Metadata-Version: 2.4
Name: writ-cli
Version: 0.1.2
Classifier: Development Status :: 3 - Alpha
Classifier: Environment :: Console
Classifier: Intended Audience :: Developers
Classifier: Programming Language :: Rust
Classifier: Topic :: Security
Summary: The writ binary: authorization and provenance for AI agents. One policy file, one tamper-evident ledger, any agent.
Keywords: ai-agents,authorization,policy,audit,mcp,claude-code
Author-email: Bhaskar Gurram <gurrambhaskar.ai@gmail.com>
License-Expression: Apache-2.0
Requires-Python: >=3.8
Description-Content-Type: text/markdown; charset=UTF-8; variant=GFM
Project-URL: Homepage, https://writ-omega.vercel.app
Project-URL: Issues, https://github.com/writ-agent/writ/issues
Project-URL: Source, https://github.com/writ-agent/writ

# writ

**Nothing runs without a writ.** Every tool call an AI agent makes is checked
against one policy file (`writ.yaml`: allow / deny / ask / redact) before it
runs, and written to a hash-chained, tamper-evident ledger after.

This package installs the prebuilt `writ` command-line tool:

```bash
pip install writ-cli      # or: npm install -g @writ-agent/cli
writ --version
writ integrate claude-code   # govern every Claude Code tool call
writ run -- claude           # or launch an agent inside a kernel write boundary
writ verify                  # check the ledger's hash chain
```

For Python agent frameworks (LangGraph, OpenAI Agents SDK, Claude Agent SDK)
install [`writ-sdk`](https://pypi.org/project/writ-sdk/), which depends on this
package.

Documentation, policy reference and threat model:
https://github.com/writ-agent/writ

