Watched how we used GPT-5 and Claude Code with nano-agents here. What? A MCP Server for experimental, small scale engineering agents with multi-provider LLM support. Why?
What's inside
Watched how we used GPT-5 and Claude Code with nano-agents here.
What? A MCP Server for experimental, small scale engineering agents with multi-provider LLM support.
Why? To test and compare Agentic Capabilities of Cloud and Local LLMs across Performance, Speed, and Cost.
"It's not about a single prompt call anymore. It's about how well your agent chains together multiple tools to accomplish real engineering results on your behalf." - From our evaluation
Multi-Model Evaluation Flow - Watch 9 models (GPT-5, Claude Opus, Local GPT-OSS) running in parallel on the same M4 Max:
Model Comparison: GPT-5 vs Local Models - Surprising results: GPT-OSS 20B/120B running on-device with $0.00 cost:
cp ./.env.sample ./.env and fill out variablescp ./apps/nano_agent_mcp_server/.env.sample ./apps/nano_agent_mcp_server/.env and fill out variablesgit clone https://github.com/disler/nano-agentnano-agent to expose it for Claude Code (any mcp client)
cd nano-agent/apps/nano_agent_mcp_server./scripts/install.shuv tool install -e ..mcp.json.sample to .mcp.json to use nano-agent.mcp.json file that looks like this:{
"mcpServers": {
"nano-agent": {
"command": "nano-agent",
"args": []
}
}
}
nano-agent globally by running it this directory with{
"mcpServers": {
"nano-agent": {
"command": "uv",
"args": ["--directory", "apps/nano_agent_mcp_server", "run", "nano-agent"]
}
}
}
Now you can follow the Nano Agent Interaction section below to test out the nano agent.
There are three ways to interact with the nano agent.
uv run nano-cli run)
.mcp.json or equivalent configuration)
Remember, when running directly your current directory is where ever you run uv run nano-cli run from.
cd apps/nano_agent_mcp_server
# Test tools without API
uv run nano-cli test-tools
# Run with different models (provider auto-detected from model name)
uv run nano-cli run "List all Python files in the current directory" # gpt-5-mini (default)
uv run nano-cli run "Create a hello world script in python" --model gpt-5-nano
uv run nano-cli run "Summarize the README.md" --model gpt-5
# Test Anthropic models (requires ANTHROPIC_API_KEY)
uv run nano-cli run "Hello" --model claude-3-haiku-20240307 --provider anthropic
uv run nano-cli run "Hello" --model claude-sonnet-4-20250514 --provider anthropic
uv run nano-cli run "Hello" --model claude-opus-4-20250514 --provider anthropic
uv run nano-cli run "Hello" --model claude-opus-4-1-20250805 --provider anthropic
# Test local Ollama models (requires ollama service) (be sure to install the model first with `ollama pull gpt-oss:20b`)
uv run nano-cli run "List files" --model gpt-oss:20b --provider ollama
uv run nano-cli run "List files and count the total number of files and directories" --model gpt-oss:120b --provider ollama
# Verbose mode (shows token usage)
uv run nano-cli run "Create and edit a test file" --verbose
mcp nano-agent: prompt_nano_agent "Create a hello world script in python" --model gpt-5
mcp nano-agent: prompt_nano_agent "Summarize the README.md" --model claude-opus-4-1-20250805 --provider anthropic
mcp nano-agent: prompt_nano_agent "Read the first 10 lines and last 10 lines of the README.md" --verbose
etc...
@agent-nano-agent-gpt-5-mini "Create a hello world script in python"
@agent-nano-agent-gpt-5 "Summarize the <file name>"
@agent-nano-agent-claude-opus-4-1 "<insert agentic prompt here>"
@agent-nano-agent-gpt-oss-20b "<insert agentic prompt here>"
@agent-nano-agent-gpt-oss-120b "<insert agentic prompt here>"
@agent-nano-agent-claude-sonnet-4 "<insert agentic prompt here>"
@agent-nano-agent-claude-3-haiku "<insert agentic prompt here>"
In Claude Code call
/perf:hop_evaluate_nano_agents .claude/commands/perf/lop_eval_1__dummy_test.md
/perf:hop_evaluate_nano_agents .claude/commands/perf/lop_eval_2__basic_read_test.md
/perf:hop_evaluate_nano_agents .claude/commands/perf/lop_eval_3__file_operations_test.md
/perf:hop_evaluate_nano_agents .claude/commands/perf/lop_eval_4__code_analysis_test.md
/perf:hop_evaluate_nano_agents .claude/commands/perf/lop_eval_5__complex_engineering_test.md
The HOP/LOP pattern enables systematic parallel evaluation of multiple models:
Example: When you run /perf:hop_evaluate_nano_agents lop_eval_3__file_operations_test.md:
This architecture ensures fair comparison by using the same OpenAI Agent SDK for all providers, creating a true apples-to-apples benchmark.
Feel free to add/remove/improve tools as you see fit.
Nano-Agent tools are stored in nano_agent_tools.py.
Tools are:
read_file - Read file contentslist_directory - List directory contents (defaults to current working directory)write_file - Create or overwrite filesget_file_info - Get file metadata (size, dates, type)edit_file - Edit files by replacing exact text matches
View @disler’s profileSee what you can do with the Agentic Drop Zone in this video. Automated file processing system that monitors directories and triggers agents (Claude Code, Gemini CLI, Codex CLI) when files are dropped.
@dislerFAQ
nano-agent is a Claude Code plugin with hand-picked skills for development work, indexed on Flowy. Install it with the command on its page. Its skills do not fire on their own yet. Request auto-invocation to have Flowy route them as you prompt. Free and open source.
Is this plugin yours?
Claim it with GitHubSubmit a pluginPromote it