What is memex AGENTS.md?

Repository-wide instructions for contributors to Memex, a local-first system that remembers coding conversations. They define rules for project scope, privacy, fact sources, provenance, synchronization, and database updates.

Use them when changing Memex code, importing or querying conversations, extracting facts, handling project scope, or maintaining its synchronization and privacy rules.

They keep memory data traceable and prevent different projects or unverified information from being mixed together.

How BongSuCHOI/memex configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to BongSuCHOI/memex. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/BongSuCHOI/memex/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/BongSuCHOI/memex

Made for: Claude Code, 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/bongsuchoi/memex/agents-md/github.svg)](https://agentmods.dev/instructions/bongsuchoi/memex/agents-md)

Your own site

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

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/bongsuchoi/memex/agents-md"><img src="https://agentmods.dev/badge/instructions/bongsuchoi/memex/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,017 This file is loaded in full into every session.

When invoked 2,017 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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 5.1	$0.02017	$0.02017
Opus 5.5	$0.00807	$0.00807
Sonnet 5.5	$0.00403	$0.00403
Haiku 4.5	$0.00202	$0.00202

Measured 1mo ago against content hash ec02ffbf3c31, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

memex 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 1mo 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.

AGENTS.md · 206 lines

How it starts

The opening of the file, as written. The whole thing — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Memex contributor rules

Memex is a Codex-native, local-first long-term memory system. This file contains repository-wide guardrails for humans and coding agents. Keep it short: detailed behavior belongs in the owner documents under docs/.

Core invariants

$CODEX_HOME/sessions rollout JSONL is the default conversation source. Never modify source rollouts; archive/index/database state is derived.
Canonical absolute session_meta.cwd is project identity. Do not infer project identity from basename, archive path, display name, or process cwd.
Enforce project/global/all scope at every query, import, graph traversal, and relation-write boundary.
Preserve exact fact provenance to source exchanges. Human assertions and allowlisted local repo/Git/test observations may be learnable; Memex recall, assistant synthesis, external/unknown output, and unverified generated output are searchable but not learnable evidence.
Keep authoritative lineage (source_exchange_ids) separate from local, non-authoritative interpretive lineage (fact_context_dependencies). The semantic verifier reports context it actually used; server validation canonicalizes that set without promoting context to authority.
Preserve exchanges.rowid on update. Extraction uses rowid watermarks.
Extraction claim, fact/provenance writes, saved counts, and watermark advance must commit atomically or remain retryable.
Model-backed work uses isolated local codex exec only. Default model: gpt-5.6-luna with no reasoning flag. Resolution order is an explicit per-call option, then MEMEX_CODEX_MODEL / MEMEX_CODEX_REASONING, then <data root>/models.json, then the built-in default. A provider that refuses the request envelope is the config error class: park the job with memory_jobs.hold_reason, spend no attempt, and let a fixed selection resume it. Never retry, split, or fail input on a configuration error.
User overlays (<data root>/overlays/) may only suppress. The recall gate fails open on a broken overlay; extraction fails closed and holds. Neither the rule hash nor the overlay ever enters the extraction scheduling key or a sync generation.
Automatic lifecycle work must be bounded, retry-safe, and observable.

Read the full file on GitHub · 206 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.

1mo ago Changed · +23 lines · +298 tokens per session ec02ffbf3c31
1mo ago Changed · +6 lines · +120 tokens per session b414e939a6bf
2mo ago Changed · +5 lines · +59 tokens per session 50907a4c4361
2mo ago First seen · 172 lines · 1,540 tokens per session scan A 9e2612d44f03

Subscribe to this mod's changes

memex AGENTS.md is an instructions file published in the GitHub repository BongSuCHOI/memex (0 stars, last pushed 1mo ago), licensed MIT. It adds 2,017 tokens to every session, about $0.0081 per session on Opus 5.5. 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.

Memory and context RAG and vectors codex knowledge-graph mcp personal-knowledge-management

memex AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
memex AGENTS.mdBongSuCHOI/memex	Instructions file	0	1mo ago	MIT	A	2,017	Claude Code, Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

memex: Instructions file for Claude Code