timesfm
TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.
Persistent memory MCP server for AI coding assistants. Chinese-first and fully local.
Skills that teach the AI this kind of work; they work alongside this one
TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.
Open-source intelligence for the global theater. Track everything from the corporate/private jets of the wealthy, and spy satellites, to seismic events in one unified interface. Hook an AI agent up to have it parse through data and find previously unseen correlations. The knowledge is available to…
scrape data from Google Maps. Extracts data such as the name, address, phone number, website URL, rating, reviews number, latitude and longitude, reviews,email and more for each place
Lists are ordered by a usage score (out of 100) built from these parts
| Popularity | 8/80 | GitHub stars or weekly downloads: the larger counts 60, the smaller 20 |
|---|---|---|
| Freshness | 3/12 | Full marks for a release or code change within 30 days |
| Still answering | 0/8 | The cloud endpoint answered at the last check |
| Usage score | 11/100 |
Quality: Passed 2/3 basic checks (shown, not used for ordering) · Momentum: No data yet (Used only on the Trending tab)
Pick the AI app you use, then copy the settings.
Let your AI install it with one sentence
Please install Aifp MCP. Follow https://mcp.popnx.com/i/wjabanjj-aifp-mcp.md, show me the commands and wait for my OK before running them.Paste it into an AI that can work on your computer (such as Claude Code or Cursor). It reads our steps, shows you the commands and waits for your OK. No key, no sign-up. · See the full text your AI reads
Passed 2/3 checks · Runs on your computer · ✓ Commands checked Nov 14, 2026
First: which AI do you use?
Pick your app and the steps appear below.
Works with Claude, with some setup first
Install Node.js on your computer first (one time) · Only the Claude desktop app (Windows or Mac), not the web or phone
Copy this message into a Claude chat. The AI checks your computer, tells you which file it will change, and waits for your OK every time.
Please install the MCP server Aifp MCP for Claude on this computer, in this order: 1) Check Node.js with node -v. If it is missing, tell me to install it from https://nodejs.org/en/download; do not install it yourself. 2) Use only this config (already checked by PopNx MCP): { "mcpServers": { "aifp": { "command": "npx", "args": [ "-y", "aifp-mcp" ] } } } 3) Tell me the full path of the file you will change, or the command you will run, and wait for my OK. 4) No key is needed. 5) Do what we agreed, then check that the Aifp MCP tools really show up.This message has no key in it. If a key is needed, the AI will ask you to paste it yourself into the file or the app’s field.
Already installed? Check first · Open Terminal, type this command and press Enter
node -vMac: press ⌘ + Space, type Terminal, press Enter
Windows: open Start, type Windows PowerShell, then Open
Not installed: Open the official download page, pick the LTS version and the click-through installer: .pkg on Mac · .msi on Windows. Double-click and follow it to the end. No curl command needed
Open the Node.js download page ↗
When it’s done, close Terminal, open it again and run the same command. You should see a version number: node -v
Install once; it works for everything that needs Node.js
SettingsDeveloperEdit Config
{
"mcpServers": {
"aifp": {
"command": "npx",
"args": [
"-y",
"aifp-mcp"
]
}
}
}Use Aifp MCP and tell me what you can do for me, then show me one thing✓ If Claude says it is using Aifp MCP or shows a Aifp MCP tool in the answer, you are connected
The command above works without these. Add them only if you want to change something, following the maker’s description.
COGNITION_LLM_API_KEY Optional LLM API key for automatic memory recognition (COGNITION_LLM_API_KEY or ANTHROPIC_API_KEY)Descriptions are as written by the maker.
Menu names checked against Anthropic’s help page on Nov 11, 2026 · your screen may differ slightly by app version
ChatGPT cannot connect Aifp MCP yet
Aifp MCP runs on your computer, but ChatGPT can only connect servers that run on the web
A · Use an app that can connect Aifp MCP
Works with Claude Code, with some setup first
Install Node.js on your computer first (one time)
Copy this message into a Claude Code chat. The AI checks your computer, tells you which file it will change, and waits for your OK every time.
