Leanfare

io.github.pouriaetabPublished by GitHub account pouriaetabv0.15.3Updated Nov 6, 2026

Makes your Claude plan last longer: hands reading and drafting to cheaper or free models.

VerifiedSTDIODesktop onlyDeveloper ToolsAI & ML

Overview

AI-generated overview

Leanfare is a local MCP server that plans a task and hands simple parts, like reading and drafting, to cheaper or free models so a Claude plan lasts longer.

What you can do
  • Plan and run a task: split a prompt into parts, pick a model for each, start, check status and stop runs
  • Delegate work: hand off parts to outside models and get the answers back with a receipt
  • Ask, grade and estimate: query models, rate answers, and estimate cost before spending
  • Tune behavior: set the delegation level, choose how many helpers a prompt starts, and pick which providers work may go to
  • Review usage: read a report of what each prompt used and saved, and see spend and available models
  • Manage local models and helpers: configure local models and Claude helper models
When to use it
Useful when you work in Claude Desktop, Cowork or Claude Code and hit plan limits, and want routine reading, searching and drafting done by free or cheaper models while Claude keeps the hard parts.
Requirements
Runs locally over stdio as a desktop app (macOS, Windows or Linux), installed via a shell or PowerShell install script, a Claude Code plugin, or a .mcpb file. Needs at least one model to hand work to: API keys or Ollama models already on the computer, or free accounts connected in Settings for providers such as ChatGPT, Gemini, Groq, OpenRouter, Mistral and Cloudflare. A small local web app runs at 127.0.0.1:4747.
Before you install
It uses the API keys already on your computer and connects third-party provider accounts, and requests go from your computer to those AI companies, so prompts may be sent to outside providers. It can spend money on paid models; check the estimate, spend and report views. It is described as early and changing weekly. It reads usage numbers, and keeps hand-off text only if you opt in.

Installation

In SourceWeft

  1. Open Leanfare in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

Leanfare

[Latest release] [Tests] [License]

Leanfare makes your Claude plan last longer. Claude keeps the hard parts of a task and hands the simple ones, like reading files, searching and drafting, to free or cheaper models. You keep working in Claude as before.

[A plan as Claude shows it in Cowork: each part of the task, the model it runs on, its tokens and its cost]

Leanfare is early and changes every week. If something breaks, report a bug; Settings, Report a problem, fills in your version. Questions and ideas go to Discussions.

How it works

  1. You ask Claude for something, in Claude Desktop, Cowork or Claude Code.
  2. Claude asks Leanfare for a plan. Leanfare splits the task into parts and picks a model for each: free or cheap models for reading and drafting, Claude's own models for the hard parts.
  3. Leanfare sends its parts to those models and hands the answers back. Claude does the rest, checks every answer, and answers you.
  4. Leanfare's report shows what each prompt used and what it saved.

Get started

On macOS or Linux, paste this in Terminal:

sh
curl -fsSL https://raw.githubusercontent.com/pouriaetab/leanfare/main/install.sh | sh

On Windows, paste this in PowerShell:

powershell
powershell -ExecutionPolicy Bypass -c "irm https://raw.githubusercontent.com/pouriaetab/leanfare/main/install.ps1 | iex"

Then type leanfare in the same window. In the page that opens, press Turn on Leanfare, then restart Claude. That's all.

Leanfare needs at least one model to hand work to. It uses the API keys and Ollama models already on your computer, and Settings connects free ones with one press each: ChatGPT (a free account works), Gemini, Groq, OpenRouter, Mistral and Cloudflare.

Other ways in: the Claude Code plugin (/plugin marketplace add pouriaetab/leanfare, then /plugin install leanfare@leanfare), or a one click .mcpb file for Claude Desktop from the latest release.

What you see

The report. Every prompt with its main model, Claude's helpers and the outside models, and what was saved. By prompt or by model, over any days.

[The Usage report, by prompt: each prompt's main model, Claude's helpers, the outside models, and what was saved]

Claude's own models. Leanfare picks the Claude model for each helper Claude starts, from llmledger's ratings and prices. As the ratings stand: Fable 5.1 for the hardest parts, Opus 5.5 for high effort, Sonnet 5.5 for medium and Haiku 5.5 for light code. Cowork can ask you to approve each helper, so you choose how many a prompt starts: one per part, one per prompt, or none.

[Settings, Claude's own models: the order, each kind's pick, and how many helpers]

Three settings

  1. Level, from 1 (Off) to 5 (All it can): how much Claude hands to Leanfare first.
  2. Helpers: one per part, one per prompt (the default), or none.
  3. Where work may go: only this computer, or the providers you ticked.

Leanfare picks the rest for you. The guide explains every part.

What's inside

Leanfare is an MCP server with a small web app, both on your computer. Claude connects to it over stdio, like any MCP server. It is TypeScript on Bun, with no runtime dependencies.

FileWhat it is
src/mcp.tsThe MCP server and its tools
src/cli.tsThe leanfare command
src/server.tsThe app and its API, at http://127.0.0.1:4747
src/planner.tsPlans: the parts, a model for each, the runs
src/delegate.tsHand offs to outside models, each with a receipt
src/claudeladder.tsClaude's own models, in order
ui/The app's screens

The MCP tools: plan, plan_run, plan_status, plan_stop, delegate, ask, grade, level, report, spend, models, estimate, trial, local_model, live and helper.

To build and run it from source:

sh
git clone https://github.com/pouriaetab/leanfare.gitcd leanfarebun installbun test             # against fake providers; nothing leaves your computerbun src/cli.ts       # the appbun src/cli.ts mcp   # the MCP server, over stdio

Privacy

Leanfare reads usage numbers, never your words, unless you choose in Settings to keep a hand off's words on your computer to read later. Your keys stay on your computer, and requests go from your computer straight to the AI company you use. No telemetry. The guide has the details.

Update, stop or take it out

  1. Update: run the install line again. Leanfare says when a new version is out.
  2. Stop: type leanfare stop.
  3. Off for a while: the switch at the top of the app.
  4. Take it out of an app: Settings, In your apps, then Remove next to the app.

Data and credits

Prices come from llmledger (MIT), built from LiteLLM's public price list (MIT). Quality ratings come from the Arena leaderboard (CC BY 4.0). The guide lists the rest. Leanfare is not affiliated with any AI provider.

Licence

MIT

Source: README.md at commit 2ac2c99

Tools

0
SourceWeft started this package once in an isolated sandbox, without credentials, to list its tools. That failed: the package type cannot run in the sandbox.

Version history

10
  1. v0.15.3LatestNov 6, 2026
  2. v0.15.1Nov 5, 2026
  3. v0.15.0Nov 5, 2026
  4. v0.14.2Nov 5, 2026
  5. v0.14.0Nov 4, 2026
  6. v0.13.12Nov 4, 2026
  7. v0.13.11Nov 4, 2026
  8. v0.13.10Nov 3, 2026
  9. v0.13.9Nov 3, 2026
  10. v0.12.1Nov 1, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts