Chelis

Chelis is a numerical computing language for code that agents write and people supervise.

Chelis is a numerical computing language designed for code that agents write and people supervise. Tensors carry named dimensions and precision in their types, and a proof stack checks stated properties. The compiler checks shapes, precision, effects, and ownership before execution, returning JSON error reports. Agents use MCP tools for checking, evaluation, proving, and structural edits. Property declarations are verified using type checking, an SMT solver, or seeded sampling. Programs use a readable syntax called Surf or a canonical form called Deep, and build to C with packages covering numerical methods, dataframes, and quantitative finance.

Chelis at a glance

Best for: Software engineer
Runs on: Linux, macOS, CLI
Pricing: Free
Released: October 2026
Category: AI coding tool
Website: github.com/chelis-lang/chelis

Key features

Named dimensions and precision in types
Pre-execution shape and effect checks
JSON error reports with source spans
MCP tools for agent integration
Property verification via SMT solver or sampling
Compiles programs to C
Reef packages for numerics and dataframes

Use it for

Write numerical computing code with AI agents
Verify tensor dimensions and precision statically
Check program properties using SMT solvers

Alternatives to Chelis

Ponytail — Cuts unneeded code and dependencies by enforcing a minimal-code ladder.
jevgrep — Reduces coding agent costs by providing targeted, relevant repository context.
Pawl — Stops costly agent mistakes using fast deterministic code instead of prompt instructions.
Ax — Develop and improve AI features with consistent, type-safe code across six languages.
Ctxvitals — Measures exact token costs and security risks before agent launch.
Chemical X — Stops wasting agent context on CLI noise and compiler dumps.
Gspot — Stops bad code, type errors, and leaked keys before commits happen.
BAML — It brings type safety, speed, and local tracing to agent codebases.
Halis Code — It includes built-in guardrails like compaction, repeat guards, and approvals.
Grit — Automates large-scale code refactoring and migration tasks efficiently.
Golem — Provides type-safe agent abstractions and zero-dependency Go implementation.
Aegis — It ensures AI coding agents work against verified baselines and proof.

All Chelis alternatives