- name
SKILL.md
技能檔案保留在發布者的儲存庫中。
在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add topoteretes/cognee --skill cognee-server -a cursor -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add topoteretes/cognee --skill cognee-server -a claude-code -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add topoteretes/cognee --skill cognee-server -a codex -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add topoteretes/cognee --skill cognee-server -a grok -y在 Grok Bot 聊天中傳送複製的訊息。Bot 會從 GitHub 取得這個 SKILL.md,並加入你所有 Bot 共用的技能中。
Install this skill: https://github.com/topoteretes/cognee/tree/HEAD/.agents/skills/cognee-server來自發布者
cognee-cli -ui
launches the full local stack: FastAPI backend on http://localhost:8000
and the UI on http://localhost:3000. Needs LLM_API_KEY in the
environment or .env. The interactive API reference is at
http://localhost:8000/docs, health at /health.
For API-only serving via Docker instead, use the cognee-docker skill (the
prebuilt cognee/cognee:main image or docker compose up from the repo).
ENABLE_BACKEND_ACCESS_CONTROL decides everything:
true (default): multi-tenant — auth required on every API call, per
user+dataset database isolation.false: single-user local mode — no auth, shared local databases. Right
choice for a personal dev server; never for anything exposed.REQUIRE_AUTHENTICATION=false is ignored while access control is on; to turn
auth off you must set ENABLE_BACKEND_ACCESS_CONTROL=false.
Behind a TLS-terminating proxy set AUTH_TOKEN_COOKIE_SECURE=true so the auth cookie
gets the Secure attribute; leave it off for plain http://localhost, where a browser
refuses to store a Secure cookie.
API requests cannot fetch URLs or clone remote repositories unless the server
sets ALLOW_HTTP_REQUESTS=true. A blocked attempt raises an error naming that
setting. With the variable unset or blank, SDK, CLI and MCP calls still allow
fetching. Only true, 1, yes or on enable it; any other value (false,
or a misspelling) disables it on every surface. This setting does not disable
LLM or embedding provider calls.
SDK / CLI against the server (instead of embedded local mode):
cognee-cli serve --url http://localhost:8000 # local instance
cognee-cli serve --url https://... --api-key ck_... # cognee cloud instance
cognee-cli serve # reconnect to the saved keyed instance
cognee-cli serve --logout # disconnect
In Python: await cognee.serve(url="http://localhost:8000").
HTTP: main routes live under /api/v1/ — the memory API is remember
(plus remember/entry), recall, improve, forget; sessions covers
session memory; datasets, users, visualize handle the rest. The legacy
add, cognify, search, and delete routes still exist and are
what the memory routes call underneath (see cognee/api/client.py for the
registered routers, or GET /openapi.json on a running server).
Note there is no /api/v1/feedback route — feedback exists as a CLI
command and in the SDK, but is not exposed over HTTP.
from cognee.api.v1.visualize import visualization_server
shutdown = visualization_server(port=8080) # synchronous; returns a shutdown callable
"8080:8000").ENABLE_BACKEND_ACCESS_CONTROL=false and restart.recall/search returns [] instead of erroring → permission-filtered
result; check dataset access rights for the calling user.Use when the user wants to run the cognee API server (and optional UI) on their own machine — starting it, checking it's healthy, connecting the SDK or other clients to it, and choosing the right auth
---name: cognee-serverdescription: Use when the user wants to run the cognee API server (and optional UI) on their own machine — starting it…---# .agents/skills/cognee-server/SKILL.md總覽
Use when the user wants to run the cognee API server (and optional UI) on their own machine — starting it, checking it's healthy, connecting the SDK or other clients to it, and choosing the right auth posture.
常見問題
從發布者下載 .agents/skills/cognee-server/SKILL.md,或複製路徑後開啟儲存庫。PlugMCP 只收錄這項技能,不代管檔案。
發布者將它存放在 https://github.com/topoteretes/cognee。
Claude、Cursor、Codex 和 Grok Build 可以讀取你從發布者儲存庫加入的 SKILL.md。在聊天中傳送技能的 GitHub 資料夾連結,Grok Bot 就會安裝它。