递归语言模型处理服务

git clone https://github.com/richardwhiteii/rlm.git
cd rlm
uv sync

python -m venv .venv
source .venv/bin/activate
pip install -e .

# From the rlm directory
claude mcp add rlm -s user -- uv run --directory "$(pwd)" python -m src.rlm_mcp_server

export RLM_DATA_DIR="$HOME/.rlm-data"
export OLLAMA_URL="http://localhost:11434"

claude mcp add rlm -s user -- uv run --directory "$(pwd)" python -m src.rlm_mcp_server

{
  "mcpServers": {
    "rlm": {
      "command": "uv",
      "args": ["run", "--directory", "/path/to/rlm", "python", "-m", "src.rlm_mcp_server"],
      "env": {
        "RLM_DATA_DIR": "/path/to/.rlm-data",
        "OLLAMA_URL": "http://localhost:11434"
      }
    }
  }
}

cp -r .claude/hooks/ /Users/your_username/your-project/.claude/hooks/

cp -r .claude/skills/ /Users/your_username/your-project/.claude/skills/

rlm_auto_analyze(
    name="my_file",
    content=file_content,
    goal="find_bugs"  # or: summarize, extract_structure, security_audit, answer:<question>
)

# After loading a context
rlm_exec(
    code="""
import re
amounts = re.findall(r'\$[\d,]+', context)
result = {'count': len(amounts), 'sample': amounts[:5]}
""",
    context_name="bill"
)

{
  "result": {
    "count": 1247,
    "sample": ["$500", "$1,000", "$250,000", "$100,000", "$50"]
  },
  "stdout": "",
  "stderr": "",
  "return_code": 0,
  "timed_out": false
}

rlm_exec(
    code="""
import re
import json

# Find all email addresses
emails = re.findall(r'\b[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\.[A-Z|a-z]{2,}\b', context)

# Count by domain
from collections import Counter
domains = [e.split('@')[1] for e in emails]
domain_counts = Counter(domains)

result = {
    'total_emails': len(emails),
    'unique_domains': len(domain_counts),
    'top_domains': domain_counts.most_common(5)
}
""",
    context_name="dataset",
    timeout=60
)

rlm_sub_query(
    query="Find all security vulnerabilities",
    context_name="codebase",
    chunk_index=0,
    max_depth=2  # Allow sub-queries to further decompose
)

rlm_sub_query_batch(
    query="Extract key points",
    context_name="my_doc",
    chunk_indices=[0, 1, 2, 3],
    provider="ollama",  # Use local Ollama instead of default claude-sdk
    concurrency=4
)

# 1. Load a large document
rlm_load_context(name="report", content=<large document>)

# 2. Inspect structure
rlm_inspect_context(name="report", preview_chars=500)

# 3. Chunk into manageable pieces
rlm_chunk_context(name="report", strategy="paragraphs", size=1)

# 4. Sub-query chunks in parallel
rlm_sub_query_batch(
    query="What is the main topic? Reply in one sentence.",
    context_name="report",
    chunk_indices=[0, 1, 2, 3],
    concurrency=4  # uses claude-sdk by default
)

# 5. Store results for aggregation
rlm_store_result(name="topics", result=<response>)

# 6. Retrieve all results
rlm_get_results(name="topics")

# Load the full encyclopedia (11MB, ~2M tokens)
content = open("docs/encyclopedia/merged_encyclopedia.txt").read()
rlm_load_context(name="encyclopedia", content=content)

# Inspect
rlm_inspect_context(name="encyclopedia")
# → 11MB, 184K lines, ~2M tokens

# Chunk for processing
rlm_chunk_context(name="encyclopedia", strategy="paragraphs", size=30)

# Query across the corpus
rlm_sub_query_batch(
    query="Summarize the main topics in this section",
    context_name="encyclopedia",
    chunk_indices=[0, 50, 100, 150],
    provider="claude-sdk"  # or "ollama" for free local inference
)

# Filter for specific subject
rlm_filter_context(
    name="encyclopedia",
    output_name="botany",
    pattern="(?i)(botan|plant|flora|flower|genus)",
    mode="keep"
)

# Analyze filtered content
rlm_auto_analyze(
    name="botany_analysis",
    content=filtered_content,
    goal="answer:List all botanical articles with brief descriptions"
)

$RLM_DATA_DIR/
├── contexts/     # Raw contexts (.txt + .meta.json)
├── chunks/       # Chunked versions (by context name)
└── results/      # Stored sub-call results (.jsonl)

Claude Code
    │
    ▼
RLM MCP Server
    │
    ├─► claude-sdk (Haiku 4.5) ─► Anthropic API
    │
    └─► ollama ─► Local LLM (gemma3:27b, llama3, etc.)

Read src/rlm_mcp_server.py and list all RLM tools with their parameters and purpose.

Explain the chunking strategies available in rlm_chunk_context.
When would I use each one?

What's the difference between rlm_sub_query and rlm_sub_query_batch?
Show me the implementation.

Read src/rlm_mcp_server.py and explain how contexts are stored and persisted.
Where does the data live?

How does the claude-sdk provider extract text from responses?
Walk me through _call_claude_sdk.

What happens when I call rlm_load_context? Trace the full flow.

Load the README as a context, chunk it by paragraphs,
and run a sub-query on the first chunk to summarize it.

Show me how to process a large file in parallel using rlm_sub_query_batch.
Use a real example.

I have a 1MB log file. Walk me through the RLM pattern to extract all errors.

Read the test file and explain what scenarios are covered.
What edge cases should I be aware of?

How would I add a new chunking strategy (e.g., by regex delimiter)?
Show me where to modify the code.

How would I add a new provider (e.g., OpenAI)?
What functions need to change?

# Load the full encyclopedia
content = open("docs/encyclopedia/merged_encyclopedia.txt").read()
rlm_load_context(name="encyclopedia", content=content)

# Inspect
rlm_inspect_context(name="encyclopedia")
# → 11MB, 184K lines, ~2M tokens

# Chunk for processing
rlm_chunk_context(name="encyclopedia", strategy="paragraphs", size=30)

# Query across the corpus
rlm_sub_query_batch(
    query="Summarize the main topics in this section",
    context_name="encyclopedia",
    chunk_indices=[0, 50, 100, 150],
    provider="claude-sdk"  # or "ollama" for free local inference
)

# Filter for specific subject
rlm_filter_context(
    name="encyclopedia",
    output_name="botany",
    pattern="(?i)(botan|plant|flora|flower|genus)",
    mode="keep"
)

# Analyze filtered content
rlm_auto_analyze(
    name="botany_analysis",
    content=filtered_content,
    goal="answer:List all botanical articles with brief descriptions"
)