+        "type": "string"
+      },
+      "edits": {
+        "items": {
+          "additionalProperties": false,
+          "properties": {
+            "new_text": {
+              "type": "string"
+            },
+            "old_text": {
+              "type": "string"
+            }
+          },
+          "required": [
+            "old_text",
+            "new_text"
+          ],
+          "type": "object"
+        },
+        "minItems": 1,
+        "type": "array"
+      },
+      "memory_id": {
+        "type": "string"
+      },
+      "summary": {
+        "type": "string"
+      }
+    },
+    "required": [
+      "action",
+      "memory_id",
+      "base_revision",
+      "edits"
+    ],
+    "type": "object"
+  },
+  {
+    "additionalProperties": false,
+    "properties": {
+      "action": {
+        "const": "replace"
+      },
+      "base_revision": {
+        "type": "string"
+      },
+      "body": {
+        "type": "string"
+      },
+      "memory_id": {
+        "type": "string"
+      },
+      "summary": {
+        "type": "string"
+      }
+    },
+    "required": [
+      "action",
+      "memory_id",
+      "base_revision",
+      "summary",
+      "body"
+    ],
+    "type": "object"
+  }
+]

removedInput schema / properties

Removed value: -{
-  "action": {
-    "enum": [
-      "create",
-      "patch",
-      "replace"
-    ],
-    "type": "string"
-  },
-  "base_revision": {
-    "type": "string"
-  },
-  "body": {
-    "type": "string"
-  },
-  "edits": {
-    "items": {
-      "additionalProperties": false,
-      "properties": {
-        "new_text": {
-          "type": "string"
-        },
-        "old_text": {
-          "type": "string"
-        }
-      },
-      "required": [
-        "old_text",
-        "new_text"
-      ],
-      "type": "object"
-    },
-    "minItems": 1,
-    "type": "array"
-  },
-  "memory_id": {
-    "type": "string"
-  },
-  "project": {
-    "type": "string"
-  },
-  "summary": {
-    "type": "string"
-  },
-  "title": {
-    "type": "string"
-  }
-}

removedInput schema / required
```
Removed value: -[
-  "action"
-]
```

3 tool updatesv0.1.0Aug 24, 2026
- First observedmemory_delete
- First observedmemory_read
- First observedmemory_write

Deploy Server

Context All Your Agents Can ShareAgents share what they learn, hand off work, and hold it when you switch models. Start with 5 GB free.fulcradynamics.comAd

TDQS

A4.2/5.0

Scored 2026-08-31 15:25 across 3 tools

Disambiguation5/5

Each tool handles a distinct lifecycle operation: reading/querying, writing/updating, and deleting memories. There is no overlap between the primary actions, and the sub-modes within memory_read are explicitly separated (list, search, get).

Naming Consistency5/5

All tool names follow the same memory_verb pattern using clear, lowercase snake_case verbs. The naming makes the operation type immediately obvious and perfectly consistent across the set.

Tool Count5/5

Three tools is a compact but complete surface for a permanent memory store. Each tool earns its place, and no redundant or extraneous operations exist.

Completeness5/5

The set covers the full lifecycle: create/modify via memory_write, read via memory_read (including list/search/get), and delete via memory_delete. Revision-handling and Git-history recovery details further round out the functionality, leaving no critical gaps.

Maintenance

ActivityMaintained

ResponsivenessUnresponsive

Resources

Need Help?

Related Servers

Related MCP Connectors

HexisOAuth
io.github.Bevel-Software
Git-backed platform for skills, tools, and context for AI agents
Agent Orchestration Developer Tools
193
agentbay-mcp AOAuth
io.github.thomasjumper
Persistent memory and knowledge management for AI agents with semantic search and 50+ tools.
Knowledge & Memory Autonomous Agents Agent Orchestration
21
goldhold
io.github.jerrysrodz
Persistent memory for AI agents. Search, store, and recall across sessions.
Knowledge & Memory Autonomous Agents RAG Systems
2
Penfield Memory AOAuth
io.github.penfieldlabs
Persistent memory and knowledge graphs for AI agents. Hybrid search, context checkpoints, and more.
Knowledge & Memory RAG Systems Vector Databases
1726

Related MCP Servers

MemoVofficial
Knowledge & Memory Version Control Developer Tools
memovai
A
license
Not graded
quality
C
maintenance
Provides a memory layer for AI coding agents with Git-powered version control, enabling automatic tracking of prompts, context, and code diffs.
Updated 8 months ago (2026-02-05 11:11 UTC)
194
MIT
Hypermnesic
Knowledge & Memory Search Version Control
leonardsellem
A
license
A
quality
A
maintenance
Git-native long-term memory for AI agents: your markdown files are the source of truth, the search index is a disposable projection rebuilt from git, and every memory the agent writes is a reviewable git commit. Served over one OAuth-secured MCP endpoint with hybrid lexical+semantic recall and a gated, git-first commit_note write tool.
Updated 10 days ago (2026-09-27 19:26 UTC)
7
9
AGPL 3.0
Ori Mnemos
Knowledge & Memory RAG Systems
aayoawoyemi
A
license
Not graded
quality
A
maintenance
Open-source persistent memory infrastructure for AI agents.
Updated 6 days ago (2026-10-01 06:50 UTC)
536 npm
328
Apache 2.0
robo-cortexofficial
Knowledge & Memory Developer Tools Version Control
robotel-limited
A
license
A
quality
A
maintenance
Provides a git-aware knowledge base for AI coding agents to store and retrieve memories anchored to code changes, with automatic staleness detection.
Updated a month ago (2026-08-31 02:12 UTC)
8
1
MIT

Perenna

为什么选择 Perenna？

快速入门

随你的 AI 代理一同安装

安装已发布版本

从源码安装以进行开发

文档

License

Available Tools

Output Schema

TDQS

Output Schema

TDQS

Output Schema

TDQS

Tool Schema Changelog

TDQS

Maintenance

Resources

Related MCP Connectors

Related MCP Servers

MemoVofficial

Hypermnesic

Ori Mnemos

robo-cortexofficial