rashbox 0.1.0

# rashbox

Fast Rust+WASM bash sandbox for LLM agents. Mount files, run real Unix commands in an isolated WASM sandbox, let an AI agent explore and analyze them.

## What it does

- **WASM isolation** -- all commands run inside a Wasmtime sandbox (no host access)
- **23 Unix commands** compiled to a single 258KB WASM binary
- **Multi-LLM support** -- Claude, OpenAI, Ollama, llama-server, llama.cpp
- **Agent loop** -- LLM calls tools (exec, write_file, done), results fed back automatically
- **Pipes** -- `cat /in/file | grep error | awk '{print $1}' | sort | uniq -c`
- **Safety limits** -- max steps, max tokens, memory limits

## Quick start

```bash
# Analyze files with Claude
export ANTHROPIC_API_KEY=sk-...
rashbox src/*.rs --goal "Find bugs and security issues"

# Use a local model (Ollama)
rashbox --llm ollama --model qwen3.5:27b data.csv --goal "Analyze this dataset"

# Use llama-server
rashbox --llm llama --model my-model sales.csv access.log

# Interactive shell (no LLM)
rashbox --shell myfiles/

# Copy agent output files locally
rashbox --output-dir ./results src/ --goal "Generate a report"
```

## Available commands

| Category | Commands |
|----------|----------|
| File viewing | `cat` `-n`, `head`, `tail`, `ls` `-alR` |
| Search | `grep` (regex: `^.$*+?[...]`), `find` `-name -type` |
| Text processing | `sed` `s///g`, `awk` (fields, math, conditions), `cut`, `tr`, `sort`, `uniq` |
| Analysis | `wc`, `csv_stats` (column types, min/max/mean/sum, uniques), `calc` (arithmetic) |
| Comparison | `diff` `-u` (unified diff) |
| File ops | `cp` `-r`, `mv`, `rm` `-r`, `mkdir` `-p`, `tee`, `echo`, `pwd` |

### Highlights

**awk** -- field extraction, math, conditions:
```bash
awk '{print $1, $3}' file              # print fields
awk -F, '{sum+=$4} END {print sum}'    # sum a CSV column
awk '$2 > 100 {print $1}' file         # conditional filter
awk 'NR>1 {print $1}' file             # skip header
```

**csv_stats** -- instant CSV profiling:
```bash
csv_stats sales.csv
# Rows: 24  Columns: 6
# -- date (string) --
#   non-null: 24  null: 0  unique: 16
# -- units (numeric) --
#   min: 25  max: 220  mean: 111  sum: 2670
```

**calc** -- arithmetic (LLMs can't do math):
```bash
calc '150 * 12.99 + 89 * 24.50'       # => 4133.0
calc '(2 + 3) * 4 ^ 2'                # => 80
```

**grep** with regex:
```bash
grep '^ERROR' log.txt                  # lines starting with ERROR
grep 'status_[0-9]+' file             # regex patterns
```

## Architecture

```
rashbox (Rust binary)
  |-- Agent loop (LLM <-> tools)
  |-- Sandbox (Wasmtime + WASI preview1)
  |     |-- /in   (read-only mounted files)
  |     |-- /out  (writable output)
  |     |-- /skills (read-only, from ~/.skills/)
  |     '-- tools.wasm (258KB, 23 commands)
  '-- LLM backends
        |-- Claude (Anthropic API)
        |-- OpenAI (+ compatible: Ollama, llama-server)
        '-- llama.cpp (optional, via feature flag)
```

## CLI options

```
rashbox [OPTIONS] <FILES>...

  --llm <BACKEND>       claude, openai, ollama, llama, llamacpp, noop
  --model <MODEL>       Model name (default: claude-sonnet-4-6)
  --api-key <KEY>       API key (or set ANTHROPIC_API_KEY / OPENAI_API_KEY)
  --base-url <URL>      Custom endpoint for OpenAI-compatible APIs
  --goal <GOAL>         Task for the agent
  --system <PROMPT>     Override system prompt (prefix with @ to read from file)
  --max-mem <MB>        Sandbox memory limit (default: 40)
  --max-steps <N>       Max agent tool calls (default: 50)
  --max-tokens <N>      Max total tokens (default: 0 = unlimited)
  --shell               Interactive shell mode (no LLM)
  --output-dir <DIR>    Copy /out files here when done
```

## Building

```bash
# Build the WASM tools (requires wasm32-wasip1 target)
rustup target add wasm32-wasip1
cd wasm-tools && cargo build --release --target wasm32-wasip1
cp target/wasm32-wasip1/release/rashbox-tools.wasm ../wasm/tools.wasm

# Build rashbox
cargo build --release
```

## Testing

```bash
cargo test --test sandbox_test    # 23 integration tests
```

## License

MIT