English  ·  简体中文

MOLT 🦀

The coding agent that grows its own tools.

Most agents solve your task and forget everything they learned. MOLT doesn't forget. After every job it reflects on what it did, and when it spots a reusable pattern, it writes itself a new tool, tests it, and keeps it in a skill library. Next time the pattern shows up, the tool is already there.

Watch the toolbox compound:

$ molt run "tidy the config files" --learn --mock

── molt run — task ─────────────────────────────────────────────
  task: tidy the config files
  model: mock

── final answer ────────────────────────────────────────────────
  All done — I inspected the workspace and the job is complete.

── learn ───────────────────────────────────────────────────────
  ✔ grew a new tool: `parse_csv_line` → .molt/skills/parse_csv_line

$ molt skills list
  parse_csv_line    [project]  Parse a CSV line of key=value pairs into a dict.

$ molt run "parse some key=value config" --mock      # the tool is already there

That's the whole idea: your AI doesn't just code — it molts. It sheds the old, grows a new tool, and keeps it.

Why MOLT

• It compounds. Every task can make the next one cheaper and more reliable. Your agent gets better at your codebase, not just smarter in general.
• It's honest self-modification. A skill only enters the library after passing its own test. The agent can grow itself new tools, but they have to prove they work first.
• It's shareable. molt export bundles your toolbox; molt install pulls someone else's. Your agent's hard-won skills become a library you can fork, star, and share.
• It's yours. MIT, zero tracking, runs on any OpenAI-compatible model — DeepSeek by default.

Quickstart

# From PyPI (the package is published as `molt-agent`):
pip install molt-agent

# …or straight from source:
git clone https://github.com/houyongsheng/deepseek-harness-molt
cd deepseek-harness-molt
pip install -e .

export DEEPSEEK_API_KEY=sk-...

Run a task and let it learn:

molt run "add retry logic to the http client" --learn

No API key? Run the exact same loop with a built-in fake model:

molt run "tidy the config files" --learn --mock
molt evolve "polish the project" -n 5 --mock     # watch the toolbox grow

Commands

How it works

   task ─▶ agent loop ─▶ answer
               │
               └──▶ reflect: "did I hit a reusable pattern?"
                        │ yes
                        ▼
                   author a skill (python + schema + test)
                        │
                   test it ── fail ─▶ discard
                        │ pass
                        ▼
                   commit to .molt/skills/
                        │
                        ▼
              next run loads it as a tool

• Run — an agent loop with shell, read_file, write_file, plus every skill you've grown.
• Reflect — a second LLM pass asks: was anything here reusable? If yes, it returns a skill as JSON.
• Test — the skill's own test runs in a fresh subprocess; no test, no commit.
• Reuse — skills become callable tools, project skills shadowing your home library.

Skills live at .molt/skills/<name>/ (project) and ~/.molt/skills/ (home). Each is plain files: skill.json (name/description/inputs), skill.py (def run(**kwargs)), test.py.

Sharing the toolbox

molt export --out ./my-agent-toolbox      # copy your skills + manifest
molt install /path/to/my-agent-toolbox    # or: molt install git@github.com:you/toolbox.git

That's the seed of an ecosystem: your agent's skills are a library, and libraries get forked, starred, and shared.

Trust & safety

• Tested before committed. Untested or failing skills never enter the library.
• Skills run in-process. MOLT is built for skills you or your project authored — treat others' skills the way you'd treat any code you pip install. Use --mock and a sandbox/container to evaluate before trusting.
• Plain files, no lock-in. Your toolbox is just directories; delete it, share it, move it.

Roadmap (honest)

• Skill dedup/merge so repeated patterns collapse into one tool
• Skill evals — benchmark a skill's accuracy before/after you edit it
• A registry command (molt publish) for a real community hub
• Streaming the agent loop, richer built-in tools, --sandbox

License

MIT — go build something that grows itself.