Cognitive AI Memory

MCP数据服务

提供方 sachitrafa

数据服务 未标注 无需鉴权 社区 / 第三方

YourMemory is an MCP server that uses biological forgetting curves to automatically prune stale data and reinforce useful context for Claude agents. It beats Mem0 by 16% on benchmarks and runs fully locally with zero LLM overhead via spaCy and SQLite.

一句话选型结论

按资料字段整理

Cognitive AI Memory 属于数据服务类 MCP 服务器,传输方式未标注,无需鉴权,没有现成安装命令,需按官方文档接入。接入前先确认权限范围;涉及写入、删除或付款的操作,建议先在测试环境验证。

分类数据服务 传输方式未标注 鉴权无需鉴权 部署方式未标注
GitHub 星标 未标注 仓库热度,无公开仓库时显示未标注
工具数 未标注 暴露给模型的工具数量
资源 / 提示词 0 / 0 资源与提示词模板数量
维护方 社区 / 第三方 核验等级 仅资料核对

工具与能力

数据服务
数量来自来源目录的标注,具体工具清单以官方文档为准
工具数量未标注暴露给模型可调用的工具个数
资源数量0可读取的资源条目
提示词数量0内置提示词模板数量

能力标签

安装与配置

未标注 无需鉴权
上游未给出传输方式
  1. 1
    准备运行环境

    按官方文档确认运行环境(常见为 Node.js 或 Python),装好后再执行安装命令。

  2. 2
    安装服务

    复制上面的安装命令执行;命令里带占位符的位置,换成自己的密钥或路径。

  3. 3
    写入客户端配置

    在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,让新配置生效。

  4. 4
    验证是否可用

    连接成功后随便调一个只读工具,确认能返回结果,再接入正式流程。

典型使用场景

3 类
按分类与标签整理的常见用法,具体以官方文档为准
数据库查询

用自然语言查库、取数,不用手写 SQL。

数据同步与清洗

把多来源数据拉到一处做整理。

报表取数

按口径快速拉出统计结果。

选择建议

选之前先看这几条
按条目字段给出的判断,不替你决定用不用

值得选的地方

  • 资料标注无需鉴权,装好就能连。

先想清楚的地方

  • 没有现成安装命令,需要按官方文档自己填启动命令和参数。
  • 资料没标注工具数量,实际能力要装好后确认。
  • 版本更新与行为细节以官方仓库为准。

更适合

  • 需要在数据服务场景里让模型直接调用外部能力的人。
  • 想先快速试一下、能接受在本地或自有环境跑服务的人。

不太适合

  • 需要厂商级 SLA 和技术支持的生产环境。

同类对比

6 个同类
同分类里挑最接近的几条,字段以各自详情页为准
MCP 服务器工具数传输方式部署方式安装命令最后核验
Cognitive AI Memory当前 未标注 未标注 未标注 无 2026-05-17
Memory 9d25f64e 9 未标注 未标注 无 2026-05-17
Getzep MCP 9 stdio · 本地进程 本地部署 有 2026-05-17
anything-llm 未标注 stdio · 本地进程 本地部署 有 2026-04-11
Prisma MCP Server 未标注 stdio · 本地进程 本地部署 有 2026-05-17
Astr Bot 未标注 stdio · 本地进程 本地部署 有 2026-05-17

服务器档案

数据服务
字段来自项目仓库与公开索引,中文说明由本站标注
提供方sachitrafa上游标注的维护方 sachitrafa
分类数据服务本站按上游分类展示
连接方式未标注上游未给出传输方式
鉴权方式无需鉴权远程服务建议用最小权限凭据
维护方社区 / 第三方核验等级 仅资料核对
包名 / 运行时未标注 · 未标注本地安装时用到的包标识与运行时
部署类型未标注上游给出的部署形态
最近核验2026-05-17上游最后核验时间

详细介绍

17.6 KB
来自项目仓库与上游目录的原文,未做删改

YourMemory

Your AI has the memory of a goldfish. Not anymore.

Persistent, self-improving memory for AI agents — built on the science of how humans remember.

