13,736 mods in this category, of every kind an
agent can take. Each one carries what it costs per session, what the
scan found, and whether it is the original.
FreeGLM API — cloud media understanding by model family: VL vision chat, OCR, and grounding on DashScope Qwen or Zhipu GLM-4.6V-Flash; Omni A/V, ASR, and segmentation on DashScope.
Local sidecar giving any tool grounded, cited, routed AI — Ollama or OpenRouter, no API key required. Runs locally from the llm-sidecar Python package.
★not rated 1 19d agoA
tokens not measured
originalMIT
MCP Server that gives DeepSeek (and other text-only LLMs) vision capability via third-party OpenAI-compatible vision APIs. Runs locally from the deepseek-vision-mcp Python package.
★not rated 1 22d agoA
tokens not measured
originalMIT
Open-source prompt optimizer plugin for terminal AI agents: cuts token waste via a behavior protocol, local prompt compression, ask-or-assume clarifying questions, and cheapest-capable model routing. Runs locally from the promptopt npm package.
★not rated 1 21d agoA
tokens not measured
originalMIT
Semantic compression layer for numerical data - token-efficient LLM context with Anthropic Advanced Tool Use support. Runs locally from the semantic-frame Python package.
★not rated 1 9mo agoA
tokens not measured
originalMIT
Train a LoRA voice adapter for pocket-tts and keep the result on your own disk, not an API subscription. Runs locally from the ownvoice-cli Python package.
★not rated 1 4d agoA
tokens not measured
originalMIT
Multi-model AI gateway for MCP clients — routes prompts to Gemini, OpenAI, Anthropic, xAI, DeepSeek, Moonshot, OpenRouter, and local models with conversation memory. Runs locally from the vox-mcp Python package. Needs 8 environment variables to run.
★not rated 1 2mo agoA
tokens not measured
originalApache-2.0
MCP server for text2sql-framework. Lets any MCP-compatible assistant (Claude Desktop, Cursor, Goose, etc.) ask a SQL database questions in natural language. Runs locally from the text2sql-mcp Python package. Needs 4 environment variables to run.
★not rated 1 1mo agoA
tokens not measured
originalMIT
An MCP server for semantic documentation search and retrieval using vector databases to augment LLM capabilities. Runs locally from the @hannesrudolph/mcp-ragdocs npm package.
★not rated 1 1y agoA
tokens not measured
originalMIT
A local retrieval service built around MCP, a standard way for tools to connect to an agent. Its description does not specify what information it retrieves or which searches it supports.
MCP server "langchain-documentation-server" as configured in LiteObject/langchain-mcp-server. Runs locally from the langchain-documentation-server Python package.