Explore
MCP servers and skills: search, filter by where they run, and compare.
llm-councilamiable-dev
LocalThe LLM Council works together to answer your hardest questions
PythonMIT★ 45No key
llm-usage-mcpzhaoyue722
Local
MCP servers and skills: search, filter by where they run, and compare.
The LLM Council works together to answer your hardest questions
PythonMIT★ 45No key
a local-first, multi-provider tool that captures LLM API spend and exposes it to coding agents via the Model Context Protocol
PythonMIT★ 5No key
Local, cross-provider preflight checks for LLM integration changes
PythonMIT★ 3Few starsNo key
Universal LLM router for AI coding tools. Works with Claude Code, Cursor, Codex, Gemini CLI, Copilot and more. Free-first fallback chain cuts costs 35-80%.
PythonMIT★ 115No key
Easily create LLM tools and agents using plain Bash/JavaScript/Python functions.
SkillMIT★ 777No key
Portfolio of production remote MCP + A2A agents on getvda.ai — auth/JWT, structured output, LangChain orchestration, OpenTelemetry tracing — metered via x402.
Hosted by authorMIT★ 1Few starsNo key
A compounding knowledge base maintained by LLM agents — inspired by Karpathy's LLM Wiki pattern
PythonMIT★ 44No key
An MCP server to judge an LLM's responses
Node.jsMITFew starsNo key
Stop re-explaining your research to your AI agent. Persistent, LLM-maintained wikis that compound over time. Drop PDFs, URLs, YouTube - your agent remembers forever. Based on Karpathy's LLM Wiki patte
PythonMIT★ 61No key
Lightweight and portable LLM sandbox runtime (code interpreter) Python library.
PythonMIT★ 1.1kNo key
Public metadata for the hosted LLM Pulse MCP server
Hosted by authorMITFew starsNo key
Local-first memory cartridge for Claude, Cursor, and MCP-compatible AI agents.
PythonMIT★ 1Few starsNo key
Zero-dependency Python CLI + MCP server for comparing LLM API costs across 144 models and 22 providers (OpenAI, Anthropic, Google, Mistral, xAI, DeepSeek, Groq...)
PythonMIT★ 2Few starsNo key
A model-agnostic Message Control Protocol (MCP) server that enables seamless integration with various Large Language Models (LLMs) like GPT, DeepSeek, Claude, and more.
PythonMIT★ 6No key
An MCP server for Karpathy-style LLM wikis — deterministic, schema-blind, security-hardened.
PythonMIT★ 1Few starsNo key
PythonMIT★ 255No key
Local-first task memory for AI coding agents: durable task bundles, checkpoints, worktrees, MCP tools, hooks, and optional Jira import.
Node.jsMIT★ 9No key
One-stop handbook for building, deploying, and understanding LLM agents with 60+ skeletons, tutorials, ecosystem guides, and evaluation tools.
SkillMIT★ 555No key
A minimal eval harness for LLM model migrations: golden set with trap cases, LLM-as-judge, A/B on quality, latency and cost.
DockerMITFew starsNo key
LLM-powered knowledge base from your Claude Code, Codex CLI, Copilot, Cursor & Gemini sessions. Karpathy's LLM Wiki pattern — implemented and shipped.
PythonMIT★ 397No key
The knowledge compiler. Raw sources in, interlinked wiki out. Inspired by Karpathy's LLM Wiki pattern.
Node.jsMIT★ 2.2kNo key
MCP server: token cost math for LLM API calls, 69 models across 17 providers, prices verified by ComparEdge
Node.jsMIT★ 2Few starsNo key
Detect and redact PII and secrets (API keys, tokens, private keys) before text reaches an LLM. Placeholder/mask/hash redaction with reversible map. Apify Actor + stdio MCP server.
Hosted by authorMITFew starsNo key
Local OpenCode-backed LLM gateway for OpenAI, Anthropic, Gemini, and Responses API-compatible tools, with streaming and tool/function calling.
Node.jsMIT★ 74No key
Who stands behind it
