explaingit

smallpeanutbaby/little-peanut-agent

13TypeScriptAudience · developerComplexity · 4/5ActiveSetup · moderate

TLDR

Desktop AI workbench where models can read files, edit code, run commands, and plan work inside your project folder, not just chat in a browser.

Mindmap

mindmap
  root((repo))
    What it does
      Agent runs tasks
      Plan proposes changes
      Pipeline chains stages
      Multiple work modes
    Key features
      File read and edit
      Terminal commands
      Permission gates
      Memory store
    Tech stack
      Electron desktop
      React interface
      SQLite database
    Integrations
      OpenAI Anthropic
      Gemini MCP servers
      QQ Feishu DingTalk
    Use cases
      Automate code tasks
      Research and plan
      Review and refactor
      Multi-stage workflows

Things people build with this

USE CASE 1

Let an AI agent automatically refactor code, run tests, and commit changes in your project folder with your approval.

USE CASE 2

Have the agent research a feature request, propose a structured implementation plan, and review the code before you merge.

USE CASE 3

Chain a planner, executor, and reviewer together so the agent researches, implements, and validates changes in one workflow.

USE CASE 4

Track tasks, permissions, and conversation history for each project in a local database without sending data to the cloud.

Tech stack

TypeScriptElectronReactSQLiteNode.js

Getting it running

Difficulty · moderate Time to first run · 30min

Requires Node.js 22+ and npm 10+. You'll need an API key from OpenAI, Anthropic, or another supported model provider to run agents.

License information not provided in the explanation.

In plain English

Little Peanut is a desktop AI workbench built as an Electron application with a React interface and a local SQLite database. Its goal is not to be another chat client. The README frames it as a place where a model can actually do work inside a real project folder on your computer, rather than just answering questions in a browser tab. The repo is described as early development, with the basic skeleton in place and many features still being filled in. The app organises work into named modes. Chat is for light conversation, Agent runs tasks against a project, Plan is a read-only mode that does research and proposes a structured implementation plan without changing files, and Pipeline strings together a planner, executor, and reviewer in stages. There are also modes called Review, Writing, Code, Learning, Research, Brainstorm, Translate, and Summarize, each tuned for a different kind of request. The agent can call local tools such as file read and search, file edits, terminal commands, todo and task tracking, web search and fetch, lint reading, and a memory store. Tool calls go through a permission gate. Risky or destructive actions trigger an approval prompt, and permission rules can be saved per project or per session. The README is careful to say this is not a full sandbox, only a controllable boundary on a local machine. Little Peanut supports several model providers including OpenAI, Anthropic, Gemini, and OpenAI-compatible endpoints, with custom base URLs and API keys. It can also connect to MCP servers over stdio, SSE, or HTTP for extra tools. SQLite stores conversations, messages, tool runs, tasks, permission rules, a memory index, cost logs, model and provider config, and channel bot settings for QQ, Feishu, and DingTalk integrations. To run it you need Node.js 22 or newer and npm 10 or newer. The root folder is a small delegator, and the real Electron app lives in the src directory. Typical commands are npm install, npm run install:app, npm run dev to start, and npm run build or npm run dist to package.

Copy-paste prompts

Prompt 1
Set up Little Peanut on my machine, connect it to my OpenAI API key, and show me how to run an agent task on a local project folder.
Prompt 2
How do I create a custom mode in Little Peanut that chains a planner, executor, and reviewer to implement a feature end-to-end?
Prompt 3
Walk me through the permission system in Little Peanut, how do I approve or block file edits and terminal commands before the agent runs them?
Prompt 4
Connect Little Peanut to an MCP server to add custom tools, then use the agent to call those tools on my codebase.
Prompt 5
Show me how to export conversation history and tool run logs from Little Peanut's SQLite database for auditing or analysis.
Open on GitHub → Explain another repo

Generated 2026-05-22 · Model: sonnet-4-6 · Verify against the repo before relying on details.