Please install the MCP server Aifp MCP for Claude Code on this computer, in this order: 1) Check Node.js with node -v. If it is missing, tell me to install it from https://nodejs.org/en/download; do not install it yourself. 2) Use only this config (already checked by PopNx MCP): claude mcp add --scope user aifp -- npx -y aifp-mcp 3) Tell me the full path of the file you will change, or the command you will run, and wait for my OK. 4) No key is needed. 5) Do what we agreed, then check that the Aifp MCP tools really show up.This message has no key in it. If a key is needed, the AI will ask you to paste it yourself into the file or the app’s field.
Already installed? Check first · Open Terminal, type this command and press Enter
node -vMac: press ⌘ + Space, type Terminal, press Enter
Windows: open Start, type Windows PowerShell, then Open
Not installed: Open the official download page, pick the LTS version and the click-through installer: .pkg on Mac · .msi on Windows. Double-click and follow it to the end. No curl command needed
Open the Node.js download page ↗
When it’s done, close Terminal, open it again and run the same command. You should see a version number: node -v
Install once; it works for everything that needs Node.js
Mac: press Command+Space and type Terminal · Windows: open PowerShell
claude mcp add --scope user aifp -- npx -y aifp-mcpYou should see Aifp MCP listed as connected
Use Aifp MCP and tell me what you can do for me, then show me one thing✓ If Claude Code says it is using Aifp MCP or shows a Aifp MCP tool in the answer, you are connected
The command above works without these. Add them only if you want to change something, following the maker’s description.
COGNITION_LLM_API_KEY Optional LLM API key for automatic memory recognition (COGNITION_LLM_API_KEY or ANTHROPIC_API_KEY)Descriptions are as written by the maker.
Menu names checked against Anthropic’s help page on Nov 11, 2026 · your screen may differ slightly by app version
Works with Cursor, with some setup first
Install Node.js on your computer first (one time)
Copy this message into a Cursor chat. The AI checks your computer, tells you which file it will change, and waits for your OK every time.
Please install the MCP server Aifp MCP for Cursor on this computer, in this order: 1) Check Node.js with node -v. If it is missing, tell me to install it from https://nodejs.org/en/download; do not install it yourself. 2) Use only this config (already checked by PopNx MCP): { "mcpServers": { "aifp": { "command": "npx", "args": [ "-y", "aifp-mcp" ] } } } 3) Tell me the full path of the file you will change, or the command you will run, and wait for my OK. 4) No key is needed. 5) Do what we agreed, then check that the Aifp MCP tools really show up.This message has no key in it. If a key is needed, the AI will ask you to paste it yourself into the file or the app’s field.
Already installed? Check first · Open Terminal, type this command and press Enter
node -vMac: press ⌘ + Space, type Terminal, press Enter
Windows: open Start, type Windows PowerShell, then Open
Not installed: Open the official download page, pick the LTS version and the click-through installer: .pkg on Mac · .msi on Windows. Double-click and follow it to the end. No curl command needed
Open the Node.js download page ↗
When it’s done, close Terminal, open it again and run the same command. You should see a version number: node -v
Install once; it works for everything that needs Node.js
Use Aifp MCP and tell me what you can do for me, then show me one thing✓ If Cursor says it is using Aifp MCP or shows a Aifp MCP tool in the answer, you are connected
The command above works without these. Add them only if you want to change something, following the maker’s description.
COGNITION_LLM_API_KEY Optional LLM API key for automatic memory recognition (COGNITION_LLM_API_KEY or ANTHROPIC_API_KEY)Descriptions are as written by the maker.
Menu names checked against Cursor’s help page on Nov 11, 2026 · your screen may differ slightly by app version
Works with VS Code, with some setup first
Install Node.js on your computer first (one time)
Copy this message into a VS Code chat. The AI checks your computer, tells you which file it will change, and waits for your OK every time.
Please install the MCP server Aifp MCP for VS Code on this computer, in this order: 1) Check Node.js with node -v. If it is missing, tell me to install it from https://nodejs.org/en/download; do not install it yourself. 2) Use only this config (already checked by PopNx MCP): { "servers": { "aifp": { "type": "stdio", "command": "npx", "args": [ "-y", "aifp-mcp" ] } } } 3) Tell me the full path of the file you will change, or the command you will run, and wait for my OK. 4) No key is needed. 5) Do what we agreed, then check that the Aifp MCP tools really show up.This message has no key in it. If a key is needed, the AI will ask you to paste it yourself into the file or the app’s field.
