io.github.withwrit/writai

writ

Verified · today

Commit-time policy checks for AI agent writes (ALLOW/DENY/STEP_UP) with a tamper-evident audit log.

Install

claude mcp add writ -- uvx writ-mcp

Requires: WRIT_API_KEY, WRIT_SPONSOR_TOKEN, WRIT_BASE_URL

Our take

Adds commit-time policy checks for AI agent file writes, including allow, deny, step-up decisions, and a tamper-evident audit log. It is relevant for teams introducing guardrails around coding agents, and the security-oriented design is promising, though adoption appears early and policy configuration quality will matter.

reviewed by hand · 2026-10-02

Something wrong or dead here? Report it

Verification record

last verified
today
github stars
1
last commit
today
archived
no
license
MIT
in registry since
2026-10-01

github.com/withwrit/pywrit

More in ai

browse all →
claude-flowai

claude-flow

Verified · 14 days ago

AI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.

hand-reviewed73k stars19k dl/wkchecked 14 days ago

tldrawai

tldraw

Verified · 15 days ago

Draw and visually collaborate with your agents on tldraw's canvas.

hand-reviewed50k starschecked 15 days ago

codebase-memory-mcpai

Codebase Memory

Verified · 5 days ago

Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.

hand-reviewed45k stars12k dl/wkchecked 5 days ago

openmetadata-mcpai

OpenMetadata

Verified · 33 days ago

Official OpenMetadata MCP: 21 read and write tools for search, lineage, data quality, governance.

hand-reviewed15k starschecked 33 days ago

mobilerunai

mobilerun

Verified · 17 days ago

Control real Android and iOS devices with LLM agents — tap, swipe, type, automate flows.

hand-reviewed9.4k starschecked 17 days ago

praisonaiai

PraisonAI

Verified · 4 days ago

AI Agents Framework with Self Reflection and MCP support

hand-reviewed9.1k starschecked 4 days ago