Code

Distills your sessions or any text corpus into a dated history of how its subject changed.

Repository-native protocol and local MCP server for Work, Docs, History and durable project Memory.

CLI and MCP server for Loci, a local-first documentation knowledge base for AI agents.

Webhook capture and replay, delivery pipes, and signed multi-agent rooms. No signup to start.

Cross-harness communication and shared work-state for AI coding agents.

CLI tool and MCP server that tests MCP servers for spec compliance

ctxloom — The Universal Code Context Engine. A local-first MCP server providing intelligent code context via hybrid Vector + AST + Graph search with token-efficient Skeletonization.

Ensemble testing for front-end web quality

Zero-trust MCP file writes, AST edits, ast-bro intelligence, hooks, and agent skills

GitLab tools plugin for OpenCode - provides GitLab API access for merge requests, issues, pipelines, and more

Local evidence-first web debugging MCP server for Codex, Claude Code, and other MCP clients.

Local read-only MCP server for Kikita UI documentation.

YuanXinMCP (元信MCP) - the pre-install security scanner for Agent skills, exposed as a stdio MCP server: scan_skill (dir/package -> verdict + findings), generate_badge (audited badge), gate_check (CI gate), get_report (JSON/Markdown). Local offline static s

LoomWeaver: open-source plugin platform for Angular workbenches. The MCP server: scaffolding and validation as tools, so an AI assistant in any product repo can build weavers without a checkout.

MCP server for managing Thally docs and tracing product changes into evidence-backed updates for human review.

Universal calendar management for AI coding agents - CLI + MCP server + interactive TUI

An intelligent MCP server that serves as a guardian of development knowledge, providing AI assistants with curated access to latest documentation and best practices

The agent runtime for React Native and Expo: an MCP server that sees the app the way React sees it, knows which file produced each element, acts without coordinates, and proves it works. Local only, zero dependencies.

The independent local harness for AI-repaired Playwright tests — it runs the tests itself, so a green run can't be faked.

45 judges that evaluate AI-generated code for security, cost, and quality with built-in AST.