▶ Try the live interactive demo · Website · Benchmarks


The problem

Every morning your AI agent treats you like a stranger. Same context re-explained. Same preferences forgotten. Every session starts from zero.

Most "memory" tools bolt a vector database onto an agent and call it done — but that's just storage. It hoards every near-duplicate until retrieval drowns in noise. A goldfish with a bigger bowl.

YourMemory is different: memory that works like a brain, not a database.```mermaid
flowchart LR
A["🧠 You tell your<br/>AI something"] --> B["Extract durable<br/>facts"]
B --> C["Dedup + embed<br/>+ graph-link"]
C --> D[("Memory<br/>store")]
D -->|"related facts pile up"| E["✨ Consolidate<br/>N → 1 summary"]
D -->|"stale + unused"| F["📉 Decay<br/>+ prune"]
D -->|"new session"| G["♻️ Recall<br/>hybrid + graph"]
E --> D
G --> H["🤖 Your agent<br/>picks up where<br/>it left off"]
style D fill:#0a2540,stroke:#19cdff,color:#fff
style E fill:#0c2b3a,stroke:#5eead4,color:#fff
style H fill:#0c2b3a,stroke:#19cdff,color:#fff


---

## ✨ What makes it different

| | Feature | What it does |
|---|---|---|
| 🧠 | **Consolidation** | When enough related facts accumulate, they&#x27;re compressed into one clean summary and the originals are archived. Memory gets **sharper over time, not bloated**. |
| 📉 | **Biological decay** | Every memory ages on an **Ebbinghaus forgetting curve**. Stale, unused facts fade; important and frequently-recalled ones persist. |
| 🔗 | **Entity graph** | Memories link by shared people, places, and concepts — so recall surfaces what you *forgot to ask for*. |
| ♻️ | **Survives context resets** | When the context window compacts, YourMemory hands the working context back — no re-reading files to figure out where you were. |
| 🔒 | **Tamper-evident audit trail** | Every read / write / delete is logged in a **hash-chained** ledger. Alter one record and the chain breaks. |
| 👥 | **Team memory pools** | Role-based shared memory, so a whole team&#x27;s agents draw on the same institutional knowledge — with private memories kept private. |
| 🛡️ | **Data rights built in** | One-command **export** (right to access) and **right-to-forget** (purge), plus SOC 2-aligned controls. |
| 🔌 | **MCP-native &amp; local-first** | Works with Claude, Cursor, Cline, Windsurf, or any MCP client. Runs entirely on your machine — no API key, nothing leaves your system. |

&gt; One command to install. DuckDB by default (zero setup), Postgres + pgvector for teams.

---

## Table of Contents

- 🏆 Benchmarks
- 🚀 Quick Start
- 🧠 How Memory Works
  - Consolidation
  - Decay
  - Hybrid Retrieval
- 🔒 Trust &amp; Audit Trail
- 👥 Team Memory Pools
- 🛡️ Data Rights &amp; Compliance
- 🎛️ Dashboards
- 🔧 MCP Tools
- ⚡ Ask Without an LLM Call
- 🔀 API Proxy — Guaranteed Memory
- 🏗️ Architecture &amp; Stack
- 🩺 Troubleshooting
- 🤝 Contributing

---

## 🏆 Benchmarks

Three external datasets. Every number independently reproducible — benchmark code lives in the repo. Full methodology in BENCHMARKS.md.

### LoCoMo-10 — multi-session conversational memory```mermaid
xychart-beta
    title &quot;Recall@5 · LoCoMo-10 (higher is better)&quot;
    x-axis [&quot;Mem0&quot;, &quot;Zep Cloud&quot;, &quot;Supermemory&quot;, &quot;YourMemory&quot;]
    y-axis &quot;Recall@5 percent&quot; 0 --&gt; 70
    bar [18, 28, 31, 59]

> 2× better recall than Zep Cloud across all 10 samples. *Supermemory and Mem0 exhausted free-tier quotas mid-benchmark; scores computed over the full 1,534 pairs.

