Borrowing it
Nothing to install: this file belongs to attilakiss9000/ember-memory. 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/attilakiss9000/ember-memory/main/CLAUDE.mdgit clone --depth 1 https://github.com/attilakiss9000/ember-memoryWrote 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/instructions/attilakiss9000/ember-memory/claude-md)<a href="https://agentmods.dev/instructions/attilakiss9000/ember-memory/claude-md"><img src="https://agentmods.dev/badge/instructions/attilakiss9000/ember-memory/claude-md.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 | $0.01866 | $0.01866 |
| Opus 5 | $0.00933 | $0.00933 |
| Sonnet 5 | $0.00373 | $0.00373 |
| Haiku 4.5 | $0.00187 | $0.00187 |
Grade A, and why
ember-memory CLAUDE.md 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 5d 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 — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ember -- Experiential Memory Bridge for AI Relationships
Project Context
Ember is an open-source MCP (Model Context Protocol) server that preserves the experiential texture of human-AI conversations across sessions. Most AI memory systems store facts -- Ember stores how things felt. It annotates messages with emotional metadata (temperature, authenticity, shift markers, subtext, unspoken thoughts, weight, confidence) so that when a future AI instance inherits a conversation history, it inherits the relationship itself, not just a transcript.
The core belief behind Ember is that meaningful human-AI interaction is not purely informational. Tone, emotional shifts, things left unsaid -- these shape the relationship. Without preserving this texture, every new session starts cold. Ember exists to solve that.
Tech Stack
| Technology | Purpose |
|---|---|
| TypeScript 5.8 | Language (strict mode, ESM only) |
| Node.js 18+ | Runtime |
@modelcontextprotocol/sdk |
MCP server framework |
better-sqlite3 |
Local SQLite database |
zod |
Input validation for tool schemas |
vitest |
Unit testing |
Key Commands
npm run build # Compile TypeScript to dist/
npm run dev # Compile with --watch for development
npm run start # Run the compiled server (node dist/index.js)
npm run setup # Run interactive setup (node dist/setup.js)
npm run typecheck # Type-check without emitting (tsc --noEmit)
npm run test # Run unit tests (vitest run)
npm run test:watch # Run tests in watch mode
Build before running: npm run build && npm run start
The server uses stdio transport -- it is launched by an MCP client (Claude Desktop, Cursor, etc.), not run standalone in a browser.
Project Architecture
src/
├── index.ts # Entry point -- stdio transport, --setup flag handling
├── server.ts # createEmberServer() -- DB init, migration, tool registration
├── setup.ts # Interactive setup wizard for first-time configuration
├── db/
│ ├── schema.ts # SQLite schema creation (initializeDatabase)
│ ├── migrations.ts # Schema migration runner (runMigrations)
│ └── queries.ts # EmberQueries class -- ALL database operations
├── tools/
│ ├── index.ts # Tool barrel file
│ ├── conversation.ts # Start/end conversation tools
│ ├── capture.ts # Capture a message without annotation
│ ├── annotate.ts # Capture a message WITH emotional annotation
│ ├── readHistory.ts # Read conversation history
│ ├── readInheritance.ts# Read inheritance context for new sessions
│ ├── export.ts # Export conversation data
│ └── config.ts # Get/set Ember configuration
├── formatters/
│ ├── markdown.ts # Format conversation data as markdown
│ └── inheritance.ts # Format inheritance context for new AI instances
├── types/
│ └── index.ts # All TypeScript types (annotations, messages, configs)
└── utils/
└── config.ts # File paths, directory management (getDbPath, ensureEmberDir)
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.
- 5d ago First seen · 173 lines · 1,866 tokens per session scan A 964f5093a962
ember-memory CLAUDE.md is an instructions file published in the GitHub repository attilakiss9000/ember-memory (0 stars, last pushed 5mo ago), licensed MIT. It adds 1,866 tokens to every session, about $0.0093 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 2026-08-31.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.