pickfit

BrowseDeveloper CLIs

Bamboo

Local Rust agent harness with sessions, tools, skills, MCP and HTTP/SSE/WebSocket runtime.

Use it

Before you install: known vulnerabilities

pickfit found 1 known high or critical vulnerability in the packages a fresh install brings (OSV.dev, 3 Nov 2026). Weigh this before you install it.

  • crates:russh 0.64.1 russh: Agent server never calls `Agent::confirm`, so keys added with the confirm constraint (`ssh-add -c`) sign without confirmation (GHSA-vp5q-ff62-jwqv, high, fixed in 0.65)

Linux x86_64

You need first

  • Runtimes: Rust 1.95+
  • Keys or accounts: provider key

These steps ran from a folder named work in the home folder, which already existed. Make it and run them from there:

mkdir -p "$HOME/work" && cd "$HOME/work"
  1. cargo install bamboo-agent --locked (built from crates.io, ~18 min, installed bamboo to ~/.cargo/bin)

    cargo install bamboo-agent --locked
Verified in pickfit: the commands exactly as its sandbox ran them

For the record only: they name the sandbox's home, /home/sbx.

cargo install bamboo-agent --locked 2>&1
export PATH="$HOME/.cargo/bin:$PATH" && bamboo --help
export PATH="$HOME/.cargo/bin:$PATH" && cd /home/sbx/work && bamboo -p "ping" --echo

Check that it works

export PATH="$HOME/.cargo/bin:$PATH" && bamboo --help

The output should contain “QUICK RUN (headless server):”.

First thing to try

export PATH="$HOME/.cargo/bin:$PATH" && cd "$HOME"/work && bamboo -p "ping" --echo

What it does

  • Serve local browser UI and HTTP API
    Tested
  • Run agent prompts on a workspace from terminal
    Not tested
  • Resume persistent agent sessions
    Not tested
  • Connect MCP servers, skills and scheduled prompts
    Not tested

How far pickfit got

Linux x86_64

  1. Installs
  2. Starts
  3. 1 of 4 features work
  4. Works offline

macOS and Windows: the project says it runs there; pickfit hasn’t tried it.

Good for

  • Run a prompt against a workspace and continue the session later
  • Embed assistant via HTTP, WebSocket/SSE events or Rust SDK
  • Carry facts across turns with session notes and durable memory
  • Connect MCP servers, skills, plugins and scheduled prompts

How pickfit tested it

Each run starts from a clean machine and follows the steps above. How pickfit verifies

Linux x86_64

Its service answers requests

  • Replayed from scratch
  • Works offline
  • Checked on 16 Nov 2026
  • Version 2026.11.23

Differences the test machine hit

  • README: Standalone Bamboo: cargo install bamboo-agent --locked; bamboo --help
    In the test: ~/.cargo/bin must be on PATH (the box's PATH did not include it); the install itself worked with the box's Rust toolchain and took about 18 minutes.
  • README: Bodhi desktop app: curl ... install.sh | sh (terminal installer)
    In the test: The script installs a different product (Bodhi-AI desktop, a .deb) with sudo apt-get and needs a terminal for the sudo prompt. It cannot run without root, so it was not used; the Bamboo CLI came from cargo.
  • README: bamboo init (interactive provider setup) then bamboo serve
    In the test: bamboo serve starts without init. Headless runs need a provider key, which was not available, so bamboo -p failed with HTTP 500 and doctor reported no config.json and no anthropic API key.
  • README: bamboo -p "Summarize the README in this workspace." --workspace /path/to/project
    In the test: Needs a configured model provider API key; without it the run fails with 'execute rejected: HTTP 500'.

How to read a tool card

Stitching
pickfit installed this tool itself. Everything under the stitches comes from that run. A tool pickfit has not run never gets stitches.
Verified on your OS
The install steps ran on the system you chose. “Ran on Linux only” means it has not been run on yours yet.
macOS, Linux and WindowsWhere it ran
Green OS marks: pickfit ran the install steps there. Grey ones: the README says it runs there, and pickfit has not tried.
How far the run got
Installs and starts, its main function works, its service answers, it produces model output. A window means a desktop app opened; a plug, an MCP client used it. The mark sits beside the run’s result, under “Why it fits and how we know” and in “How pickfit tested it”.
Visual check
pickfit looked at screenshots of the app. Green: it looks right. Amber with a number: things that look wrong; open it to see them. Grey and dashed: not checked yet.
Known vulnerabilities
Known high or critical vulnerabilities (OSV.dev) in what it installs. Green: none known. Red with a number: how many; open it for the list, and read it before you install. Grey and dashed: not checked, which does not mean safe.
About the run
The day it ran, and the version that ran.
Source of a reason
Every reason a pick fits rests on one profile field. Open the reason to see the field and the value it relies on.
Hidden gem
High quality, little known.
Quality and popularity
Two scores out of 100. Quality: how well it installed and worked when pickfit tried it, and how good its install docs and upkeep are. Popularity: from stars, downloads and Hacker News.
Features checked
Of the main features the README advertises, how many the run actually exercised (green), and how many failed (red). Grey ones were not checked, and the card says why.
Not verified
A well-known tool Fitz mentions from general knowledge. No run record, no steps, no score.