Files
Pizza 52d5c368fa init: project scaffold with SmallClawPlus brain files
- Brain: STATUS, PLAN (4 milestones), ARCH (module design), CONTEXT, SESSIONS, DEPS
- Learnings: ERRORS.md, LEARNINGS.md (empty)
- Code: cli.py stub, pyproject.toml, __init__.py
- README with architecture diagram and queue format
- Queue format: EDIT/CREATE/DELETE/TEST actions
2026-04-02 21:19:38 +00:00

1.9 KiB

TinyClaw

Orchestrator that makes 1-4B parameter language models capable of real project work.

How it works

Tiny models (1-4B) can't plan, can't manage state, and can't reliably use tools. But they can edit a single function when given clear instructions.

TinyClaw exploits this: a driver script handles everything the model can't (file extraction, state management, verification, git), and the model just generates code edits.

User request --> Big model decomposes into atomic tasks (QUEUE.md)
                    |
                Driver reads next task
                    |
                Extracts target function (Python AST)
                    |
                Builds minimal prompt (~500 tokens)
                    |
                Tiny model returns edited function
                    |
                Verifier checks syntax/imports
                    |
            Pass? --> Splice back, git commit, next task
            Fail? --> Retry (max 3), then skip

Usage

# Process a task queue
tinyclaw run --queue QUEUE.md --model qwen/qwen3.5-9b

# Check progress
tinyclaw status

# Auto-decompose a feature (uses big model)
tinyclaw plan "add user authentication with JWT tokens"

Queue Format (QUEUE.md)

EDIT auth.py validate_login "reject empty password strings"
EDIT main.py handle_request "add validate_token() call before processing"
CREATE config.py - "define AUTH_SECRET from environment variable"
TEST auth.py - "verify login rejects empty passwords"

One task per line: ACTION file function "instruction"

Install

pip install -e .

Design Principles

  • The model is the hands, not the brain
  • One function per task, one task per commit
  • Under 500 tokens per prompt (fits in 2k context)
  • Verify everything, trust nothing
  • Auto-revert on failure

Status

Early development. Milestone 1 (core loop) in progress.