Rasmus Rasmussen's picture
Open to Collab

Rasmus Rasmussen

theprint

AI & ML interests

Small model experiments and homespun datasets.

Recent Activity

liked a dataset 2 days ago
AdamCodd/unreal-engine-5-raw
reacted to Nymbo's post with 🚀 4 days ago
🚀 I've just shipped a major update to the https://huggingface.co/spaces/Nymbo/Tools MCP server: the `Agent_Terminal`, a single "master tool" that cuts token usage by over 90%! Anthropic found 98.7% context savings using code execution with MCP, Cloudflare published similar findings. This is my open-source implementation of the same idea. # The Problem Traditional MCP exposes every tool definition directly to the model. With 12 tools, that's thousands of tokens consumed *before the conversation even starts*. Each tool call also passes intermediate results through the context window — a 10,000-row spreadsheet? That's all going into context just to sum a column. # The Solution: One Tool to Rule Them All `Agent_Terminal` wraps all 12 tools (`Web_Search`, `Web_Fetch`, `File_System`, `Generate_Image`, `Generate_Speech`, `Generate_Video`, `Deep_Research`, `Memory_Manager`, `Obsidian_Vault`, `Shell_Command`, `Code_Interpreter`) into a single Python code execution gateway. Instead of the model making individual tool calls, it writes Python code that orchestrates the tools directly: ``` # Search for Bitcoin price result = Web_Search("current price of bitcoin", max_results=3) print(result) ``` Don't know what tools are available? The agent can discover them at runtime: ``` print(search_tools('image')) # Find tools by keyword print(usage('Generate_Image')) # Get full docs for a specific tool ``` The individual direct tool calls are all still there, but they can be disabled if using the `Agent_Terminal`. Try it now - https://www.nymbo.net/nymbot
updated a dataset 4 days ago
theprint/Alpaca-Docs-n-Summaries
View all activity

Organizations

Hugging Face Discord Community's profile picture Chronicler Games's profile picture