Ombre BrainSAFE
For Claude.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
一个给提供给Claude 用的长期情绪记忆系统。基于 Russell 效价/唤醒度坐标打标,Obsidian 做存储层,MCP 接入,带遗忘曲线。
A long-term emotional memory system for Claude. Tags memories using Russell's valence/arousal coordinates, stores them as Obsidian-compatible Markdown, connects via MCP, and has a forgetting curve.
[](https://render.com/deploy?repo=https://github.com/P0lar1zzZ/Ombre-Brain)
它是什么 / What is this
Claude 没有跨对话记忆。每次对话结束,之前聊过的所有东西都会消失。
Ombre Brain 给了它一套持久记忆——不是那种冷冰冰的键值存储,而是带情感坐标的、会自然衰减的、像人类记忆一样会遗忘和浮现的系统。
Claude has no cross-conversation memory. Everything from a previous chat vanishes once it ends.
Ombre Brain gives it persistent memory — not cold key-value storage, but a system with emotional coordinates, natural decay, and forgetting/surfacing mechanics that loosely mimic how human memory works.
核心特点 / Key features:
- 情感坐标打标 / Emotional tagging: 每条记忆用 Russell 环形情感模型的 valence(效价)和 arousal(唤醒度)两个连续维度标记。不是"开心/难过"这种离散标签。
Each memory is tagged with two continuous dimensions from Russell's circumplex model: valence and arousal. Not discrete labels like "happy/sad".
- 自然遗忘 / Natural forgetting: 改进版艾宾浩斯遗忘曲线。不活跃的记忆自动衰减归档,高情绪强度的记忆衰减更慢。
Modified Ebbinghaus forgetting curve. Inactive memories naturally decay and archive. High-arousal memories decay slower.
- 权重池浮现 / Weight pool surfacing: 记忆不是被动检索的,它们会主动浮现——未解决的、情绪强烈的记忆权重更高,会在对话开头自动推送。
Memories aren't just passively retrieved — they actively surface. Unresolved, emotionally intense memories carry higher weight and get pushed at conversation start.
- Obsidian 原生 / Obsidian-native: 每个记忆桶就是一个 Markdown 文件,YAML frontmatter 存元数据。可以直接在 Obsidian 里浏览、编辑、搜索。自动注入
[[双链]]。
Each memory bucket is a Markdown file with YAML frontmatter. Browse, edit, and search directly in Obsidian. Wikilinks are auto-injected.
- API 降级 / API degradation: 脱水压缩和自动打标优先用廉价 LLM API(DeepSeek 等),API 不可用时自动降级到本地关键词分析——始终可用。
Dehydration and auto-tagging prefer a
92ea431e2ec1OBSERVED · 2026-10-07Exposed tools (5)
4 read · 0 write · 1 destructive. Blast radius: 1 tool can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.
| Tool | Risk | Description |
|---|---|---|
breath | read | 检索记忆或浮现未解决记忆。query 为空时自动推送权重最高的未解决桶;有 query 时按关键词+情感检索。domain 逗号分隔,valence/arousal 传 0~1 启用情感共鸣,-1 忽略。 |
grow | read | 日记归档。自动拆分长内容为多个记忆桶。 |
hold | read | 存储单条记忆。自动打标+合并相似桶。tags 逗号分隔,importance 1-10。 |
pulse | read | 系统状态和所有记忆桶摘要。include_archive=True 时包含归档桶。 |
trace | destructive | 修改记忆元数据。resolved=1 标记已解决(桶权重骤降沉底),resolved=0 重新激活,delete=True 删除桶。其余字段只传需改的,-1 或空串表示不改。 |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (3 observation(s))
- Network
- declared (5 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (4)
trace
2. (可选)设置 `OMBRE_BASE_URL`:API 地址,支持任意 OpenAI 化地址,如 `https://api.deepseek.com/v1` / `http://123.1.1.1:7689/v1` / `http://your-ollama:11434/v1`
2. (Optional) `OMBRE_BASE_URL`: any OpenAI-compatible endpoint, e.g. `https://api.deepseek.com/v1`, `http://123.1.1.1:7689/v1`, `http://your-ollama:11434/v1`
mcp, rapidfuzz, openai, pyyaml, python-frontmatter, jieba, httpx
Gates applied: no_behavioural_pass.
92ea431e2ec1full audit observations/trust-audit/mcp-server/p0lar1zzz__ombre-brain.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-07 | 92ea431e2ec1 | SAFE | B | 89 | first audit |
Questions
What is the Ombre Brain MCP server?
For Claude.
What tools does Ombre Brain expose?
5 in total: 4 read-only, 0 that write, and 1 that can delete or overwrite (trace). Every one is listed on this page with its risk.
Is Ombre Brain safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B. Separately from the audit: 1 of its tools can destroy data, so scope the token you give it to what you actually need.
What credentials does Ombre Brain need?
It reads OMBRE_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Ombre Brain run?
It speaks streamable-http, so it runs as a service you connect to over the network.
How current is this page?
The grade is for one exact copy of the source (92ea431e2ec1), read on 2026-10-07. The repository is watched and re-audited when it changes.