Context7
Up-to-date docs for AI agents
作者提供的说明(英文原文)
Memory interface for coding agents — stable memory_* tools over Hindsight, mem0, or Cognee.
这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。
我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。
选择你使用的 AI 应用,然后复制设置。
MEMORY_PROVIDER, PM_STACK_ROOT你需要
你用的是哪个应用?
在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。
打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json
{
"mcpServers": {
"openmem": {
"command": "npx",
"args": [
"-y",
"@bcmyguest/openmem"
],
"env": {
"MEMORY_PROVIDER": "your-value",
"PM_STACK_ROOT": "your-value"
}
}
}
}在终端中运行这条命令
claude mcp add openmem --env MEMORY_PROVIDER=your-value --env PM_STACK_ROOT=your-value -- npx -y @bcmyguest/openmem运行前请先填写空着的值。
粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"openmem": {
"command": "npx",
"args": [
"-y",
"@bcmyguest/openmem"
],
"env": {
"MEMORY_PROVIDER": "your-value",
"PM_STACK_ROOT": "your-value"
}
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"openmem": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@bcmyguest/openmem"
],
"env": {
"MEMORY_PROVIDER": "your-value",
"PM_STACK_ROOT": "your-value"
}
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
这个服务器在你的电脑上运行,而 ChatGPT 只能连接互联网上的服务器。请选择其他应用。
你的选择通过 Cookie 保存在这台设备上,无需账户。
MEMORY_PROVIDER envPM_STACK_ROOT env这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月7日
注册名称已通过 GitHub 账户 bcmyguest 验证,该账户拥有此仓库
我们还没有从 GitHub 读取这个仓库
我们还没有从 GitHub 读取这个仓库
它在你的电脑上运行,没有互联网端点
在你的电脑上运行,改用本地设置
它在你的电脑上运行;我们只能读取互联网端点的工具列表
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。
它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。
GitHub 仓库最后更新于–,最新版本(0.6.3)于10天前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 Node.js。
同一分类中有:Context7, Codebase Memory, Exa
同一分类中其他作者的服务器,按星标数排序。
如何看卡片:★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
Up-to-date docs for AI agents
Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
Connect AI agents to Exa for web search, content fetching, and multi-step research.
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
[!CAUTION]
Context management is leaving OpenMem. Smart compaction, the LiteLLM context proxy, and the OpenCode trim plugin in this repo are deprecated here and moving to [Smarter Compact](https://github.com/bcmyguest/smarter-compact) (docs,
npm install -g smarter-compact). Use OpenMem for memory (providers, indexer,memory_*MCP). Existing OpenMem stacks can still enable the composecontext-proxyprofile; new context work belongs in Smarter Compact.
OpenMem. Pluggable memory providers (Hindsight, mem0, Cognee) and one setup wizard for coding-agent memory — retain, recall, and index your sources.
A. Memory: your sources become memory any agent can query.
B. Context management *(deprecated in OpenMem — use Smarter Compact instead)*: long sessions stay under the limit; nothing is summarized away.
Benchmarks (context — deprecated here): In seed-matched ContextBench log tasks on Haiku 5.5, smart compaction scored 0.469 higher than keep-everything (95% bootstrap interval 0.339–0.578; eight pairs). Methods and charts still live in this repo (redirect · evidence plan); ongoing product docs and install are on Smarter Compact.
Docs: bcmyguest.github.io/openmem/
MCP: npx -y -p @bcmyguest/openmem openmem-mcp (after the wizard — it needs a running provider)
Start here: Concepts · Quickstart · Compatibility · Development (clone, tests, prek)
| Step | Command |
|---|---|
| 1. Wizard | npx @bcmyguest/openmem setup |
| 2. Check | npx @bcmyguest/openmem doctor |
| 3. Coding agents | npx @bcmyguest/openmem install-coding-agent --yes |
From a git clone: Development guide (npm install, npm run setup, tests, prek).
Needs (wizard): Docker Compose v2, Node ≥ 24, and an LLM route for Hindsight — see Quickstart.
Later: npx @bcmyguest/openmem up / down / switch --yes / doctor.
Wizard dry-run (what first setup plans — no writes):
Full guide: Quickstart · Concepts · Architecture
The two diagrams at the top show memory (A) and context management (B; deprecated in OpenMem, see Smarter Compact).
