Search

Enables step-level routing of AI workflows by decomposing tasks, selecting the best model per step within constraints, executing steps, and providing full execution traces.

Local semantic code context engine — indexes large repos and serves a codebase-retrieval MCP tool

High performance Redis MCP Server using node-redis

Telegram notification MCP server for Claude Code

RingDev MCP server — gives AI coding agents a phone. Calls the developer when the agent gets stuck.

AI-powered Minecraft build concept generator MCP server

MCP server for Praesentire — bilingual financial news sentiment (English + Traditional Chinese) as a Claude tool.

Local MCP context engine for Codex with Gemini Embedding 2 support.

https://github.com/catfish-1234/sessionmem

No description available

An extensible MCP server: a registry of paper-backed quantitative trading methods plus a deterministic, no-LLM decision helper. Research tooling only — not financial advice.

Switch between AI providers (Anthropic, GLM, Alibaba Qwen, OpenRouter, Ollama, Gemini) for Claude Code and OpenCode

Vendor-independent natural-language browser automation CLI. Run plain-English objectives against local Chrome, LambdaTest/TestMu, BrowserStack, any CDP endpoint, or Playwright MCP.

Agentic Memory Layer for AI-Assisted Development. Automatically documents your code changes, architecture decisions, and development intent.

MCP server for JobHunter - query and manage job postings from any AI assistant

CLI tool for structured software specifications. Validate .dog files, compile .dag graphs, query via MCP.

Estimate token budgets and daily costs for loop engineering patterns. By cadence, readiness level (L1/L2/L3), and coding agent tool.

Local agent skills and client resources for the SWQT remote MCP service.

TurboLLM — local LLM platform: run any inference engine auto-tuned to your GPU, with a web UI and OpenAI/Anthropic-compatible API. Point Claude Code at your own machine in one command.

MCP server for managing llms.txt documents