CLAUDE.md@cortexA
CLAUDE.md@cortex from kapella-hub/firekeephq is a CLAUDE.md file: the standing instructions Claude Code reads in that repo.
mdr add kapella-hub/firekeephq/cortex/CLAUDE.md@git:20261006.e4c172bPins git:20261006.e4c172b in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 14 of 14 checks passed
- Kind
- CLAUDE.md file
- Repository
- kapella-hub/firekeephq
- Path
cortex/CLAUDE.md- Versions recorded
- 6
- Latest version
- git:20261006.e4c172b, committed Oct 6, 2026
- First version recorded
- Aug 25, 2026
- Size
- 14,998 bytes
- Repository stars
- 3
- License
- a license file GitHub does not identify
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# CLAUDE.md This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository. ## Project Overview FirekeepCortex is a domain-agnostic Memory-as-a-Service (MaaS) layer that provides persistent cognitive memory for LLM agents. It tracks procedural memory, declarative memory, and mistake resolution across arbitrary software projects and automated workflows. ## Tech Stack - **API**: FastAPI (Python 3.11+) - **Graph DB**: Neo4j 5.x (knowledge graph) - **Vector DB**: Qdrant (semantic embeddings) - **Queue/Cache**: Redis 7+ (event stream) - **Background Worker**: Celery (Sleep Cycle consolidation) - **LLM**: OpenAI-compatible API (Ollama/vLLM/OpenAI) - **Embeddings**: mxbai-embed-large (1024-dim, configurable via `EMBEDDING_MODEL`/`EMBEDDING_DIM`; embed input is capped and shrink-to-fit at `EMBED_MAX_CHARS=2000` so long memories still embed) ## Architecture ``` app/ ├── config.py # Pydantic BaseSettings, env var loading ├── llm.py # Chat endpoint selection (ollama native /api/chat vs /v1), body build + response normalise, optional JSON-schema structured outputs ├── models.py # Request/response Pydantic models …
Read the whole file at its exact version.
How to install
mdr add kapella-hub/firekeephq/cortex/CLAUDE.md@sha256:4a7a1f36c92e4e5fThe line at the top of this page pins the label git:20261006.e4c172b, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_yg3qpthaktv2aapy)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 6 versions of this file, between Aug 25, 2026 and Oct 6, 2026, about one every 9 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261006.e4c172b latest | 2026-10-06 | e4c172b | 14,998 B | A | view · diff |
| git:20261002.d8fc05d | 2026-10-02 | d8fc05d | 14,740 B | A | view · diff |
| git:20260903.2046362 | 2026-09-03 | 2046362 | 14,768 B | A | view · diff |
| git:20260825.9253706 | 2026-08-25 | 9253706 | 14,436 B | A | view · diff |
| git:20260825.99778d1 | 2026-08-25 | 99778d1 | 13,966 B | A | view · diff |
| git:20260825.a9248e3 | 2026-08-25 | a9248e3 | 13,250 B | A | view |
Audit of the latest version
- pass: Size between 200 bytes and 200 KB (14998 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
kapella-hub/firekeephq · 3 stars · license a license file GitHub does not identify · pushed 2026-10-12 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_yg3qpthaktv2aapy GET https://markdownregistry.com/api/v1/resolve?ref=kapella-hub/firekeephq/cortex/CLAUDE.md GET https://markdownregistry.com/api/v1/blob/4a7a1f36c92e4e5f6116fca4f63983a85f5b2ccfa824f4c5c73d40fc567de8b1
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: what a CLAUDE.md file is · keeping AGENTS.md and CLAUDE.md in sync · which agent file does what.