Same diagrams as Mermaid
flowchart LR
S[" Sources Git repos: docs, code outlines Obsidian vaults · notes · papers · bookmarks RSS · OpenAlex feeds"] -->|index| I[" OpenMem indexer polls repos, watches folders"] I -->|retain| P[(" Memory provider one active, swappable Hindsight (default) · mem0 · Cognee · …")] P <--> M[" OpenMem MCP memory_recall · memory_add memory_search · memory_reflect memory_pages_* + export/import, status…"] M <-->|tools| A[" Coding agents Claude Code · Codex · Cursor · OpenCode"] A -.->|"session hooks: recall at start · retain at stop"| M classDef om fill:#e8eaf9,stroke:#4651a6,color:#1b1d2a class I,M om
flowchart LR
A[" Coding agent Claude Code · Codex · OpenCode 1"] -->|requests| X[" Context proxy LiteLLM pre-call hook trims at 125k tokens (Haiku 95k) · no LLM call"] X -->|trimmed request| API[" Model API Anthropic · ChatGPT (Codex)"] X -->|every turn| S[(" Session store SQLite · every turn, verbatim")] S -->|"MCP: smart_compact_search · smart_compact_sql"| A O[" OpenCode 2 native plugin, no proxy"] -.->|same store| S classDef om fill:#e8eaf9,stroke:#4651a6,color:#1b1d2a class X,S om
Native compaction replaces history with an LLM summary, so exact values can be lost; smart compaction keeps every turn verbatim and searchable. Context trimming in OpenMem is deprecated — use Smarter Compact (smarter-compact enable). Legacy stack path: context proxy redirect. See architecture for memory runtime paths and provider-specific behavior.
memory_* plus optional native/NotebookLM servers: MCP setup.memory_export / memory_import speak PMM: Portable memory.npx @bcmyguest/openmem switch does not migrate data by itself; export/import (or re-index) moves content.Compose runs the shared indexer and the services required by the selected provider. Hindsight uses litellm and hindsight (127.0.0.1:8888); mem0 and Cognee use their own APIs and do not include LiteLLM by default. LiteLLM can also be added for memory_reflect synthesis on mem0/Cognee, or to host the optional context proxy's pre-call hook. See Architecture for runtime paths.
OpenMem is not affiliated with these projects; they shape the problem or the pattern.
| [OpenFeature](https://openfeature.dev/) | Inspiration for a vendor-agnostic interface + pluggable providers (there: feature flags; here: coding-agent memory). |
| [mise](https://mise.jdx.dev/) / [asdf](https://asdf-vm.com/) | One CLI over many backends; declarative config and tasks without replacing each tool’s own settings. |
| [LiteLLM](https://github.com/BerriAI/litellm) | Model proxy used on Hindsight stacks; its pre-call hook hosts the context proxy. |
| [Hindsight coding agents](https://www.npmjs.com/package/@vectorize-io/hindsight-coding-agents) | Reference implementation for knowledge pages, initiative capture and ingest status; OpenMem's hooks replace it in openmem mode. |
| [Mainplane](https://github.com/mainplane-ai/mainplane) | Inspiration for smart compaction: continue in a fresh context with a pointer to the saved transcript and retrieve as you go, instead of an LLM summary. |
| [Letta](https://www.letta.com/) / [MemGPT](https://arxiv.org/abs/2310.08560) | Inspiration for smart compaction: evicted turns kept verbatim in searchable recall storage the agent pages back with tools, and file-style search over the transcript (74.0% on LoCoMo). OpenMem does this in a proxy and an MCP server, so no Letta server is needed. |
| [rtk](https://github.com/rtk-ai/rtk) | Compresses shell command output before the agent sees it; install-coding-agent runs rtk init when it is installed. Inspired the context proxy's compression of large tool results (reimplemented, not bundled). |
| [opencode-clm](https://github.com/bcmyguest/opencode-clm) | OpenCode plugin for Context Language Models: the model edits a file mirror of its own context. Same goal as smart compaction, with the model doing the trimming (comparison). |
| [Meridian](https://github.com/rynfar/meridian) | Bridges a Claude subscription to an Anthropic-compatible API; optional Hindsight model backend (guide). |
| [OpenCode](https://opencode.ai/) / [Claude Code hooks](https://code.claude.com/docs/en/hooks) / [Codex hooks](https://developers.openai.com/codex/hooks) | The agent hook and plugin APIs OpenMem translates between (compatibility). |
Research notes and benchmark results for the context proxy: Context research.
More setup analogues: Pluggable memory providers.
Formerly personal-memory. Use the
openmemCLI and MCP server name; installers drop the oldpersonal-memoryMCP entry.
Papers and preprints cited in our context-management work (full list):
| Reference | Link |
|---|---|
| MemGPT (Packer et al., 2023) | arXiv:2310.08560 |
| LoCoMo (An et al., 2024) | arXiv:2402.17753 |
| LongMemEval (Wu et al., 2024) | arXiv:2410.10813 |
| MemoryAgentBench (2025) | [arXiv:2507.052
只显示了开头部分;其余内容请在仓库中阅读