llm — independent software & tools
-
Wardian
Modular, local-first desktop habitat for agents, workflows, and reusable context.
-
cardinal-harness
Sort and rank anything with LLMs — pairwise ratio judgements fitted into calibrated cardinal scores with uncertainty, active pair selection, budget control, and full cost receipts. Rust library + CLI.
-
agentic-ai
🤖 Explore AI agent architectures with agentic-ai, featuring ReAct agents, reflection-based designs, and modular LLM integrations using LangChain and LangGraph.
-
nanobot
AI Agent Platform built in Rust — Multi-model, MCP tools, 14+ channel integrations. Self-host or use teai.io
-
agent-sessions
🚀 Monitor your Claude Code sessions effortlessly on macOS with real-time status updates and quick access features for a streamlined development experience.
-
@andersmyrmel/vard
Lightweight prompt injection detection for LLM applications. Zod-inspired chainable API for prompt security.
-
@ericthered926/duckduckgo-mcp-server
A Model Context Protocol (MCP) server for DuckDuckGo web and news search
-
mcp-evals
GitHub Action for evaluating MCP server tool calls using LLM-based scoring
-
@nlux/core
nlux is JavaScript and React library for building conversational AI interfaces, with support for OpenAI, Hugging Face, and more.
-
task-master-ai
A task management system for ambitious AI-driven development that doesn't overwhelm and confuse Cursor.
-
tokenlens
A lightweight registry of LLM model information, like name and context sizes, for building AI-powered apps.
-
@tokenlens/core
Core types and registry utilities for TokenLens (model metadata).
-
@tokenlens/fetch
Typed client for models.dev to fetch model catalogs with friendly errors.
-
@tokenlens/helpers
Helpers for context windows, usage normalization, compaction, and cost estimation.
-
@tokenlens/models
Tree-shakeable static models.dev catalog split by provider for TokenLens.
-
tokenx
Fast token estimation at 96% accuracy of a full tokenizer in a 2kB bundle