#llm

AI Agent Evaluator & Red Team Platform

Build interactive AI agents in Elixir with OTP supervision, middleware composition, human-in-the-loop approvals, sub-agent delegation, and real-time Phoenix LiveView integration. Built on LangChain.

A rich semantic bot detection engine.

MCP server + CLI giving AI agents 50 spreadsheet tools for .xlsx — live-recalc formulas (~390 Excel functions), repair broken references & external links, read/write, diff, and audit. Works in Claude Code, Cursor, Codex, and any MCP client.

Advanced CLI tool that scans your hardware and tells you exactly which LLM or sLLM models you can run locally, with full Ollama integration.

A Vitest reporter that keeps results of test runs focused for LLMs

323個の即戦力AI専門エージェント — Claude Code/Cursor/Copilot等に対応。SIer/受託開発/SaaS/製造DX/公共分野など日本市場向け114個のオリジナルを含む、agency-agents日本語コミュニティ版

Framework-neutral DOCX engine with React/Vue editors, Nuxt integration, and agent tooling

Craft CMS MCP accelerates AI-assisted development by giving your AI assistant direct access to your Craft installation's content architecture, database schema, and configuration.

Understand your agent traces. Identify failures, get improvements.

A Go framework for the microagents architecture with dynamic discovery — specialized agents and tools that register their capabilities with a shared registry, find each other by logical name at runtime, and coordinate without a central conductor.

A Go framework for chat-network agents: an IRC bouncer, browser UI, and bot orchestrator in one static binary, with an optional LLM hookup for AI features. Stewarded by xShellz.

Turn PDF, DOCX, tables, and figures into citation-ready reusable agent assets and Foam/LightRAG wikis — MCP SDK 2 server plus VS Code extension

Storybook Addon for DTCG design tokens

Whale — blazingly fast, terminal-first AI coding agent for DeepSeek. ~98% prompt cache hit rate, 1M context, MCP tools, dynamic workflows.

MCP Fusion - The TypeScript framework for secure MCP servers.

Reviewable finding, proposal, redaction, and decision-history tooling for coding-agent learning loops.

Encrypt PII, not meaning. Locally.

Turn your company's scattered knowledge into AI ready Books ✨

Manage configs for Claude Code, Codex, Gemini CLI, Goose, and Amp from one repo — symlinks, merge pipeline, profile inheritance, cross-machine sync

Like Lighthouse for your agent harness - verify your CLAUDE.md/AGENTS.md, skills & hooks are real, then test and measure they actually work. Claude Code + Codex.

Self-improving agents, governed. Areev is the substrate for adaptive agents — agents that get better from their own history, under human authority, in steps you can inspect, undo, and re-measure.

An open-source MCP server that turns any LLM into an Intelligent Tutoring System. 50 years of cognitive science, MIT licensed.

The lightweight framework for building agents

Expose djangorestframework-services services and selectors as a Model Context Protocol (MCP) 2025-11-25 Streamable HTTP server.

Gradient descent, but the parameters are agents — a parallel, asynchronous framework for self-evolving agents (skills, prompts, harnesses). Diffs are the gradients; the aggregator is the optimizer.

No repository description published.

One config for every AI coding agent — cross-tool config + a cognitive substrate (memory, blast-radius, guardrails) for Claude Code, Codex, Cursor, Gemini, Aider, and more.

Local-first, inspectable memory for coding agents: durable context across sessions and repositories, code-aware recall, bi-temporal history, MCP, and a self-hosted WebUI.

🔄 A versatile utility library for converting various file formats to Markdown