Aleph

"What my eyes beheld was simultaneous, but what I shall now write down will be successive, because language is successive." — Jorge Luis Borges, "The Aleph" (1945)

MCP server for recursive LLM reasoning over documents. Instead of cramming context into one prompt, the model iteratively explores with search, code execution, and structured thinking—converging on answers with citations.

Quick Start

pip install aleph-rlm[mcp]
aleph-rlm install        # auto-detects Claude Desktop, Cursor, Windsurf, VS Code
aleph-rlm doctor         # verify installation

{
  "mcpServers": {
    "aleph": {
      "command": "aleph-mcp-local"
    }
  }
}

How It Works

┌──────────────────────────────────────────────────────────────────┐
│  CONTEXT  →  stored once as `ctx`                                │
└──────────────────────────────────────────────────────────────────┘
                                 │
                                 ▼
┌──────────────────────────────────────────────────────────────────┐
│  🔧 80+ TOOLS                                                    │
├──────────────────────────────────────────────────────────────────┤
│  extract_*  │ emails, IPs, money, dates, URLs, functions, TODOs │
│  grep/head  │ filter lines, sort, uniq, columns                 │
│  search     │ regex with context, contains, find_all            │
│  stats      │ word_count, frequency, ngrams, diff               │
│  transform  │ replace, split, before/after, normalize           │
│  validate   │ is_email, is_url, is_json, is_ip                  │
│  convert    │ to_json, to_snake_case, slugify                   │
└──────────────────────────────────────────────────────────────────┘
                                 │
                                 ▼
┌──────────────────────────────────────────────────────────────────┐
│  📋 EVIDENCE  →  cite() accumulates provenance with line numbers │
└──────────────────────────────────────────────────────────────────┘
                                 │
                        ┌────────┴────────┐
                        ▼                 ▼
                    Continue          Finalize
                  (loop back)    (answer + citations)

The model sees metadata, not full text. It writes Python to explore iteratively. Evidence auto-accumulates.

Example

You: Load this contract and find all liability exclusions

[AI calls load_context, search_context, cite(), evaluate_progress, finalize]

AI: Found 3 liability exclusions:
    1. Section 4.2: Consequential damages excluded (lines 142-158)
    2. Section 7.1: Force majeure carve-out (lines 289-301)
    3. Section 9.3: Cap at contract value (lines 445-452)

    Evidence: [4 citations with line ranges]

When to Use

# Examples
emails = extract_emails()  # Auto-extracts from ctx
money = extract_money()    # Finds $1,234.56 patterns
errors = grep("ERROR")     # Filter lines
word_frequency(top_n=10)   # Most common words

aleph-rlm install              # Interactive installer
aleph-rlm install <client>     # Install to specific client
aleph-rlm uninstall <client>   # Remove from client
aleph-rlm doctor               # Verify installation

Development

git clone https://github.com/Hmbown/aleph.git
cd aleph
pip install -e '.[dev,mcp]'
pytest  # 190 tests

Recent Changes

v0.2.0 (December 2025)

80+ new REPL helpers for document analysis:

• 16 extraction functions (emails, IPs, money, dates, phones, URLs, paths, versions, UUIDs, functions, classes, TODOs, log levels)
• 8 statistics (word/line/char count, word frequency, n-grams)
• 12 grep-like line operations (head, tail, grep, sort, uniq, columns)
• 15 text manipulation (replace, split, before/after, truncate, normalize)
• 6 pattern matching (contains, count_matches, find_all)
• 4 comparison (diff, similarity)
• 11 collection utilities (dedupe, flatten, group_by, frequency)
• 7 validators (is_email, is_url, is_ip, is_uuid, is_json)
• 11 converters (to_json, to_snake_case, slugify)

30+ new builtins: map, filter, iter, next, repr, chr, ord, pow, divmod, hash, id, callable, frozenset, bytes, slice...

6 new allowed imports: random, string, hashlib, base64, urllib.parse, html

v0.1.3 (December 2025)

• Added type builtin to sandbox
• Added NameError and AttributeError exceptions

Research

Inspired by Recursive Language Models by Alex Zhang and Omar Khattab.

License

MIT