pip install rlm-cli    # or: pipx install rlm-cli
uvx rlm-cli ask ...    # run without installing

export OPENROUTER_API_KEY=...  # default backend
export OPENAI_API_KEY=...      # for --backend openai
export ANTHROPIC_API_KEY=...   # for --backend anthropic

rlm ask <inputs> -q "question"

{"ok": true, "exit_code": 0, "result": {"response": "..."}, "stats": {...}}

{
  "result": {
    "response": "...",
    "tree": {
      "depth": 0,
      "model": "openai/gpt-4",
      "duration": 2.3,
      "cost": 0.05,
      "iterations": [...],
      "children": [...]
    }
  }
}

=== RLM Execution Summary ===
Total depth: 2 | Nodes: 3 | Cost: $0.0054 | Duration: 17.38s
Depth 0: 1 call(s) ($0.0047, 13.94s)
Depth 1: 2 call(s) ($0.0007, 3.44s)

rlm complete "prompt text"
rlm complete "Generate SQL" --json --backend openai

rlm search "query" [options]

rlm index .              # Index current dir
rlm index ./src --force  # Force full reindex

rlm doctor       # Check config, API keys, deps
rlm doctor --json

git diff | rlm ask - -q "Review for bugs"
git diff --cached | rlm ask - -q "Ready to commit?"
git diff HEAD~3 | rlm ask - -q "Summarize changes"

rlm ask . -q "Explain architecture"
rlm ask src/ -q "How does auth work?" --extensions .py

rlm search "database" --paths-only
rlm ask src/db.py -q "How is connection pooling done?"

rlm ask old.py new.py -q "What changed?"

backend: openrouter
model: google/gemini-3-flash-preview
max_iterations: 30

undefined

undefined

undefined

**Requirements:** OpenRouter backend (returns cost data in responses).

rlm complete "Complex task" --max-timeout 30

rlm ask . -q "Analyze" --max-tokens 10000

rlm complete "Write code" --max-errors 3

undefined

3. **Max budget exceeded** - Spending > `--max-budget` (exit code 20, error)
4. **Max timeout exceeded** - Time > `--max-timeout` (exit code 20, error with partial answer)
5. **Max tokens exceeded** - Tokens > `--max-tokens` (exit code 20, error with partial answer)
6. **Max errors exceeded** - Consecutive errors > `--max-errors` (exit code 20, error with partial answer)
7. **User cancellation** - Ctrl+C or SIGUSR1 (exit code 0, returns partial answer as success)
8. **Max depth reached** - Child RLM at depth 0 cannot recurse further

**Note on max iterations:** This is a soft limit. When exceeded, RLM prompts the LLM one more time to provide a final answer. Modern LLMs typically complete in 1-2 iterations.

**Partial answers:** When timeout, tokens, or errors stop execution, the error includes `partial_answer` if any response was generated before stopping.

**Early exit (Ctrl+C):** Pressing Ctrl+C (or sending SIGUSR1) returns the partial answer as success (exit code 0) with `early_exit: true` in the result.

undefined

The file is checked before each iteration and executed if modified.

export EXA_API_KEY=...  # Get from https://exa.ai

from rlm_cli.tools_search import exa, web

**exa.search() parameters:**
| Param | Default | Description |
|-------|---------|-------------|
| `query` | required | Search query |
| `limit` | 10 | Max results |
| `search_type` | "auto" | "auto", "neural", or "keyword" |
| `include_domains` | None | Only these domains |
| `exclude_domains` | None | Exclude these domains |
| `include_text` | False | Include full page text |
| `include_highlights` | True | Include relevant excerpts |
| `category` | None | "company", "research paper", "news", etc. |

**When to use exa.search() / web():**
- Finding external documentation, tutorials, articles
- Researching topics beyond the local codebase
- Finding similar pages to a reference URL

import sys
sys.path.insert(0, "/path/to/rlm-cli/rlm")        # rlm submodule
sys.path.insert(0, "/path/to/rlm-cli/pageindex")  # pageindex submodule

from rlm.clients import get_client
from rlm_cli.tools_pageindex import pi

**Indexing (costs $$$):**
```python

**Viewing structure (free after indexing):**
```python

**Finding node IDs:**
Node IDs are assigned sequentially ("0000", "0001", ...) in tree traversal order.
To see all node IDs, access the raw tree structure:
```python
import json
print(json.dumps(tree.raw["structure"], indent=2))

**pi.* API Reference:**
| Method | Cost | Returns | Description |
|--------|------|---------|-------------|
| `pi.configure(client)` | Free | None | Set rlm backend (REQUIRED first) |
| `pi.status()` | Free | dict | Check availability, config, warning |
| `pi.index(path=str)` | $$$ | PITree | Build tree from PDF |
| `pi.toc(tree, max_depth=3)` | Free | str | Formatted table of contents |
| `pi.get_section(tree, node_id)` | Free | PINode or None | Get section by ID |
| `pi.available()` | Free | bool | Check if PageIndex installed |
| `pi.configured()` | Free | bool | Check if client configured |

**PITree attributes:** `doc_name`, `nodes` (list of PINode), `doc_description`, `raw` (dict)
**PINode attributes:** `title`, `node_id`, `start_index`, `end_index`, `summary` (may be None), `children` (may be None)

**Notes:**
- `summary` is only populated if `add_summaries=True` in `pi.index()`
- `children` is None for leaf nodes (sections with no subsections)
- `tree.raw["structure"]` is a flat list; hierarchy is in PINode.children
- PageIndex extracts document structure (TOC), not content. Use page numbers to locate sections in the original PDF.

**Example output from pi.toc():**

undefined