pickfit

BrowseDeveloper CLIs

protoagent_

Local-first coding agent with Rust terminal UI and Python core for workspace tasks.

Tested on Linux

Use it

Linux x86_64

You need first

  • Runtimes: python>=3.12
  • Keys or accounts: BRAVE_SEARCH_API_KEY
  1. clone protoagent source

    rm -rf protoagent-src && git clone https://github.com/nMaroulis/protoagent.git protoagent-src
  2. pip install core without compiler-heavy deps plus protolink http mcp extras

    python3 -m pip install --no-deps -e protoagent-src/core && python3 -m pip install "protolink[http,mcp]>=0.8.2"

Check that it works

python3 -c "import protoagent_core; print(protoagent_core.__version__)"

The output should contain “0.3.1”.

First thing to try

python3 -c "import protoagent_core; print(protoagent_core.__version__)"

Check the install with python3 -c "import protoagent_core; print(protoagent_core.__version__)".

What it does

  • Index a workspace and build context packs
    How to use it
    1. Index your workspace with python3 -c "from protoagent_core.context import refresh_context_index; print(refresh_context_index('<workspace>'))".
    2. Build a context pack for a question with build_context_pack('<your question>', '<workspace>') from protoagent_core.context.
    3. Format the pack for a prompt with format_context_pack_for_prompt(<pack>).
    Tested
  • Run local LLMs from a Python core
    Not shown working
  • Run agents in a Rust terminal interface
    Not tested

How far pickfit got

Linux x86_64

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

Good for

  • browse workspace files without a model
  • explain authentication flow and propose safer change
  • design regression cases and run approved checks

How pickfit tested it

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

Linux x86_64

Its main function works

  • Replayed from scratch
  • Works offline
  • Checked on 30 Oct 2026
  • Version 0.3.1

Differences the test machine hit

  • README: python -m pip install -e core
    In the test: install with --no-deps then protolink[http,mcp] to avoid llama-cpp-python gcc build; full pip install -e core tries to build llama-cpp-python and fails with Could not find compiler gcc
  • README: cargo run --locked --manifest-path cli/Cargo.toml -- version/check/agents
    In the test: Python equivalents via protoagent_core.agent_engine (component_versions/doctor/get_agent_settings) and harness_eval/context modules; cargo run examples need Rust toolchain absent in box

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.