io.github.withwrit/writai

writ

Verified · 2 mo ago

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
2 mo ago
github stars
1
last commit
2 mo ago
archived
no
license
MIT
in registry since
2026-10-01

github.com/withwrit/pywrit

reaai

REA

Verified · 30 days ago

Reverse engineer anything from your terminal or agent with one CLI and MCP server.

hand-reviewed291k stars232k dl/wkchecked 30 days ago

rufloai

Ruflo

Verified · 6 days ago

Agent teams, swarms, memory and hooks for Claude Code and Codex, served over MCP.

hand-reviewed81k stars72k dl/wkchecked 6 days ago

claude-flowai

claude-flow

Verified · 2 mo ago

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

hand-reviewed73k stars19k dl/wkchecked 2 mo ago

tldrawai

tldraw

Verified · 2 mo ago

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

hand-reviewed50k starschecked 2 mo ago

codebase-memory-mcpai

Codebase Memory

Verified · 2 mo ago

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

hand-reviewed45k stars12k dl/wkchecked 2 mo ago

openseoai

OpenSEO

Verified · 2 days ago

Keyword research, site audits, rank tracking and AI visibility for your AI agent.

hand-reviewed28k starschecked 2 days ago