Already installed? Check first · Open Terminal, type this command and press Enter
node -vMac: press ⌘ + Space, type Terminal, press Enter
Windows: open Start, type Windows PowerShell, then Open
Not installed: Open the official download page, pick the LTS version and the click-through installer: .pkg on Mac · .msi on Windows. Double-click and follow it to the end. No curl command needed
Open the Node.js download page ↗
When it’s done, close Terminal, open it again and run the same command. You should see a version number: node -v
Install once; it works for everything that needs Node.js
Use Aifp MCP and tell me what you can do for me, then show me one thing✓ If VS Code says it is using Aifp MCP or shows a Aifp MCP tool in the answer, you are connected
The command above works without these. Add them only if you want to change something, following the maker’s description.
COGNITION_LLM_API_KEY Optional LLM API key for automatic memory recognition (COGNITION_LLM_API_KEY or ANTHROPIC_API_KEY)Descriptions are as written by the maker.
Menu names checked against VS Code’s help page on Nov 11, 2026 · your screen may differ slightly by app version
Other apps that use MCP, such as Windsurf, Zed or Gemini CLI, each add servers differently. See how in the app list.
JSON settings are under “For developers” below
Claude Code
claude mcp add --scope user aifp -- npx -y aifp-mcpClaude Desktop (claude_desktop_config.json)
{
"mcpServers": {
"aifp": {
"command": "npx",
"args": [
"-y",
"aifp-mcp"
]
}
}
}Cursor (~/.cursor/mcp.json)
{
"mcpServers": {
"aifp": {
"command": "npx",
"args": [
"-y",
"aifp-mcp"
]
}
}
}VS Code (mcp.json)
{
"servers": {
"aifp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"aifp-mcp"
]
}
}
}COGNITION_LLM_API_KEY secret envDescriptions are as written by the maker.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Based on how this server connects and on each app’s own docs, checked Nov 10, 2026.
Run on your computer in
ClaudeGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatRaycast
Runs on your computer; the tool list appears in your AI app after you install it.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 19, 2026
The registry name was verified with the GitHub account wjabanjj, which owns the repo
Code last changed 3 months ago
GitHub could not identify the licence type; open the file to check
This one runs on your computer; there is no internet endpoint
Runs on your computer and uses local settings instead
Runs on your computer; we can only read tool lists from internet endpoints
No entries on OSV.dev for aifp-mcp@1.5.8
Checks only this package version, not every dependency · checked Nov 15, 2026
If you made this, paste this code into your README. The badge links back to this page.
[](https://mcp.popnx.com/en/servers/wjabanjj-aifp-mcp)Ask, share a tip or report that it does not work. Sorted by what people marked helpful.
No posts yet. Be the first to ask or share.
Posts here are written by users, not the PopNx team.
No reviews yet
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 2 of 3 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
The registry does not list a required key, though some servers ask you to sign in on first use.
It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).
The GitHub repo last changed 3 months ago, and the latest version (1.5.8) reached the registry 3 months ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Node.js on your computer.
In the same category: OpenSEO, Exa, Microsoft Learn MCP, Docs, COTAL actions (cotal.ai)
Same category, other makers, commands already checked. Official ones first, then by stars.
Reading a card:↓ Downloads per weeki★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
Keyword research, site audits, rank tracking and AI visibility for your AI agent.
Connect AI agents to Exa for web search, content fetching, and multi-step research.
Official Microsoft Learn MCP Server – real-time, trusted docs & code samples for AI and LLMs.
