Power your agent
คำสั่งของผู้เผยแพร่เอง ไม่ใช่เอนด์พอยต์ของ PlugMCP
Host a copy with our keys and logs.
npx -y @lorekit/[email protected]Claude Code ไม่มีลิงก์ติดตั้งสำหรับคำสั่งแบบโลคัล ให้คัดลอกคำสั่งด้านล่างแล้วรันในเทอร์มินัล
claude mcp add lorekit-cli -- npx -y @lorekit/cli@1.78.0รันในเทอร์มินัล
{ "mcpServers": { "lorekit-cli": { "command": "npx", "args": [ "-y", "@lorekit/[email protected]" ] } }}claude_desktop_config.json
URL แบบรีโมตหรือคำสั่งบนเครื่องของคุณ? การติดตั้งสองแบบต่างกันอย่างไร
รันบน PlugMCP
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
เปิดจากผู้เผยแพร่
When your agent hits a wall and works its way out, it writes down what it learned — and the next agent to hit that wall gets the lesson with the error, on any machine, in any tool. What keeps recurring becomes a rule. What nobody uses gets archived.
Install the LoreKit shared-memory skill and run health checks for the LoreKit MCP server.
Website · Docs · Blog · Quick start · FAQ
npx @lorekit/cli install
Works with Claude Code and Cursor, Codex (experimental), and any MCP client. Runs fully offline with no account, or hosted so your whole team shares one set of lessons. MIT licensed and self-hostable.
LoreKit makes retrieval deterministic and leaves reasoning to the model.
It stores lessons in scopes (branch::, repo::, project::, global; the
most specific copy of a key wins), delivers them through lifecycle hooks and
error matching, counts recurrence so lessons worth promoting into a rule
surface, and archives by measured usage (how often a lesson is chosen versus
delivered). Reasoning over what it delivers is the model's job. Non-goals, by
design:
The bet: keep memory small, legible, and in the hot path — no structure precomputed at write time. Beyond catching failures, a skill can use LoreKit to improve on every run: self-improving workflows.
Keep it. A rules file holds what you knew to write down before anything broke. LoreKit captures what your agents find out the hard way — and keeps sorting it.
LoreKit is how you find out what has earned a place in your CLAUDE.md.
Each step is shipped behaviour, not a roadmap item:
npx @lorekit/cli install
The installer wires the MCP server, three companion skills, and the lifecycle hooks into your project, and picks up the repo's scope from its git remote. It then asks for a token — and that's where you pick a path:
Free plan: 5,000 active memories, 120 requests a minute.
.mcp.json at the CLI's built-in local server and set
"mode": "local" in .lorekit.json — see the
offline guide.Lessons are markdown files you can grep, diff, and commit.
Then check it's wired up:
npx @lorekit/cli doctor # connectivity, token permission, detected scopes
From then on, every session starts with the lessons that apply to it.
Claude Code marketplace plugin — skill + hooks + MCP in one install:
/plugin marketplace add mthines/lorekit
/plugin install lorekit-memory@lorekit
Claude Code on the web runs in a fresh clone each session, so add
--mcp-json to write a committable, secret-free .mcp.json (auth via
${LOREKIT_TOKEN}):
npx @lorekit/cli install --global --mcp-json
See the Claude Code on the web guide.
Use the CLI a lot? Install it globally and drop the npx prefix:
npm install -g @lorekit/cli
lorekit search "flaky test"
lorekit install --completions auto # zsh / fish tab completion
The companion skills the installer adds:
lorekit-memory — reads relevant lessons when a task starts, writes one when
something goes wrong.lorekit-setup — wires a self-improvement loop into your own skills: a
fast episodic tier that promotes proven lessons into permanent rules, with
guards that stop a loop reinforcing its own mistakes.lorekit-groom — tidies a noisy store: merges near-duplicates, lints weak
lessons, sets expiry. Always proposes a plan before changing anything.Also shipped in the Claude plugin, but not installed by lorekit install
(it's a one-time runbook, not everyday agent memory): lorekit-self-host — a
slash-only guided deployment walkthrough. Invoke it with /lorekit-self-host.
branch::, repo::, project::, or global. Agents read narrowest first,
so one repo's lore never crowds another's.
(scope format)repo::acme/* to your org and every
teammate's agent reads and writes the same lessons. CI reads with a
read-only lk_ro_ token. Anything unbound stays personal.
(organizations)lorekit migrate --from ~/.lorekit --to remote
previews the whole plan before it changes anything — lessons are never
stranded.All integrations share one zero-dependency hook engine; each host only gets a thin adapter. See plugins/.
list, search, show, tree, diff, dedupe, lint,
groom, and more — against either store, with --json for scripting.
(CLI reference)No. LoreKit doesn't index your codebase. It stores exactly what an agent
writes to it through memory.write — short lessons — and nothing else. In
local mode nothing leaves your machine at all.
Only you. Every memory is personal by default — visible only to the user or token that wrote it. Sharing with a team is opt-in, per scope, through an org. See private lore.
It can surface a lesson you didn't need — that's the honest answer. What keeps it in check: scopes narrow what an agent sees, recall only injects what matches, LoreKit measures which lessons are actually opened, and grooming archives what has stopped earning its place.
Nothing. There is no paid tier yet. The hosted free plan holds 5,000 active memories at 120 requests a minute. Local mode needs no account, and a self-hosted instance sets its own limits.
The whole stack — MCP server, dashboard, database — is in this repo under MIT, and deploys to your own Supabase and Vercel projects in about five minutes (self-hosting guide, or the walkthrough at lorekit.io/docs/self-host). Or skip the hosted store entirely and keep lessons as markdown in your repo.
The human-facing CLI commands (install, doctor, list, search, …) send
one usage span per run so the maintainers can see which commands get used: the
command name, a few boolean flags, the CLI/runtime/OS version, and the outcome.
No path, token, endpoint, repo, or scope is ever sent
(details). Turn it off with LOREKIT_TELEMETRY=0 or the cross-vendor
DO_NOT_TRACK=1, or set "telemetry.disabled": true in .lorekit.json for a
whole team.
LoreKit is an NX monorepo — MCP server (Deno, Supabase Edge Functions), dashboard (Next.js), and a zero-dependency CLI. Issues and PRs are welcome; DEVELOPMENT.md gets you from clone to green checks.
If LoreKit saves your agent a retry or two, a ⭐ helps other developers find it.
MIT © LoreKit contributors.
Install the LoreKit shared-memory skill and run health checks for the LoreKit MCP server.
{ "mcpServers": { "lorekit-cli": { "command": "npx", "args": [ "-y", "@lorekit/[email protected]" ] } }}เครื่องมือ
ยังไม่มีรายการเครื่องมือ เซิร์ฟเวอร์แบบรีโมตจะได้รายการหลังการตรวจสอบสถานะครั้งแรก
FAQ
คัดลอกคอนฟิก stdio สำหรับ Cursor, Claude Desktop, Claude Code หรือ VS Code ได้ในหน้านี้ คอนฟิกนี้ใช้การติดตั้งของผู้เผยแพร่ ไม่ใช่พร็อกซีของ PlugMCP
ระเบียนนี้ไม่ได้ระบุตัวแปรสภาพแวดล้อมที่จำเป็น
@lorekit/cli ทำงานแบบโลคัลผ่าน stdio
ตรวจสอบล่าสุดเมื่อ 2026-11-12 Install the LoreKit shared-memory skill and run health checks for the LoreKit MCP server.