by morluto
Pure mathematics for agents: search for examples and counterexamples, compute exactly, and independently check what a result proves.
# Add to your Claude Code skills
git clone https://github.com/morluto/jacobianjacobian is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by morluto. Pure mathematics for agents: search for examples and counterexamples, compute exactly, and independently check what a result proves. It has 51 GitHub stars.
jacobian's catalog security scan is still queued. You can run an instant dependency and prompt-injection check now with the "Scan for vulnerabilities" button above.
Clone the repository with "git clone https://github.com/morluto/jacobian" and add it to your Claude Code skills directory (see the Installation section above).
jacobian is primarily written in Python. It is open-source under morluto on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh jacobian against similar tools.
No comments yet. Be the first to share your thoughts!
Unlocks once the catalog security scan passes (runs nightly).
The deep catalog scan for this skill is still queued. Run an instant dependency check now instead.
English · 简体中文
Jacobian is an MCP server that gives AI agents atomic, composable tools for
higher mathematics. It exposes two tools: math.find searches an immutable
library of typed mathematical operations, and math.run executes exactly one
of them and returns its concrete typed result. Each operation is one bounded,
exact computation: a typed request in, a typed mathematical value out, with
no workflow, state, or intermediate runtime between them. The same
mathematical library is also available through a CLI and native Python API.
Run the canonical Python MCP command without installing Jacobian globally:
uvx --from jacobian jacobian-mcp
Where an MCP host requires an npm command, the npm package is a deterministic carrier for that same command:
npx jacobian mcp
For a persistent installation:
python -m pip install jacobian
jacobian-mcp
That package includes Jacobian's exact maintained Python backend stack: SymPy, NetworkX, Z3, and Python-FLINT. A normal Python or npm installation therefore exposes the same built-in Python-backed operation portfolio. The tested binary-install contract is CPython 3.12 or 3.13 on glibc Linux x86-64; the release gate installs the built wheel and starts Jacobian on both Python versions. Other systems may have compatible upstream wheels, but are not part of the tested release contract yet. In particular, Alpine/musl cannot install the complete mandatory stack from PyPI.
The Python distribution contains the mathematical kernel, CLI, and MCP server.
The npm package contains no lifecycle manager or JavaScript API; it only maps
its exact package version to the corresponding uvx invocation.
An ordinary operation returns mathematics first. For example,
matrix.determinant.compute accepts one exact rational matrix and returns its
determinant directly. Callers compose results by passing their typed values to a
subsequent operation; Jacobian retains no project state or artifact store.
The built-in portfolio covers work in:
SAT and SMT operations use the maintained Z3 Python binding directly. The
optional lean.check operation runs one bounded source snippet in the fixed
Lean service environment. It creates only a request-scoped temporary directory
and returns typed diagnostics; it does not expose a proof-state session or
retain source. Use math.find to search for an operation, browse an unfamiliar
domain, and inspect one operation before calling math.run once.
See the domain operation library for the maintained operation portfolio and backend requirements.
Jacobian 0.12.0 is pre-stable. Its published package and operation contracts describe the supported surface; experimental operation contracts may change between releases.
Jacobian uses Python 3.12, uv, and a small Makefile:
make setup
make test-math
make check
Read CONTRIBUTING.md before changing code. It documents focused test commands, verification rules, documentation placement, and pull-request expectations.