LongMemEval-S — 500 questions, ~53 distractor sessions each

The hardest standard benchmark for long-term memory. Each question is buried in ~53 sessions.

Metric Score
Recall@5 (any gold session in top-5) 89.4%
Recall-all@5 (all gold sessions in top-5) 84.8%
nDCG@5 (ranking quality) 87.4%

HotpotQA — 200 multi-hop questions

System BOTH_FOUND@5
YourMemory (vector + BM25 + entity graph) 71.5%
YourMemory (no entity edges) 59.5%

Entity graph edges add +12 pp — they traverse from Fact 1 to Fact 2 even when Fact 2 has low embedding similarity to the query.

Writeup: I built memory decay for AI agents using the Ebbinghaus forgetting curve


🚀 Quick Start

Python 3.11–3.14. No Docker, no database setup. All memory stored locally in ~/.yourmemory/.```bash
pip install yourmemory
yourmemory-register <your-token>
yourmemory-setup


**Get your token:** visit **yourmemoryai.xyz** → enter your email → verify with a 6-digit code → copy your token.

`yourmemory-setup` auto-detects and wires up **Claude Code, Claude Desktop, Cursor, Windsurf, and Cline**, then asks which backend to use:

- **DuckDB** — zero setup, single local file *(default)*
- **Postgres** — shared / production; you provide a `DATABASE_URL` (needs the pgvector extension)

&gt; **Optional — smarter local extraction:** YourMemory works out of the box with built-in heuristics. For higher-quality, fully-local fact extraction, install Ollama and `yourmemory-setup` pulls the model (`qwen2.5:7b`, ~4.7 GB) automatically. Prefer the cloud? Set `YOURMEMORY_EXTRACT_BACKEND=anthropic`.

### Or install from a binary — no Python required

Prefer not to touch pip? Grab the standalone binary for your platform from the latest release:

