What is aleph AGENTS.md?

A repository instruction file for Aleph, an MCP server that lets language models explore large data through search, previews, and code without placing all of it in the conversation.

Use it when modifying Aleph, running its build and test checks, understanding its server and sandbox components, or contributing changes to the project.

It gives coding agents the project’s architecture, key files, setup commands, and testing expectations so they can work consistently in the repository.

aleph AGENTS.md — Instructions file by Hmbown

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/hmbown/aleph/agents-md

Clone the repo

git clone --depth 1 https://github.com/Hmbown/aleph

Made for: Codex, OpenCode.

Per session 594 This file is loaded in full into every session.

When invoked 594 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	$0.00594	$0.00594
Opus 5	$0.00297	$0.00297
Sonnet 5	$0.00119	$0.00119
Haiku 4.5	$0.00059	$0.00059

Measured 2d ago against content hash a310114c4750, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

aleph 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 2d 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 · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Project instructions for Codex and other AI agents working on this repository.

What is Aleph

Aleph is an MCP server implementing Recursive Language Models (RLMs). It loads large data into RAM as in-memory contexts, letting LLMs explore data via search/peek/code execution without consuming the context window. Published on PyPI as aleph-rlm.

Build & Test

pip install -e ".[dev,mcp]"
pytest tests/ -v          # ~426 tests, ~5s
ruff check aleph/ tests/  # linter

Tests use pytest-asyncio with asyncio_mode = "auto".

Architecture

MCP Server: aleph/mcp/local_server.py (~150K chars) — 30+ tools, recipe engine, sub-query orchestration
Core RLM Loop: aleph/core.py — load context, LLM loop, code execution, convergence
REPL Sandbox: aleph/repl/sandbox.py + helpers.py — sandboxed exec_python with 100+ helpers
Sub-Query: aleph/sub_query/ — CLI backends (kimi, claude, codex, gemini) and API backend
Recipes: aleph/mcp/recipes.py — declarative pipeline validation and estimation

Key Files

File	Purpose
`aleph/mcp/local_server.py`	MCP server, tool registration, recipe execution
`aleph/repl/helpers.py`	REPL helpers, Recipe DSL
`aleph/repl/sandbox.py`	Sandbox, async bridge, sub_query injection
`aleph/sub_query/cli_backend.py`	CLI sub-agent spawning
`aleph/sub_query/__init__.py`	Backend detection, SubQueryConfig
`aleph/mcp/recipes.py`	Recipe schema validation
`aleph/core.py`	Core Aleph RLM loop

Entry Points

Command	Module	Purpose
`aleph`	`aleph.mcp.local_server:main`	MCP server (primary)
`aleph-rlm`	`aleph.cli:main`	Installer/configurator

Gotchas

SandboxConfig timeout field is timeout_seconds (not timeout)
Load files with absolute paths when using MCP load_file tool
Non-zero CLI exit codes return failure (stdout content is not treated as success)
sub_query_batch/sub_query_map parallel path uses raw async fn to avoid event loop deadlock
MCP server needs /mcp restart in Claude Code or Codex restart after code changes

Read the full file on GitHub · 53 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.

2d ago First seen · 53 lines · 594 tokens per session scan A a310114c4750

Subscribe to this mod's changes

aleph AGENTS.md is an instructions file published in the GitHub repository Hmbown/aleph (213 stars, last pushed 4mo ago), licensed MIT. It adds 594 tokens to every session, about $0.0030 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.

Data and AI LLM Research Testing mcp recursive repl rlm

aleph AGENTS.md

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

AGENTS.md

What is Aleph

Build & Test

Architecture

Key Files

Entry Points

Gotchas

What this file has done since we first saw it

Other instructions, from other repositories

mq copilot-instructions.md

mq commit.instructions.md

mq general.instructions.md

mq rust-crate.instructions.md

mq testing.instructions.md

mq cli.instructions.md