Cognee is an AI memory platform that stores information in a self-hosted knowledge graph so agents can retain context across sessions. It ingests data, connects related information, and helps agents retrieve it for reasoning and actions. The catalogue includes skills and instructions that extend agent workflows around Cognee.
Borrowing it
Nothing to install: this file belongs to topoteretes/cognee. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/topoteretes/cognee/main/.claude/skills/cognee-server/SKILL.mdgit clone --depth 1 https://github.com/topoteretes/cogneeWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/topoteretes/cognee/cognee-server)<a href="https://agentmods.dev/skills/topoteretes/cognee/cognee-server"><img src="https://agentmods.dev/badge/skills/topoteretes/cognee/cognee-server.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00050 | $0.00702 |
| Opus 5 | $0.00025 | $0.00351 |
| Sonnet 5 | $0.00010 | $0.00140 |
| Haiku 4.5 | $0.00005 | $0.00070 |
Grade A, and why
cognee-server scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Start the cognee server locally
From an installed cognee (no Docker)
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).
Auth posture
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.
Connecting clients to the running server
-
SDK / CLI against the server (instead of embedded local mode):
cognee-cli serve --url http://localhost:8000 # local instance cognee-cli serve # cognee cloud (device flow) cognee-cli serve --logout # disconnectIn Python:
await cognee.serve(url="http://localhost:8000"). -
HTTP: main routes live under
/api/v1/— the memory API isremember(plusremember/entry),recall,improve,forget;sessionscovers session memory;datasets,users,visualizehandle the rest. The legacyadd,cognify,search,memify, anddeleteroutes still exist and are what the memory routes call underneath (seecognee/api/client.pyfor the registered routers, orGET /openapi.jsonon a running server).Note there is no
/api/v1/feedbackroute —feedbackexists as a CLI command and in the SDK, but is not exposed over HTTP.
Graph visualization without the full UI
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago First seen · 72 lines · 50 tokens per session scan A cfe8c98f834e
cognee-server is a skill published in the GitHub repository topoteretes/cognee (30,501 stars, last pushed yesterday), licensed Apache-2.0. It adds 50 tokens to every session and 702 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
openmemory
Manage persistent memory via OpenMemory MCP. TRIGGER when: user says "remember this", "save to memory", "store this", "recall", "what do you remember about", "check memory", "forget this", "delete memory", "clean up memory", or when agent forms a stable conclusion worth persisting. DO NOT TRIGGER when: user refers to…
verify
Build, launch, and drive a local Honcho stack to verify a change at its runtime surface (the /v3 HTTP API and the deriver queue). Use when verifying a diff or confirming a change works in the running app.
surface-learnings
Use when the user asks "what have you learned", "what do you remember about me", "show me memory stats", "memory state", "/reflexes", or any variant. Surfaces what the limbic engine has accumulated as patterns, not as a memory dump.
context-recovery
Use at the start of every session, and especially after context compaction or a cold restart. Fires as the first action, before engaging with the user's opening message.
decision-encoding
Use when an architectural choice is made, a library is selected, an approach is committed to, a convention is set, or any "we'll do it this way" moment occurs. Fires the moment the decision stabilizes, not after.
pre-response-recall
Use when the user asks about anything that could have context in prior sessions — names, preferences, decisions, past work, or anything starting with "remember", "what did", "have we", "did we". Fires before generating any substantive response.