Parallelclaw

README

# ParallelClaw.ai

Execution layer for OpenClaw: multi-threaded AI workflows with multiple models and providers.

**Website:** https://parallelclaw.ai  
**MVP Blueprint:** https://parallelclaw.ai/mvp-v2.html

---

## Talk While Work — Pattern 1 of 4

Self-delegation skill for OpenClaw agents. The main agent decides on every query: direct reply or spawn a sub-agent.

- ⚡ **Zero config** — routing works immediately after install
- 🔥 **True parallelism** requires OpenClaw config check (see references/requirements.md)
- 💡 **Fast Main + Smart Sub-agents** — use fast model for main, powerful for sub-agents

### Installation

```bash
# Via ClawHub (when available)
clawhub install talk-while-work

# Or download and install manually
wget https://github.com/parallelclaw/parallelclaw/releases/latest/download/talk-while-work.skill
clawhub install ./talk-while-work.skill
```

### Manual Setup

```bash
git clone https://github.com/parallelclaw/parallelclaw.git
cd parallelclaw
python3 skills/talk-while-work/scripts/install.py
```

### Four Patterns

| # | Pattern | Status | Command |
|---|---------|--------|---------|
| 1 | **Talk While Work** | ✅ Ready | — |
| 2 | **Multi-Mind** (`/pc-ask`) | 📝 Planned | Consensus voting across N models |
| 3 | **Multi-Shard** (`/pc-scan`) | 📝 Planned | Sharded throughput for mass tasks |
| 4 | **Multi-Agent** (`/pc-do`) | 📝 Planned | Stateful sub-agents with tools |

### Architecture

- **Layer 1:** Skills (zero infrastructure, open source)
- **Layer 2:** MCP-server (key vault, cost tracking, rate-limit pool, cache)
- **Layer 3:** Self-tuning routing (adaptive model selection, closed-source moat)

### Business Model

- **Stage 1:** OSS Wedge (free plugin)
- **Stage 2:** ParallelClaw Cloud ($10-50/mo, hosted orchestrator, BYOK)
- **Stage 3:** Personal Agent Layer (Memex integration, local-first memory)

### Resources

- [Website](https://parallelclaw.ai)
- [MVP Blueprint](https://parallelclaw.ai/mvp-v2.html)