What is mnema AGENTS.md?

Repository instructions for mnema, including its shared memory and agent-coordination setup, project structure, commands, and operating rules.

Use it to start the local server, build the TypeScript project, run smoke tests, check context quality, use the command-line interface, and understand the MCP and REST server layout.

It gives coding agents a common set of rules and commands to follow, reducing confusion when several agents work with the same project memory and services.

mnema AGENTS.md — Instructions file for Codex and OpenCode by fthsrbst: Repository instructions for mnema, including its shared memory and…

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add instructions/fthsrbst/mnema/agents-md

Clone the repo

git clone --depth 1 https://github.com/fthsrbst/mnema

Made for: Codex, OpenCode.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/fthsrbst/mnema/agents-md.svg)](https://agentmods.dev/instructions/fthsrbst/mnema/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/fthsrbst/mnema/agents-md"><img src="https://agentmods.dev/badge/instructions/fthsrbst/mnema/agents-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 1,936 This file is loaded in full into every session.

When invoked 1,936 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.01936	$0.01936
Opus 5	$0.00968	$0.00968
Sonnet 5	$0.00387	$0.00387
Haiku 4.5	$0.00194	$0.00194

Measured 3d ago against content hash 3639b624dd2e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mnema AGENTS.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 3d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

mnema CLAUDE.md — 97% identical, 6 lines differ

AGENTS.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

mnema — Agent Talimatları

Bu dosya CLAUDE.md ile eş içeriklidir (Codex/opencode gibi AGENTS.md okuyan agentlar için). Birini güncellerken diğerini de güncelle.

Tüm AI agentların ortak hafızası: MCP + REST üzerinden hafıza, RAG, proje mapleri ve agent koordinasyonu. Raspberry Pi 5'te systemd servisi olarak çalışır; istemciler Tailscale/LAN üzerinden bağlanır. Detaylı mimari ve fazlar: PLAN.md.

Komutlar

npm run dev — sunucuyu lokal başlat (http://127.0.0.1:8033)
npm run build — tsc → dist/
npm run smoke — uçtan uca smoke test (geçici DB ile; GEMINI_API_KEY= boş bırakarak çalıştır)
npm run smoke:cloud — SaaS/Cloud smoke paketi (saas-security + tenant + router + rate-store + hosted)
npm run eval:context — context kalite regresyonu (gerçek hub DB'sine karşı; HUB_DB_PATH ile hedef DB ver)
npm run hub -- <komut> — CLI'ı kaynak koddan çalıştır (örn. npm run hub -- status)

Yapı

src/core/ — DB (SQLite + sqlite-vec + FTS5), Gemini embedding, chunker, hibrit arama (RRF), memory/document/project/session/presence işlemleri. Sunucudan bağımsız, saf kütüphane.
src/server/ — Express: /mcp (Streamable HTTP, stateless), /api (REST), /health. Auth: HUB_AUTH_TOKENS (scope'lu tokenlar) veya legacy HUB_TOKEN; ikisi de boşsa kapalı (local_dev).
src/saas/ — hosted Cloud profili: Supabase JWT doğrulama, Postgres RLS tenancy, Paddle billing, Valkey rate-limit. Community (self-host) kodundan izole.
src/cli/ — hub komutu. REST üzerinden konuşur. hub recall --hook (UserPromptSubmit) ve hub bridge --hook (SessionStart) Claude Code hook'larıdır: sessizce başarısız olur. hub sync skill/MCP/kural dosyalarını cihaza dağıtır (~/.claude/CLAUDE.md, ~/.config/opencode/AGENTS.md, ~/.codex/AGENTS.md yönetilen blokları dahil).
skills/, prompts/ — DB authority (assets tablosu). Bu klasörler yalnızca ilk kurulum SEED'idir; sonraki yazımlar (skill_save) DB'ye düşer ve sync ile yayılır — git gerekmez.
Agent presence (agent_presence tablosu, src/core/presence.ts) — advisory koordinasyon, KİLİT DEĞİL. Aşağıdaki "Agent koordinasyon protokolü"ne bak.
Ortak MCP sunucu kayıt defteri (mcp_servers tablosu, src/core/mcp-registry.ts) — hangi MCP sunucuların kullanılacağı hub'dan yönetilir; yazımlar sync ile tüm cihazlara yayılır. hub mcp-servers listeler; MCP mcp_server_register/list/get/delete veya REST /api/mcp-servers yazar. env/headers düz metin senkronlanır — secret koymayın.
evals/ — context_get golden suite; kanonik canlı bilgi durumuna (proje: mnema) karşı yazılır.
deploy/ — Pi kurulum/güncelleme/yedek scriptleri + systemd unit; deploy/cloud/ hosted compose.
Agent Intelligence Platform (src/core/tasks.ts, capabilities.ts, messaging.ts, hygiene.ts, compaction.ts, learning.ts, worker.ts, webhooks.ts) — görev kuyruğu, agent yetenek kaydı, agent-agent mesajlaşma, hafıza hijyeni, bilgi sıkıştırma, ders çıkarma, webhook'lar ve async job kuyruğu. Detay ve tam MCP tool listesi: docs/agent-platform.md.

Read the full file on GitHub · 85 lines

Changes

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.

3d ago First seen · 85 lines · 1,936 tokens per session scan A 3639b624dd2e

Subscribe to this mod's changes

mnema AGENTS.md is an instructions file published in the GitHub repository fthsrbst/mnema (2 stars, last pushed 3d ago), licensed MIT. It adds 1,936 tokens to every session, about $0.0097 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.

Building agents Memory and context ai-agents claude cli codex local-first mcp

mnema AGENTS.md

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

Copies of this mod

How it starts

mnema — Agent Talimatları

Komutlar

Yapı

What this file has done since we first saw it

Other instructions, from other repositories

siyuan AGENTS.md

veritas-kanban AGENTS.md

ima2-gen AGENTS.md

gini-agent AGENTS.md

paxm AGENTS.md

engraphis CLAUDE.md