Search and read Empryo's documentation. Read-only, no auth, no local access.
cotal.ai actions: product overview, site search, build log, feedback, Cloud waitlist, updates, calls
| This one Aifp MCP | OpenSEO | Exa | Microsoft Learn MCP | Docs | COTAL actions (cotal.ai) | |
|---|---|---|---|---|---|---|
| Runs where | Installs on your computer | Runs in the cloud, nothing to install | Runs in the cloud, nothing to install | Runs in the cloud, nothing to install | Runs in the cloud, nothing to install | Runs in the cloud, nothing to install |
| Needs a key | No | No | No | No | No | No |
| Add with + in Claude | No | Yes | Yes | Yes | No | No |
| Basic checks | 2/3 | 5/5 | 2/4 | 4/4 | 4/4 | 4/4 |
| License | NOASSERTION | MIT | MIT | CC-BY-4.0 | NOASSERTION | Apache-2.0 |
| Price | No cost listed in the registry | No cost listed in the registry | No cost listed in the registry | No cost listed in the registry | No cost listed in the registry | No cost listed in the registry |
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
通过 Model Context Protocol 为 AI 编程助手提供持久记忆。
让 Obsidian、DeepSeek Harness、Claude Code、Cursor、Codex 等一切支持 MCP 的 AI 工具拥有跨会话的持续记忆。完全本地运行,数据不出本机(默认 ~/.ai-cognition/)。
你受够了 AI 的"健忘"吗?
多数 AI 记忆系统只是存——存是存了,但用不上。AiFP 是让 AI 真正记住、想通、共享,把上面这些毛病一次解决。
先讲别人做不到的(共享):
一套记忆,所有 AI 共用。 今天 DeepSeek Harness 学会的,明天 Claude Code 还记得;Codex 攒的偏好,VS Code Copilot 不用重新问。别的记忆系统做不到——因为它们每个各记各的,互不相通。AiFP 让同电脑上所有 AI 工具共用一个大脑,记一份,处处用。
再讲它为什么好用(能力):
看这些名字,就知道它不简单——记忆被做成了大脑的结构:
| 概念 | 它到底在干嘛(大白话) |
|---|---|
| 🧠 海马体 · 记忆感知 | 会掂量着记——先进"待定区",识别器判断值不值得长期记住,值得才正式记下,不值得就跳过 |
| 🔗 神经元突触 · 感知链 | 自动发现信息之间的联系,还能顺着线索找到最直接的关系 |
| 👃 嗅觉皮层 · 语义检索 | 说错也能找到——你说"拍森",它知道你要找 Python |
| ⚡ 共燃神经元 · 关联 | 一起出现的东西自动绑在一起,问 A 顺带带出 B |
| 🗣 语言中枢 · 理解 | 懂口语、认错字、认得"上个月"是哪个月 |
| 🌊 神经扩散 · 联想回忆 | 一条线索能联想出好几层相关的记忆 |
| 🧬 突触固化 · 记忆巩固 | 用得越多记得越牢,从临时记忆慢慢变成长期记忆 |
| ⏳ 遗忘曲线 | 太久不用的自然淡出,记忆库永远干净不堆积 |
| 📊 神经信号 · 置信度 | 每条记忆带个"可信度"标尺,越靠谱的越优先给你 |
| 👤 主人认知模型 · 画像 | 懂你这个人——偏好习惯会积累成画像,但不跟它的想法混 |
| 💪 肌肉记忆 · 跨轮复用 | 做过的经验跨会话记得,不用每次从头学 |
天生为中文服务:认错字、懂口语、认时间词,全都是为中文设计的。英文为主的记忆系统,遇到"拍森找 Python"这种就抓瞎了。
默认完全私有:所有数据都存你本机,不上云、不注册、不偷偷上报。所谓"共享"只是多个工具读写同一份本地记忆——你的数据从没离开过这台电脑。
一条命令装好:npm install -g 自动帮你配好 12 个 AI 工具(Claude Code、Cursor、Windsurf、Cline、Gemini CLI、Qwen Code、Zed、VS Code Copilot、Codex CLI、Trae、DeepSeek Harness、pi-coding-agent)。
一个大脑,多个助手:今天 DeepSeek Harness 学到的,明天 Claude Code 还记得——像跟一个有记忆的同事说话,不用每次都重新自我介绍。
npm install -g aifp-mcp
