Search

Automated product update emails with per-product voice powered by LLM drafts

Drop-in replacement for ChatGoogleGenerativeAI that automatically fixes schema compatibility issues with MCP tools and Gemini API

Returns real-time cost estimates and model recommendations for LLM API calls. Compares pricing across OpenAI, Anthropic, Google, and open-source providers. Helps agents optimize spend and stay within budget constraints. Hosted stdio bridge package.

AST-powered architecture intelligence layer for AI coding agents. Multi-language structural analysis via tree-sitter.

Epistemic cache-control layer for MCP servers. Prevents LLM stale context hallucination via RFC 7234 semantics and causal domain invalidation.

One config to rule them all — Practical standard layer for multi-LLM development. Sync MCP servers, skills, and AGENTS.md across Codex, Claude Code, Gemini CLI, Cursor, Copilot, Antigravity, Windsurf, and OpenCode.

AI gateway — multi-provider, multi-channel personal AI assistant with memory

Hush: A Semantic Security Gateway for AI Agents. Redacts PII from prompts and tool outputs locally before they hit the cloud.

A React MCP-style AI chatbot component with tool calling and backend integration

Architectural Coverage Engine — zero-dependency incremental architectural analysis for Laravel projects. Measures consistency, infers patterns, evaluates security baselines, and exposes an MCP server for LLM integration.

ContextForge CLI - Generate production-ready MCP servers from docs, OpenAPI, GraphQL & codebases. Multi-URL, private docs, generate_code tool. Local + cloud LLMs (BYOK). Archestra & Claude Desktop ready.

TypeScript MCP client with Anthropic Claude integration

An efficient task manager. Designed to minimize tool confusion and maximize LLM budget efficiency while providing powerful search, filtering, and organization capabilities across multiple file formats (Markdown, JSON, YAML)

AttackDataGraph for autonomous penetration testing

Open-source CI failure triage for humans and agents — smart log parsing, flake detection, structured JSON, MCP server.

MCP server for Winnow neural code pruning - reduces LLM context size 23-38%

Generate production-ready MCP servers from docs, OpenAPI, GraphQL & codebases. Multi-URL, private docs, generate_code tool. Local + cloud LLMs (BYOK). Archestra & Claude Desktop ready.

Autopilot AI orchestration — auto-plan, parallelize, and execute with ownership enforcement

MCP Chain of Draft (CoD) Prompt Tool - A Model Context Protocol tool for efficient reasoning

The Universal Agent Data Layer - Consolidate 50+ tools into 1 dynamic navigable tool