| Platform | Asset |
|----------|-------|
| macOS (Apple Silicon) | `yourmemory-macos-arm64.tar.gz` |
| macOS (Intel) | `yourmemory-macos-x86_64.tar.gz` |
| Linux (x86-64) | `yourmemory-linux-x86_64.tar.gz` |
| Windows (x86-64) | `yourmemory-windows-x86_64.exe.zip` |
```bash
# macOS / Linux — download, extract, run
tar -xzf yourmemory-macos-arm64.tar.gz
./yourmemory-macos-arm64 register &lt;your-token&gt;
./yourmemory-macos-arm64 setup
./yourmemory-macos-arm64            # start the server

One executable handles every command: register, setup, ask &quot;&quot;, path, and (with no args) starts the server.

Fully self-contained & offline — the binary bundles Python, every dependency, and both ML models (the embedding model + spaCy). Nothing is downloaded on first run. The trade-off is size (~2 GB). Build your own with a single command — ./build-binary.sh — and multi-platform release binaries are produced automatically by the build workflow.


🧠 How Memory Works

YourMemory treats memory as a living system — it grows, consolidates, forgets, and connects, the way a brain does.

Consolidation — N → 1

Most memory tools just keep growing. YourMemory watches for clusters of related facts and, once enough accumulate, compresses them into a single clean summary — archiving the originals (never deleting, so nothing is lost).```mermaid
flowchart LR
subgraph before [Related facts pile up]
A1["Railway uses Nixpacks"]
A2["Railway on Pro plan"]
A3["Railway env vars hold<br/>the Postgres URL"]
A4["Deploys on Railway<br/>with Postgres"]
end
before --> C{"cluster +<br/>LLM summarize"}
C --> S["✨ Summary<br/>Deploys on Railway (Pro,<br/>Nixpacks) with Postgres<br/>via env vars"]
C -.->|"archived, recoverable"| ARC[("archive")]
style S fill:#0a2540,stroke:#5eead4,color:#fff
style C fill:#0c2b3a,stroke:#19cdff,color:#fff


&gt; Real example from one production store: **444 memories → 16 summaries** — same knowledge, a fraction of the noise. Consolidation is **event-driven** (triggered when related memories pile up), not a blind nightly job.

### Decay — the forgetting curve

Memory strength decays exponentially. Importance and recall frequency slow that decay:```
effective_λ  = base_λ × (1 − importance × 0.8)
strength     = clamp(importance × e^(−effective_λ × active_days) × (1 + recall_count × 0.2), 0, 1)

active_days counts only days you were active — vacations don't cause memory loss. Memories below strength 0.05 are pruned automatically. Each category ages at its own rate:

Category Half-life Best for
strategy ~38 days Patterns that worked, architectural decisions
fact ~24 days Preferences, identity, stable knowledge
assumption ~19 days Inferred context, uncertain beliefs
failure ~11 days Errors, wrong approaches, environment-specific issues

Chain-aware pruning: a decayed memory is kept alive if any graph neighbour is still strong — load-bearing context survives even when rarely queried directly.

Hybrid Retrieval — Vector + BM25 + Graph

Recall runs in two rounds so it surfaces both what you asked for and what you forgot to ask for:```mermaid
flowchart LR
Q["query"] --> R1["Vector + BM25<br/>hybrid search"]
R1 --> R2["Graph expansion<br/>(what you forgot to ask)"]
R2 --> S["rank by<br/>similarity × strength"]
S --> OUT["🎯 Ranked memories"]
style OUT fill:#0a2540,stroke:#19cdff,color:#fff


**Subject-aware deduplication** runs before every store — it embeds the subject of each sentence so `&quot;Sachit uses DuckDB&quot;` and `&quot;YourMemory uses DuckDB&quot;` stay separate (different entities), while `&quot;YourMemory uses DuckDB&quot;` and `&quot;YourMemory stores data in DuckDB&quot;` merge (same entity). No hardcoded word lists; generalises to any language.

---

## 🔒 Trust &amp; Audit Trail

Enterprises won&#x27;t let an opaque black box store their data. So every operation — **read, write, update, delete, consolidation** — is appended to a **hash-chained, tamper-evident audit log**.```mermaid
flowchart LR
    E0[&quot;GENESIS&quot;] --&gt; E1
    subgraph E1 [Event 1]
        H1[&quot;row_hash =&lt;br/&gt;sha256(prev + data)&quot;]
    end
    E1 --&gt; E2
    subgraph E2 [Event 2]
        H2[&quot;row_hash =&lt;br/&gt;sha256(#1.hash + data)&quot;]
    end
