Fable Mode

Agents that think before they write.

       

Fable Mode is an open-source control plane for AI coding agents.

It makes an agent deliberate, produce evidence, and survive adversarial review before it earns permission to write to your workspace. The gates are mechanical, not prompt advice: no timer, no proof, no write access.

See it work

A session starts locked. Confidence does not unlock it.

>>> session = create_session('demo-refactor', budget='2 min')
    state=INIT  execution_locked=True  can_execute_code=False

>>> session.unlock_execution('the plan looks fine, let me write code now')
    PermissionError: HARD TIME-LOCK VIOLATION: Execution unlock rejected!
    The immutable 2.0m authority budget has not elapsed yet
    (Remaining: 1m 59s / 120.0s).

The same gates guard every phase: evidence receipts for claims, a five-vector red-team swarm for code, and a sealed record of what was verified.

Install

pip install fable-engine

Point your agent at the MCP server:

// Claude Code: claude mcp add fable-engine -- python -m fable_engine.server
// Cursor: ~/.cursor/mcp.json
{
  "mcpServers": {
    "fable-engine": {
      "command": "python",
      "args": ["-m", "fable_engine.server"]
    }
  }
}

Python 3.10+, zero runtime dependencies. PyPI package publishing is in progress.

How it works

1. Think — Time-locked deliberation. The agent cannot write until the timer ends.
2. Prove — Claims need real evidence (tool receipts, hashes, invariants).
3. Attack — A red-team swarm tries to break the code.
4. Write — Only then is the workspace unlocked.

What it is not

• Not a claim of flawless code. It is a checkable workflow, not a guarantee.
• Not a bigger prompt. The locks are enforced by the engine, not by wording.
• Not a framework lock-in. It speaks MCP and runs beside your current agent.

Docs

• V1 → V2 migration
• V2 architecture
• System 3 (experimental)

Contributing

Issues and pull requests are welcome. See CONTRIBUTING.md.