llmtrim

fkiene/llmtrim

MCP server and proxy that compresses LLM prompts, tool output, and replies to cut token cost.

Tools

3 tools

Public tool metadata for what this MCP can expose to an agent.

llmtrim_compressCompresses an LLM API request payload.

Compresses an LLM API request payload.

No parameter schema in public metadata yet.

llmtrim_compress_textCompresses plain text.

Compresses plain text.

No parameter schema in public metadata yet.

llmtrim_statsReturns the same savings ledger as the status command.

Returns the same savings ledger as the status command.

No parameter schema in public metadata yet.

llmtrim

Local proxy that compresses LLM API traffic so you pay less. Same answers, smaller bill.

_{−31% input · −74% output · −66% round-trip cost
· 112 live A/B cases · ~5 ms/call · no model to load}

_{Using Claude Code? One install also gets you /sub
to serve it through CLIProxyAPI.}

_{Proxy · CLI · MCP · library (Python · Ruby · Swift · Kotlin · JS/WASM)}

llmtrim status: Overview savings dashboard, Sessions, Detail, and Sub routing tab (CLIProxyAPI presets, fallback hops, and model map)

Foundrymicrosoft-foundry/mcp-foundryCloud-hosted MCP endpoint for Foundry with tools for models, knowledge, evaluations, and agent workflows.248stars

YourMemorysachitrafa/yourmemoryPersistent memory for AI agents. Memories decay with time and strengthen on recall.244stars

Kilncodeofaxel/kilnSpawn an object into existence: describe it, and your agent designs it, checks it, and 3D prints it.242stars

Mpp32 Mcp Servermpp32/mpp32Payment layer for AI agents. One MCP, five protocols, thousands of paid APIs your agent can call.242stars

NotebookLM MCProomi-fields/notebooklm-mcpGoogle Gemini Notebook (ex NotebookLM) over MCP + a local REST API — cited answers, Studio, history240stars

UI Beatsnikhils4/ui-beatsMCP server for UI Beats. Let your coding agent search, read and install animated React components.235stars