Context7
Up-to-date docs for AI agents
作者提供的说明(英文原文)
Hierarchical markdown memory palace for AI agents — structured palace navigation via MCP tools.
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。
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": {
"locus": {
"command": "uvx",
"args": [
"locus-mcp"
]
}
}
}在终端中运行这条命令
claude mcp add locus -- uvx locus-mcp粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"locus": {
"command": "uvx",
"args": [
"locus-mcp"
]
}
}
}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": {
"locus": {
"type": "stdio",
"command": "uvx",
"args": [
"locus-mcp"
]
}
}
}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。
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 EDKarlsson 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(0.6.2)于8个月前进入注册中心。
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 Python (uv)。
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。
Hierarchical markdown-based memory system for autonomous AI agents. Each directory is a room (locus) in the palace, containing specific knowledge navigated on demand. Named for the atomic unit of the Method of Loci.
Core idea: Keep context windows small. Load only the room you need, not the whole palace.
palace/
INDEX.md ← always read first (~50 lines max) global/ toolchain/ toolchain.md ← canonical facts about tools projects/ my-project/ my-project.md ← room overview + key files technical-gotchas.md ← specialty: issues & resolutions sessions/ 2026-03-02.md ← append-only session log
An agent reads INDEX.md, navigates to the relevant room, and reads only that room. Session logs accumulate until consolidation merges them into canonical files.
See the wiki for full documentation.
# Install
pip install locus-mcp
locus init ~/.locus
locus-mcp --palace ~/.locus
pip install locus-mcp
Or run without installing using uvx:
uvx locus-mcp --palace ~/.locus
The skill files are the one part of Locus written for a specific runtime. The palace convention, the MCP server, and the recall / lint / index CLIs are runtime-neutral and work from anything that can read a file or speak MCP. The skills in skills/claude/ are written and maintained for Claude Code, and that is the only set shipped here. They are plain markdown with YAML frontmatter, so another runtime is welcome to adapt them. Per-runtime copies used to live in skills/codex/ and skills/gemini/; they were removed because keeping three variants honest cost more than it returned.
Install them from a clone:
git clone https://github.com/Nano-Nimbus/locus.git
cd locus make install-skills # copies skills/claude/* to ~/.claude/skills/ make install-skills-dry # print what would be copied, write nothing
CLAUDE_SKILLS_DIR overrides the destination.
| Skill | Command | Description |
|---|---|---|
locus | /locus | Recall, navigate the palace, write rooms and session logs, regenerate indexes |
locus-consolidate | /locus-consolidate | Merge session logs into canonical files |
locus-audit | /locus-audit | Audit palace health |
locus-feedback | /locus-feedback | Record explicit feedback on a palace recall |
locus-release | /locus-release | Post-release verification workflow (contributors) |
locus-security | /locus-security | Trust tags, nonce discipline, and the locus-security CLI |
locus-palace-init | /locus-palace-init | Bootstrap a palace from existing memory files |
pip install locus-mcp
locus --palace ~/.locus --task "What toolchain conventions are set?"
The locus-mcp command exposes five tools over the Model Context Protocol.
Use stdio for all local integrations (Claude Desktop, Claude Code, Codex, Gemini — default, no extra flags needed). SSE transport is available for network deployments (--transport sse) and requires FASTMCP_HOST=0.0.0.0 to be set explicitly — the server binds to loopback by default.
| Tool | Description |
|---|---|
memory_list | Returns INDEX.md (no args) or lists a room's files |
memory_read | Reads any file in the palace |
memory_write | Atomically writes a file (guarded — cannot write to _metrics/, sessions/, .sig/, .security/) |
memory_search | Ranked full-text search over the shared FTS5 index (see Recall); ripgrep only without FTS5 |
memory_batch | Reads up to 20 palace files in a single call — use for multi-room loads |
Add --security to enable Ed25519 signature verification on reads and automatic signing on writes. See Security below.
claude_desktop_config.json){
"mcpServers": { "locus": { "command": "locus-mcp", "args": ["--palace", "/path/to/palace"] } } }
Or using uvx (no install required):
{
"mcpServers": { "locus": { "command": "uvx", "args": ["locus-mcp", "--palace", "/path/to/palace"] } } }
{
"mcp": { "servers": { "locus": { "command": "locus-mcp", "args": ["--palace", "/path/to/palace"] } } } }
All clients support LOCUS_PALACE as an alternative to --palace:
export LOCUS_PALACE=~/.locus
locus-mcp
See MCP Server Configuration for the full client setup guide and spec/mcp-server.md for architecture details.
locus recall answers "what do I already know about this?" in one call, fast enough to run on every prompt from a hook. It keeps a SQLite FTS5 index (standard library only, no PyYAML) over any number of markdown roots: a palace, an OKF bundle, a Claude Code memory directory, or all of them at once.
