Install the gate.

pip install 'courant-dev[mcp]'

# Python 3.11 or later; the command is courant

Or one signed file, no Python. macOS and Linux · arm64 and x86_64

curl -fsSL https://github.com/courantdev/courant/releases/latest/download/install.sh | sh

The installer checks the binary's SHA-256 and, where it can, the release's Ed25519 signature, against the key pinned in the installer; COURANT_REQUIRE_SIGNATURE=1 makes it refuse without the signature check.

Or the file itself:

courant demo

Four real OpenFOAM runs, offline, and an HTML report.

Licence: Apache-2.0
Source: github.com/courantdev/courant
Release: 0.5.0 · 12 Oct 2026
Key · Ed25519: 04936391…5c821192

First verdict in seconds.

Then point it at a case directory, or at a solver log on its own.

Courant demo · offline · read-only · four real OpenFOAM v2406 runs

1  A healthy run: icoFoam cavity, as OpenFOAM ships it
     accept  (rule VER-5.6, grade A)

2  A broken run: the same cavity with a timestep ten times too large
     reject  (rule VER-5.3, grade C)
     why     cfl.max: Courant number exceeds stability limit: max Co=9.66 at t=0.15 exceeds limit 1.0; still 8.92 over the final fifth of the run
     why     convergence.residual: transient solve judged on stability rather than a residual threshold — Courant number settled at 8.92, above the stability limit of 1 — a transient solve that does not respect its timestep criterion is not converged, whatever the residuals say (final worst residual 3.61e-01)
     cause   NUM.CFL_VIOLATION (Courant number too high)
     next    Suggested, not applied: Reduce deltaT in controlDict

3  Before the run: the cavity with its viscosity in the wrong units (courant preflight)
     SETUP_FAULT  before the first timestep
     why     physics.nu: Suspicious viscosity value: nu=1e-09 m^2/s is outside typical fluid range [1e-8, 1e-2]
     next    Suggested, not applied: Correct nu in transportProperties (units m^2/s)

4  A steady run with a fixed budget: pitzDaily, 2,000 iterations, monitors on the walls and the inlet
     accept  (rule VER-5.6, grade B); convergence PASS
     1  Answer       courantWallForces/moment:total_z: value -5.55254e-06 at step 977, -5.55373e-06 at the end (step 2,000)
     2  Change       0.021% of scale after the stopping point (limit 1.0% of scale)
     3  Iterations   1,023 of 1,999 past convergence (51.2%)
     4  Wall clock   9 s of 21 s past convergence (solver ClockTime; rank-0 CPU 9.51 s)
     5  Core-hours   0.0025 past convergence (1 rank, nProcs in the log, x wall clock)

5  The compute audit over these 4 runs (courant audit)
     2 of 4 trustworthy · 1 of 4 with a setup fault preflight finds before the start · on 1 of 1 monitored runs the answer settled, with 51.2% of its iterations still to run
     On your runs it totals the core-hours, and the cost at your rate.

courant 0.5.0 · 19 Oct 2026 · the first screen of its output

courant verify ./my_case                   # a case directory: finds the solver log itself
courant verify log.simpleFoam              # or a log on its own

courant verify --about           # the error rates published for this version

Every verdict travels with this version's measured error rate.

Is it the problem that was asked?

A run can converge and still answer the wrong question: it checks every value the task names against the case.

Lock the hash before the run: an edited specification makes the verdict insufficient.

courant spec init ./reference_case -o spec.json --task "pitzDaily, inlet 10 m/s, k-epsilon"
courant spec hash spec.json              # lock it before the run; keep the hash
courant verify ./agent_case --spec spec.json --spec-sha256 <hash>

Every report states its basis: validity, validity+conformance or validity+unlocked-spec.

For AI agents.

An agent that runs a simulation can check its own result before it reports success.

courant mcp --root ~/runs

courant mcp --print-config --root ~/runs

claude mcp add courant -- courant mcp --root ~/runs

The server offers six read-only tools, confined to the directories you name:

verify_run
score_agent_output
check_convergence
explain_code
list_failure_modes
verifier_certification

In CI.

Any CI system that reads JUnit shows each run as a test: GitHub Actions, GitLab, Jenkins, Azure.

The batch exit code is 2 if any run is rejected, otherwise 3 if any is insufficient, otherwise 4 if any is unreadable.

courant verify --batch runs/ --junit courant.xml     # exit 2: runs/ holds rejected runs

The GitHub Action

Verdicts and exit codes.

Verdict	Exit code	Meaning	In JUnit
`accept`	0	No check failed, and the run produced enough output to be judged.	a passed test
`reject`	2	At least one check failed. Each reason gives the file it read, the method, the threshold and the value.	a failed test
`insufficient`	3	There was not enough to judge. The verdict carries one reason, `insufficient.<name>`, from a closed list, and the report says what was missing.	a skipped test

An unreadable input exits 4.

The eleven reasons for insufficient

Reason	Rule	Cause
`insufficient.no_output`	VER-5.1	run
`insufficient.unrecognised_log`	VER-5.1	fork
`insufficient.no_residuals`	VER-5.5	run
`insufficient.no_time_markers`	VER-5.15	run
`insufficient.spec_hash_mismatch`	VER-5.8	spec
`insufficient.spec_value_unreadable`	VER-5.9	spec
`insufficient.unsupported_version`	VER-5.10	fork
`insufficient.spec_invalid`	VER-5.11	spec
`insufficient.spec_extracted_mismatch`	VER-5.12	spec
`insufficient.spec_role_unresolved`	VER-5.13	fork
`insufficient.time_scheme_unreadable`	VER-5.14	fork

The previous verdict names (TRUSTWORTHY, NOT_TRUSTWORTHY, NOT_ASSESSABLE, courant.verdict/1) are available for one more minor release with --schema 1; the decision is the same.