#llm

28 MCP tools that give Claude, Cursor and any MCP client the live web — scrape, crawl, search, real Google rank, change tracking, document parsing, plus an autonomous agent that researches from a plain-English prompt with no URLs. Clean Markdown and schema-validated JSON, not raw HTML. Local-Ollama extraction by default. MIT, 1,000 free credits.

A Typescript library to use LLM providers APIs in a unified way.

DeepSeek API SDK for .NET developer

A stateless, zero-latency reverse proxy for real-time PII redaction in LLM streams.

Pest Browser Evals

No repository description published.

CLI tool to export and analyze workout data from the Liftoff fitness app — workouts, exercise stats, bodyweight trends

CLI tool for reconciling transactions between two CSV sources (bank statements, Stripe, etc.)

Intelligent Scientific Agent for Materials Design

Multi-provider coding-agent orchestration in a verified loop: a critic on a different model signs off before work ships. Claude Code, Codex, Gemini, aider, Copilot, opencode, local.

Ultra cost-effective terminal AI coding assistant with excellent token cache hit rate. Built in ~10K lines of Go, it uses DeepSeek by default with multiple modes and sandbox.

Azure AI platform bridge for Symfony AI

Monolog bridge for AI Mate - provides log search and analysis tools

Official Go implementation of the UTCP

The full-stack open-source agentic ecosystem.

Provenance-aware memory for AI agents.

An AI Hedge Fund Team

No repository description published.

CLI tool to turn a Git repository or local directory into a single text digest for LLMs

Adaptive fork of Pi coding agent for self-evolving agent harness experiments

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

Governed, durable-ready AI agent (chat + tool-calling + governance + HITL) for AdonisJS — part of the Agora ecosystem

orchestrateur universel agents ia multi modeles ultra rapide et modulaire via protocole mcp pour piloter claude-code gemini-cli qwen-cli Kilo/Cline et openclaw sans limite, GLM Minimax Kimi Ollam etc Ready

Let Claude (or any LLM) actually watch a video — scene-aware, deduplicated frames + transcript, from a URL or local file. Runs locally, MIT.

Open-source Vibe Testing suite: an MCP server for the coding agent you already run, a VS Code review cockpit, and CI. Your agent explores your app and crystallizes each flow into a plain @playwright/test spec you own — record == replay, runs in CI with zero AI.

No repository description published.

No repository description published.

🧠 Local-first LLM state branching & debugging. Capture, visualize, branch, and regression-test LLM calls as a DAG. Free & local via Ollama, any OpenAI-compatible API, MCP for agents. Zero config.

OpenCode stops working if a model goes in timeout or there are errors, this plugin fixes those issues

Jamshid: CLI tool for managing multiple Claude Code profiles. Switch between personal Anthropic, enterprise keys, and OpenRouter configurations across projects.