    E2 --&gt; E3
    subgraph E3 [Event 3]
        H3[&quot;row_hash =&lt;br/&gt;sha256(#2.hash + data)&quot;]
    end
    E3 --&gt; V{&quot;GET /audit/verify&quot;}
    V --&gt;|chain intact| OK[&quot;✅ verified&quot;]
    V --&gt;|any row altered| BAD[&quot;❌ chain breaks&lt;br/&gt;at that row&quot;]
    style OK fill:#0a2540,stroke:#5eead4,color:#fff
    style BAD fill:#3a0c14,stroke:#fb7185,color:#fff

Each row records the timestamp, actor user + agent, action, operation, target memory, source (http vs mcp), and the previous row's hash. Change any historical record and verify_chain() pinpoints exactly where the chain broke.```bash
GET /audit # browse the trail (filter by user / action / operation)
GET /audit/verify # cryptographically verify the chain is untampered
POST /audit/prune # retention-based cleanup (90-day minimum, never lower)


&gt; Audit logging is **fail-open** — it never blocks a memory operation — and read/list events from the dashboard&#x27;s own render loop are excluded, so the trail stays signal, not noise.

---

## 👥 Team Memory Pools

Give a whole team&#x27;s agents one shared brain — without leaking anyone&#x27;s private context. Memories are either **shared** (visible to the pool) or **private** (visible only to their owner).```mermaid
flowchart TB
    P((&quot;🧠 Team Pool&lt;br/&gt;shared memory&quot;))
    A[&quot;Alice&#x27;s agent&quot;] &lt;--&gt;|shared| P
    B[&quot;Bob&#x27;s agent&quot;] &lt;--&gt;|shared| P
    C[&quot;Carol&#x27;s agent&quot;] &lt;--&gt;|shared| P
    A -. private .-&gt; AP[&quot;🔒 Alice-only&quot;]
    B -. private .-&gt; BP[&quot;🔒 Bob-only&quot;]
    style P fill:#0a2540,stroke:#19cdff,color:#fff
    style AP fill:#0c1424,stroke:#5a6b80,color:#8294a8
    style BP fill:#0c1424,stroke:#5a6b80,color:#8294a8

Role-based access is enforced per agent — what one engineer's agent learns, the whole team benefits from instantly; sensitive context stays scoped to its owner.```bash
POST /pools # create a pool
POST /pools/{id}/members # add a member (with role)
POST /pools/{id}/memories # contribute a shared memory
POST /pools/{id}/retrieve # recall across the pool


---

## 🛡️ Data Rights &amp; Compliance

Because memory that stores real data needs the controls to be trusted with it:

| Right | Endpoint | What it does |
|-------|----------|--------------|
| **Access** (DSAR export) | `GET /users/{id}/export` | Full export of everything stored for a user |
| **Erasure** (right to forget) | `DELETE /users/{id}/memories` | One-command purge of a user&#x27;s memories |
| **Portability** | `POST /users/{id}/import` | Re-import a previous export |
| **Recoverability** | `GET /users/{id}/archive` | Retrieve consolidated-away originals |

Combined with the hash-chained audit trail and 90-day retention floor, these map directly onto the controls documented in SECURITY.md (SOC 2-aligned).

---

## 🎛️ Dashboards

Two built-in browser UIs — no extra setup, they start automatically with the server.

### Memory Dashboard — `http://localhost:3033/ui`

A full read/write view with **Memories · Audit · Pools** tabs: stats bar (Strong / Fading / Near-prune), per-agent tabs, memory cards with live strength bars, category filters, the audit trail, and pool management.

### Graph Visualiser — `http://localhost:3033/graph`

An interactive force-directed map of how memories connect — root memory as a bright node, neighbours color-coded by category, edge thickness = connection strength. Drag, zoom, and click any node for full content.```
http://localhost:3033/graph?memoryId=42&amp;userId=alex&amp;depth=2

🔧 MCP Tools

Three tools, called by your AI automatically.

Tool When your AI calls it What it does
recall_memory(query, current_path?) Start of every task Surfaces memories ranked by similarity × decay strength; spatial boost for path-matched memories
store_memory(content, importance, category?, context_paths?) After learning something new Embeds, deduplicates, stores with decay; tags optional file/dir paths
update_memory(id, new_content, importance) When a stored fact is outdated Re-embeds and replaces; logs the change to the audit trail
# Store with spatial context
store_memory(
    &quot;Alex prefers tabs over spaces in Python&quot;,