locus recall --root ~/memory --root ./docs "why does the flux kustomization stall"
Recalled memory:
| Flag | Default | Meaning |
|---|---|---|
--root DIR | .locus.toml, then LOCUS_PALACE | Directory to index; repeatable |
-k N | 3 | Number of hits |
--budget BYTES | 4096 | Hard cap on text output |
--include journal | off | Include type: Journal files |
--type TYPE | all | Only this frontmatter type; repeatable |
--json | off | Print a JSON list instead of text |
--refresh | off | Rebuild the index from scratch |
Frontmatter drives the result: title (or name, or the first heading), description, tags, type (or metadata.type), modified (else generated.at, else file mtime), status, stale_after, and verified. Ranking is bm25 with title and description weighted above the body; exact ties go to human-reviewed files, then to the newest modified. A hit is flagged STALE when its stale_after has passed or its status is deprecated. Trust tiers follow OKF: unverified, machine-confirmed (only non-human verified entries), human-reviewed (any verified entry whose by starts with human:).
Roots can live in a .locus.toml in the project or any parent directory:
[recall]
roots = ["docs", "~/memory/shared"]
The index is stored at ${XDG_CACHE_HOME:-~/.cache}/locus/ .sqlite, never inside a root, and is refreshed incrementally (mtime, then content hash) on every call. With no hits the text output is empty and the exit status is still 0, so a prompt hook can call it unconditionally:
#!/bin/sh
prompt=$(jq -r .prompt) exec locus recall -k 3 --budget 4096 "$prompt"
The MCP server's memory_search uses the same index, so MCP results are ranked the same way. Full rules in spec/recall.md.
locus lint checks markdown roots for Open Knowledge Format v0.2 conformance and the Locus palace conventions. locus index generates the index files those conventions define. Both read the same frontmatter recall indexes, and neither imports the Agent SDK, so a CI job that only checks conformance does not install it.
locus lint --root docs --check # CI gate: exit 1 on any error
locus lint --root docs --fix # add inferable fields, rewrite nothing locus index --root docs --check # exit 1 when a generated index drifted
docs/runbooks/valve-chatter.md: error [okf.type-missing] frontmatter has no non-empty type (fix: add type: Runbook) docs/log.md: error [okf.log-order] entries run oldest first: 2026-05-09 follows 2026-05-01 docs/reference/platform.md: warning [locus.size-limit] 214 lines exceeds the 200-line soft limit for a specialty file 2 error(s), 1 warning(s), 1 fixable
| Flag | Default | Meaning |
|---|---|---|
--root DIR | .locus.toml, then LOCUS_PALACE | Directory to check; repeatable |
--check | off | Exit non-zero on any error. For CI |
--strict | off | Treat warnings as errors under --check |
--fix | off | Add inferable fields. Never rewrites an existing key |
--type-map DIR=TYPE | none | Infer this OKF type under DIR; repeatable |
--archive-glob GLOB | none | Paths that should carry status: deprecated; repeatable |
--json | off | Print a JSON report instead of text |
Rules split in two. okf.* checks what the specification requires: a parseable frontmatter block with a non-empty type on every non-reserved document, an index.md with no frontmatter beyond a bundle-root okf_version, a log.md that is date-headed and newest first, and ISO 8601 timestamps. Unknown keys and unknown type values are never reported: the spec requires consumers to tolerate both. locus.* checks the palace conventions: the size limits from spec/size-limits.md and the room main-file rule from spec/room-conventions.md.
Errors fail --check; warnings are advisory. A palace legitimately carries no frontmatter at all, so on a palace root the missing type rules are warnings rather than a CI failure on a layout the palace spec itself describes.
--fix adds three fields and only three: type from --type-map or [lint.types], generated.at from the file's first git commit, and status: deprecated for archive paths. It never rewrites or deletes a key, it never invents a generated block (nothing in a file says who produced it), and running it twice produces identical bytes.
| Flag | Default | Meaning |
|---|---|---|
--root DIR | .locus.toml, then LOCUS_PALACE | Directory to index; repeatable |
--check | off | Write nothing; exit non-zero on drift. For CI |
--kind | auto | Force okf, palace, or memory classification |
--json | off | Print a JSON report instead of text |
What gets generated depends on the root: an OKF bundle gets an index.md per directory in section 8 form (* [Title](path) - description, with okf_version: "0.2" frontmatter at the bundle root only), a palace gets the 50-line routing table INDEX.md, and a Claude Code memory directory gets a MEMORY.md of one - [Title](file.md) - description line per topic file. Output is deterministic, so --check is a byte comparison, and only index files are ever written.
Configure both from one .locus.toml:
[lint]
roots = ["docs"] archive_globs = ["archive/*"]
[lint.types] "." = "Reference" runbooks = "Runbook"
Full rules in [`spec/lint-and-index
只显示了开头部分;其余内容请在仓库中阅读