Reactive AI Agent Framework
A reactive AI agent framework for creating agents that use tools to perform tasks, with support for multiple LLM providers and MCP servers.
Directory
A reactive AI agent framework for creating agents that use tools to perform tasks, with support for multiple LLM providers and MCP servers.
Agency OS delivering 26 specialized AI roles over MCP with a real-time retro CRT Pixel Office visualizer and multi-provider live LLM workspace.
Zero-tool-call codebase intelligence for Claude Code and MCP clients. Automatically injects the right code context, functions, callers, and call chains, before…
Provides context optimization tools to extract targeted information rather than processing large files and command outputs in their entirety.
Local, privacy-preserving PII detection & redaction over MCP: the model works on shape (schemas, synthetic twins, masked output) while local code touches the…
Provides persistent long-term memory capabilities through semantic indexing, retrieval, and search functions with support for multiple LLM providers and…
A TypeScript-based server that provides a memory system for Large Language Models (LLMs), allowing users to interact with multiple LLM providers while…
Bridges Claude with locally running LLM models via LM Studio, enabling users to leverage private models through Claude's interface while maintaining local…
Structured task management system that breaks down complex projects into manageable tasks with progress tracking, user approval checkpoints, and support for…
Extracts and transforms webpage content into clean, LLM-optimized Markdown by removing non-essential elements while preserving key metadata.
Integrates with Supabase to persist and retrieve LLM interaction styles using emojikeys, enabling consistent personalized experiences across conversations.
Enables multiple LLMs to share and analyze each other's responses to the same prompt, facilitating collaborative problem-solving and multi-perspective analysis…
Enables AI assistants to interact with web browsers through a FastAPI server for web browsing, content extraction, and automation tasks with configurable LLM…
Enables LLM applications to interact with macOS through AppleScript.
Dynamically scan and analyze potentially malicious URLs using the [urlDNA](https://urlDNA.io)
Share code context with LLMs via Model Context Protocol or clipboard.
Enables LLM clients to interact with any MediaWiki wiki using the Model Context Protocol.
Remediate vulnerabilities found by Contrast products using LLM and Coding Agent capabilities.
36 tools for dependency graphs, architecture analysis, security scanning, refactoring, and CI tracking for LLM agents
Integrates LLM applications with documentation sources using the Model Context Protocol.
Backpressure and concurrency control middleware for FastMCP. Prevents server overload from LLM tool-call storms with configurable limits and JSON-RPC errors.
A universal REPL session manager supporting Python, Node.js, Ruby, and more, with session management and LLM-assisted recovery.
Provides Go language updates and best practices in a structured Markdown format for LLM coding agents.
GPU infrastructure control plane + per-agent LLM FinOps. 74 tools. Deploy, scale, track cost per agent, enforce budgets. MIT license.