v0.10.0 · MIT License
@codapult/guard is local-first, model-agnostic architecture guardrail software for AI coding agents. Use it to detect architectural drift, enforce approved software architecture rules, and check code changes in JavaScript and TypeScript projects.
v1.0.0 · MIT License
Enables AI assistants and agents to send WhatsApp, SMS, and email messages, verify OTP codes, and run campaigns through an account-based messaging platform.
v1.3.2 · MIT License
Enables AI coding agents to extract structural C# contracts from files and build solution-wide dependency graphs, so they can navigate code and assess change impact without reading entire files.
v0.2.0 · GPL 3.0
Enables an AI agent to set up, run and verify engineering simulations through typed tools — creating or importing cases, setting boundary conditions, running solvers, checking convergence, verifying results against references, and rendering output, with edits appearing live in the GUI. It exposes no shell or code-execution tool.
v0.1.0 · Apache 2.0
Gives AI coding agents on-demand security playbooks, a code scanner they can run on their own output, and live lookups against CISA KEV, NVD and OSV so they verify threats instead of guessing. Runs locally with no API keys or accounts, exposing skills, tools and a secure-build prompt to Claude Code, Codex, Cursor or any MCP client.
v0.1.1 · MIT License
Enables agents to search and look up companies in a local mirror of India's MCA master data, decode CINs offline, and validate GSTIN structure and checksums. Every field carries provenance and explicitly flags missing or stale data instead of fabricating it.
v0.2.0 · MIT License
Enables MCP clients such as Claude Desktop, Claude Code and Cursor to OCR local scanned PDFs and images in 100+ languages, returning the extracted text or a searchable PDF. It also lets agents check document status, list recent documents and delete them.
v0.1.0 · MIT License
A free, read-only server that lets users diagnose production AI-agent risks: it flags over-privileged API keys from permission descriptions, scans code snippets for the signals that prevent duplicate execution, and explains guard patterns such as idempotency keys, approval gates, outboxes, and circuit breakers. It makes no network calls or writes, and rejects inputs that look like real secrets.