    importance=0.9, category=&quot;fact&quot;,
    context_paths=[&quot;/projects/backend&quot;],
)

# Next session — spatial boost fires when working in that directory
recall_memory(&quot;Python formatting&quot;, current_path=&quot;/projects/backend&quot;)
# → {&quot;content&quot;: &quot;Alex prefers tabs over spaces in Python&quot;, &quot;strength&quot;: 0.87}

⚡ Ask Without an LLM Call

The only memory system that can answer questions without making any LLM API call:```bash
yourmemory ask "what database does this project use"

→ YourMemory uses DuckDB locally and Postgres in production.

yourmemory ask "how do I fix a kubernetes deployment"

→ Not enough memory context to answer without an LLM.


When memory is strong enough it answers instantly — zero tokens, zero cloud cost, zero latency. When it isn&#x27;t, it declines cleanly rather than hallucinating. Your query never leaves your machine.

---

## 🔀 API Proxy — Guaranteed Memory

MCP tools are called at the AI&#x27;s discretion. The API proxy removes that uncertainty — it intercepts every LLM call, injects relevant memories automatically, and handles `store_memory` / `update_memory` with no model configuration.

Start the server (`yourmemory`), then point your client at `localhost:3033`:```python
from anthropic import Anthropic

client = Anthropic(
    api_key=&quot;sk-ant-...&quot;,
    base_url=&quot;http://localhost:3033/proxy/anthropic&quot;,
    default_headers={&quot;X-YourMemory-User&quot;: &quot;alex&quot;},  # per-user memory
)

# Memory is injected automatically — no other changes needed
response = client.messages.create(
    model=&quot;claude-opus-4-8&quot;,
    max_tokens=1024,
    messages=[{&quot;role&quot;: &quot;user&quot;, &quot;content&quot;: &quot;What database do I use?&quot;}],
)

OpenAI works identically via base_url=&quot;http://localhost:3033/proxy/openai&quot;.


🏗️ Architecture & Stack```mermaid

flowchart LR
C["Your AI client<br/>Claude · Cursor · any MCP"] <--> Y["🧠 YourMemory"]
Y --> M[("Memory<br/>store")]
Y --> A[("Audit<br/>ledger")]
style Y fill:#0a2540,stroke:#19cdff,color:#fff
style M fill:#0c1a2c,stroke:#5eead4,color:#fff
style A fill:#0c1a2c,stroke:#5eead4,color:#fff


| Component | Role |
|-----------|------|
| **DuckDB** | Default vector store — zero setup, native cosine similarity |
| **PostgreSQL + pgvector** | Optional — for teams or large datasets |
| **NetworkX** | Default graph backend (`~/.yourmemory/graph.pkl`) |
| **Neo4j** | Optional graph backend |
| **sentence-transformers** | Local embeddings (`multi-qa-mpnet-base-dot-v1`, 768 dims) |
| **spaCy** | Local NLP for deduplication and entity extraction |
| **APScheduler** | Automatic decay + pruning |

---

## 🩺 Troubleshooting

**Writes hang / time out (DuckDB single-writer lock).** If both the MCP server and the HTTP server run at once, they compete for the DuckDB write lock. Fix:```bash
pkill -f yourmemory 2&gt;/dev/null || true
rm -f ~/.yourmemory/memories.duckdb.wal ~/.yourmemory/memories.duckdb.lock 2&gt;/dev/null || true
# restart your client

Running Claude Desktop (MCP) and Claude Code (hooks) simultaneously? Use SQLite instead — it handles concurrent readers/writers cleanly:
DATABASE_URL=sqlite:///~/.yourmemory/memories.db


🤝 Contributing

PRs welcome — see CONTRIBUTORS.md.

📚 Dataset References

  • LoCoMo — Maharana et al. (2024)
  • LongMemEval — Wu et al. (2024)
  • HotpotQA — Yang et al. (2018)

📄 License

Copyright 2026 Sachit Misra — Licensed under CC-BY-NC-4.0.

Free for personal use, education, academic research, and open-source projects.
Commercial use requires a separate written agreement → mishrasachit1@gmail.com

Give your AI a memory worth keeping.
pip install yourmemory

常见问题

5 问
答案由本站依据条目字段整理,不引用上游原文
Cognitive AI Memory 怎么安装?

资料没有给出安装命令,请到官方仓库或文档按说明接入;这类条目多数是生态应用,或尚未发布可安装包。

Cognitive AI Memory 怎么在客户端里配置?

它的传输方式未标注,在客户端 MCP 配置里按官方文档填写启动命令和参数,保存后重启客户端生效。

Cognitive AI Memory 收费吗?

本站不代收费用,也没有标注具体价格。是否收费取决于服务本身和背后的接口额度,正式使用前按官方说明确认。

Cognitive AI Memory 需要 API Key 吗?

资料标注为无需认证,装好就能连;如果实际调用时报鉴权错误,按官方文档补上凭据。

Cognitive AI Memory 能提供哪些能力?

资料显示能力标签包括 数据分析、API集成、知识管理。具体工具清单以官方文档为准。

热门专题

按标签挑服务器
全部专题 →

服务器信息以作者仓库与官方文档为准;分类、传输方式与鉴权方式的中文说明为中文整理,最近核验 2026-05-17。