claude mcp add ai-cognition -s user -- npx aifp-mcp
重启 Claude Code 即可使用。数据存在 ~/.ai-cognition/data/cognition.db。
装完 aifp-mcp 后自动接入 dsh,无需手动执行任何 dsh 命令:
npm install -g aifp-mcp
安装时会自动检测 dsh 并写入配置(~/.dsh/cordis.patch.yml)。重启 dsh,记忆工具自动注册为 mcp__aifp__*(如 mcp__aifp__search_memories、mcp__aifp__save_memory),无需手动改任何配置。
不需要手动配任何东西。在 Claude Code、Codex、Cursor、DeepSeek Harness 等任意工具里直接输入:
帮我安装记忆系统:
npm install -g aifp-mcp
postinstall 钩子会自动检测并配置所有已安装的 AI 工具(Claude Code、Cursor、Windsurf、Cline、Gemini CLI、Qwen Code、Zed、VS Code Copilot、Codex CLI、Trae、DeepSeek Harness、pi-coding-agent),并打印状态报告。重启工具即可使用记忆工具——AI 看到报告后会告诉你重启哪个,无需手动改任何 MCP 配置文件。
首次启动:需要下载 ~30MB 的 bge-small-zh 嵌入模型,最多阻塞 45 秒。后续启动有缓存,秒开。
AiFP 支持两种运行模式(环境变量 COGNITION_MODE,默认 remote):
本地模式完全私有(数据不出本机),但感知链工具需要连接服务器。服务器地址不随包分发,需通过官方接入渠道获取。
接入地址和密钥通过官方渠道发放:联系作者(微信:zm8571806/QQ:8571806/邮箱:8571806@qq.com)订阅后发放,不随包公开。订阅到期可单独吊销,不影响其他用户。
# 1. 安装(如未安装)
npm install -g aifp-mcp
aifp-mcp --connect https://<官方地址> <你的64位key>
--connect 会把连接信息保存在本机 ~/.ai-cognition/server.json,之后启动自动生效,无需每次配置环境变量。
不需要手动敲命令。在 Claude Code / Cursor / Codex / dsh 等任何 AI 工具的输入框里说:
这是我的 aifp 服务器地址和 key,帮我配置:
地址:https://<官方地址>
key:<你的64位key>
AI 会自动执行 aifp-mcp --connect 并提示你重启工具。重启后感知链增强自动生效。
⚠️ key 会出现在对话记录中,介意的话配置完可在管理后台吊销重发(不影响使用)。
Obsidian 笔记 → 记忆库(AI 可语义检索你的笔记):直接让你的 AI 导入,无需配置环境变量:
把 Obsidian 笔记导入记忆:directory = C:/Users/你/Obsidian/我的笔记库
AI 会调用 reimport_sources 同步导入(frontmatter 自动剥离、哈希去重)。以后新增笔记再说一次即可。
记忆库 → Obsidian 笔记(在 Obsidian 里看到全部记忆):让 AI 调用 export_memories_md:
把记忆导出到 Obsidian:directory = C:/Users/你/Obsidian/我的笔记库/AiFP记忆
导出的笔记带 frontmatter(type/tier/tags),Obsidian 可直接识别和检索;同名笔记自动覆盖更新,保持与记忆库同步。
核心工具(15 个):
| 工具 | 功能 | 链路 |
|---|---|---|
save_memory | 保存记忆(自动去重 + 向量索引) | 基础 |
search_memories | 双路检索:FTS5 关键词 + 向量语义 | 逻辑链 |
recall_context | 一键回忆(直接命中 + 因果链 + 关联 + 扩散) | 综合链 |
get_memory | 按 ID 获取记忆详情 | 基础 |
list_memories | 分页列出 | 基础 |
trace_perception_chain | BFS 感知链追踪(6 类因果) | 上下链 |
find_perception_path | 双向 BFS 找两条记忆间最短路径 | 关系链 |
get_perception_graph_stats | 感知图统计 | 关系链 |
diffuse_memories | 图扩散搜索(关联多跳) | 关系链 |
get_memory_tree | 层级树结构 | 基础 |
get_related_memories | Hebbian 共现关联 | 关系链 |
get_user_profile | 用户画像——聚合偏好/事实/习惯 | 画像 |
observe_turn | 记录对话轮次到识别队列(跨平台自动记忆入口) | 自动 |
reimport_sources | 重新扫描外部笔记目录 | 导入 |
get_stats | 系统统计 | 基础 |
