High-Perf Tools for LM Studio — Full Developer Toolbelt for Local AI Agents

Keywords: lm studio plugin, ai developer tools, local code execution, python ai agent, cpp compilation ai, git ai tools, file system ai, agent zero, autonomous ai, no cloud

A high-performance LM Studio plugin for Python and C++ development, filesystem operations, git, web research, and autonomous Agent Zero capabilities.

Who This Is For

Developers building autonomous AI agents that need to actually run code, not just talk about it
Engineers wanting a local AI with filesystem, git, and shell access from LM Studio
Power users who need Python execution, C++ compilation, and persistent memory in their LLM workflow
Anyone replacing cloud-based coding assistants with a fully local, zero-telemetry alternative

Features

Filesystem (11 tools)

Tool	Description
`read_file`	Read files with optional line range selection
`write_file`	Write or append to files, creating parent dirs
`replace_in_file`	Surgical find-and-replace (literal or regex)
`diff_preview`	Preview a write or replace as a unified diff without modifying anything
`delete_path`	Delete files or directories
`move_path`	Move or rename files/directories
`copy_path`	Copy files within the workspace
`list_directory`	List files with metadata, filtering, recursive walk
`create_directory`	Create directories (with parents)
`file_info`	File metadata: size, line count, permissions
`search_in_files`	grep-like search across workspace files

Execution (4 tools)

Tool	Description
`run_command`	Execute arbitrary shell commands
`run_python_code`	Run a Python snippet (temp file)
`run_python_file`	Run an existing Python script
`get_environment`	Report Python version, PATH, installed tools

Python Dev (7 tools)

Tool	Description
`analyze_python`	AST analysis: imports, classes, functions, globals
`format_python`	Format with ruff or black
`lint_python`	Lint with ruff or pylint, optional auto-fix
`run_tests`	Run pytest with filtering and verbosity control
`pip_install`	Install Python packages
`pip_list`	List installed packages (supports `--outdated`)
`type_check_python`	Run mypy, optional `--strict` mode

C++ Dev (7 tools)

Tool	Description
`compile_cpp`	Compile with clang++/g++, sanitizers, custom flags
`run_binary`	Execute a compiled binary
`compile_and_run`	Compile and immediately run a snippet or file
`format_cpp`	Format with clang-format
`analyze_cpp`	Static analysis with clang-tidy
`cmake_build`	CMake configure + build
`get_cpp_info`	Compiler and tool version report

Research (2 tools)

Tool	Description
`fetch_url`	Fetch a URL and return plain text (HTML stripped)
`search_web`	DuckDuckGo search, returns titles + snippets

Git (8 tools)

Tool	Description
`git_status`	Working-tree status
`git_diff`	Working-tree or staged diff
`git_log`	Commit history with filtering
`git_show`	Show a specific commit
`git_branches`	List local and remote branches
`git_stage`	Stage files (git add)
`git_commit`	Create a commit (optionally stages files first)
`git_init`	Initialise a new repository

Agent Zero (10 tools)

Tool	Description
`memory_save`	Persist a fact or solution across conversations
`memory_recall`	Keyword-search persistent memory
`memory_list`	List all saved memories
`memory_delete`	Delete a memory by id or key
`list_models`	List models loaded in LM Studio
`spawn_agent`	Delegate a task to an autonomous sub-agent
`create_tool`	Create a reusable Python tool saved to the workspace
`call_tool`	Call a previously created tool by name
`list_custom_tools`	List all dynamically created tools
`delete_tool`	Delete a dynamic tool

Installation

Or during development:

Configuration

Open Settings → Plugins → high-perf-tools in LM Studio.

Setting	Default	Description
Workspace Path	(cwd)	All file operations are sandboxed here
Python Interpreter	(system python3)	Conda env name (e.g. `misc`) or full binary path
Allow Shell Commands	off	Enables `run_command`
Allow Python Execution	off	Enables `run_python_code`, `run_python_file`, `run_tests`
Allow C++ Compilation	off	Enables `compile_cpp`, `run_binary`, `compile_and_run`, `cmake_build`
Allow pip install

Python / Conda Environment

Set Python Interpreter to:

Blank — uses system python3
A conda env name (e.g. ml) — the plugin searches common conda prefix directories (~/miniconda3/envs, ~/anaconda3/envs, etc.) and falls back to conda run -n <name> if not found

All Python tools, pip, pytest, and dynamic tools share this single interpreter.

Agent Zero

Persistent Memory

The plugin stores memories as JSON at .agent_memory/memory.json inside the workspace. Memories survive across conversations. The model can tag and query them with memory_save / memory_recall.

Sub-agents (`spawn_agent`)

Sub-agents run an autonomous tool-call loop against LM Studio's OpenAI-compatible API.

RAM-aware model selection:

One model loaded (low-RAM devices) → the same model is reused with a different system prompt. Zero extra RAM.
Sub-Agent Model ID set and loaded → uses the dedicated sub-agent model.

The sub-agent has access to: read_file, write_file, list_directory, run_python_code, run_command, memory_save, memory_recall.

Set allow_tools=false for pure generation tasks (faster, no tool-call loop).

Dynamic Tools (`create_tool` / `call_tool`)

The model can write Python functions and register them as persistent tools:

Tools are saved as Python scripts in .agent_tools/ inside the workspace and can be called by name in future conversations. Arguments are passed as JSON via stdin; the function returns a string or JSON-serialisable value.

Error Handling

Every tool is wrapped in safe_impl(). When a tool throws, the model receives a structured JSON response it can parse and retry:

The prompt preprocessor injects tool-call rules on the first turn, reminding the model to output valid JSON and handle tool_error responses.

Security

Workspace sandbox: all file paths are resolved and validated against the configured workspace root. Paths that escape (e.g. ../../etc/passwd) are rejected.
Private IP blocking: fetch_url blocks requests to localhost, RFC 1918, and link-local addresses.
Execution opt-in: shell, Python, C++, and pip tools are disabled by default and must be explicitly enabled in settings.

Peer Plugin: altra/web-search

If the altra/web-search plugin is also installed and loaded, fetch_url and search_web are automatically omitted from this plugin's tool list at startup. The web-search plugin's fetch_and_read and search tools handle those instead.

This avoids duplicate web-fetching tools in the LLM's context when both plugins are active.

Requirements

LM Studio with plugin support
Node.js 18+
lms CLI (npm install -g @lmstudio/lms)
Optional: Python / conda, gcc/clang++, cmake, ruff, black, mypy, pytest

high-perf-tools