另有 18 个管理/进阶工具:consolidate_memories / share_memory / merge_memories / batch_delete / batch_update / export_memories / export_memories_md(Obsidian)/ explain_query / get_confidence_stats / scan_memory_patterns / validate_memory / get_top_experiences / deduplicate_memories / scan_observation_patterns / rotate_observation_logs / session_mine / derive_memories / flush_recognizer。
Claude Code 使用原生 hooks(100% 自动,零遗漏)。其他工具通过 observe_turn 工具 + 指令文件实现(详见 rules/ 目录):
| 平台 | 配置方式 | 自动程度 |
|---|---|---|
| Claude Code | hooks(原生) | 100% 自动,零遗漏 |
| Cursor | .cursor/rules/ 指令文件 | AI 遵守指令时自动触发 |
| Codex CLI | AGENTS.md 指令文件 | AI 遵守指令时自动触发 |
| Trae | 项目规则(手动配置) | AI 遵守指令时自动触发 |
指令文件告诉 AI:"每次回答完用户后调用 observe_turn 记录本轮消息"。系统会自动判断是否有值得记住的内容,不需手动决定。
npm install -g aifp-mcp 时自动完成(postinstall 检测所有已装 AI 工具并写入 MCP 配置)。以后新装了某个 AI 工具,跑一次即可接入:
aifp-mcp --setup # 重新检测并配置所有 AI 工具
自动检测并配置已安装的 AI 工具(检测到才写入,不重复覆盖):
| 平台 | 配置方式 |
|---|---|
| Claude Code | ~/.claude/settings.json → mcpServers + 启动 hook |
| Cursor | ~/.cursor/mcp.json |
| Windsurf | ~/.codeium/windsurf/mcp_config.json |
| Cline | ~/.config/cline/mcp_settings.json |
| Gemini CLI | ~/.gemini/settings.json → mcpServers |
| Qwen Code | ~/.qwen/settings.json → mcpServers |
| Zed | ~/.config/zed/settings.json → context_servers |
| VS Code Copilot | %APPDATA%/Code/User/mcp.json → servers |
| Codex CLI | ~/.codex/config.toml |
| pi-coding-agent | 生成扩展到 ~/.pi/agent/extensions/aifp-memory/(pi 无内置 MCP,用扩展机制) |
{
"mcpServers": { "ai-cognition": { "command": "node", "args": ["path/to/aifp-mcp/dist/index.js"] } } }
COGNITION_DATA_DIR=/path/to/data npx aifp-mcp
| 变量 | 默认值 | 说明 |
|---|---|---|
COGNITION_DATA_DIR | ~/.ai-cognition/ | 数据存储目录 |
COGNITION_MODE | remote | local 本地保底 / remote 连接服务器增强 |
COGNITION_SERVER_URL | *(无默认,须显式配置)* | 远程算法服务器地址(自建) |
COGNITION_API_KEY | - | 远程模式 API 密钥 |
COGNITION_RECOGNIZER | 0 | 设为 1 启用自动识别 |
COGNITION_LLM_API_KEY | - | 识别器 LLM 密钥(OpenAI 兼容) |
COGNITION_LLM_BASE_URL | https://api.deepseek.com | 识别器 LLM 地址 |
COGNITION_LLM_MODEL | deepseek-chat | 识别器 LLM 模型 |
HF_MIRROR | https://hf-mirror.com | 嵌入模型下载镜像(失败自动回退 huggingface.co) |
CORS_ORIGIN | * | HTTP 模式跨域白名单 |
PORT | 5000 | HTTP 端口 |
观察队列需要 LLM 判断是否值得入记忆,二选一:
# OpenAI 兼容(推荐:DeepSeek 等)
export COGNITION_RECOGNIZER=1 export COGNITION_LLM_API_KEY=你的DeepSeek密钥 export COGNITION_LLM_BASE_URL=https://api.deepseek.com # 可选,默认同左 export COGNITION_LLM_MODEL=deepseek-chat # 可选
不配置则只记录观察日志,自动识别不落地(AI 主动 save_memory 不受影响)。
专有软件 — 见 LICENSE。个人/非商业用途免费;商业用途需授权。第三方依赖遵循各自开源许可。