Quell reads your docstrings, Pydantic models, and type annotations, extracts every testable requirement, finds which ones have no test, generates pytest tests via a rule engine, verifies each test through a 5-gate pipeline, and writes only proven tests to disk.

Does Quell require an LLM API key?

The rule engine runs entirely in-process — no source code is ever transmitted. ~75% of edge cases are handled with no network call and no API key. LLM fallback is opt-in and only sends the function signature, never the full body.

What is the 5-gate pipeline?

Every generated test must pass: Gate 1 (AST valid Python), Gate 2 (not already in a test file), Gate 3 (no shell calls or file writes), Gate 4 (passes against original code), Gate 5 (fails when the requirement is violated). Only gate-5-verified tests are written to disk.

What is the Production Readiness Score (PRS)?

PRS = (WRITTEN × 1.0 + SCAFFOLDED × 0.5) / total_requirements × 100. Tiers: 80-100 Production Ready, 60-79 Review Needed, 0-59 Needs Work.

How is Quell different from GitHub Copilot or Qodo for test generation?

Quell reads specifications that already exist in your code — it does not generate tests from scratch. It finds requirements already documented in your docstrings, Pydantic models, and type annotations that have no test. The 5-gate pipeline, especially Gate 5 (violation injection), verifies each test actually catches the bug it claims to catch. This verification step is not present in Copilot, Qodo, or Hypothesis.

Can Quell be used in CI pipelines?

Yes. Run quell ci src/ --threshold 80 to fail CI if PRS falls below 80. Set prs_threshold in pyproject.toml under [tool.quell]. Works with GitHub Actions, GitLab CI, and any system that checks exit codes.

Can Claude Code or Cursor use Quelltest directly?

Yes. Quelltest ships a local MCP server: install with pip install quelltest[mcp], then add {"mcpServers": {"quelltest": {"command": "quelltest-mcp"}}} to your project's .mcp.json. The agent can then call find_edge_cases, write_verified_tests, get_prs_score, prove_file, and reproduce_bug directly — no terminal needed. A Claude Code plugin is also available via /plugin marketplace add quelltest/quelltest-lib.

Does the Quelltest MCP server send my code anywhere?

No. The local MCP server (quelltest-mcp) runs entirely on your machine over stdio — no cloud, no network calls, no telemetry. The separate opt-in Claude.ai connector only ever transmits sanitized metrics (PRS score, bucket counts, test names, flag locations); a sanitizer blocks source code, function bodies, and docstrings structurally.

How do I add Quelltest as a Claude.ai connector?

In Claude.ai, go to Settings, then Connectors, then Add custom connector, and enter https://mcp.quelltest.com. Claude discovers the OAuth endpoints automatically and walks you through authorization.

Open source

Contribute to Quelltest.

Quelltest is MIT-licensed and built in the open. The fastest ways to help: report extraction gaps, add spec readers, and teach the rule engine new constraint kinds.

quelltest/quelltest-lib good first issues

Where to start

Report an edge case we missed

Found a docstring pattern or Pydantic constraint Quell doesn't extract? File an issue with a minimal snippet — these are the highest-value reports we get.

Open an issue →

Add a spec reader

OpenAPI, SQLAlchemy, attrs — every new reader is a new source of requirements. The SpecReader protocol is small and readers must never raise.

Reader guide →

Add a ConstraintKind rule

Each rule teaches the deterministic engine a new violation to inject at Gate 5. Rule + injection + test — three files, well-trodden path.

Rule guide →

Improve the docs

Docs live in the website repo as MDX. Typos, missing examples, unclear explanations — small PRs are welcome and reviewed fast.

Docs guide →

Dev setup

# fork first, then clone your fork
$ git clone https://github.com/quelltest/quelltest-lib && cd quelltest-lib
# Python 3.11+ · uv manages the venv
$ uv sync --dev
# the suite must be green before you branch
$ uv run pytest tests/ -v
# lint + types — CI enforces both
$ uv run ruff check . --fix && uv run mypy quell/

Ground rules

Every WRITTEN-path change needs a test. The verifier and writer have hard invariants — read CLAUDE.md before touching them.

Spec readers return [] on any error. A reader that raises breaks the contract and will not merge.

No source-code transmission paths. Anything that sends payloads must go through the sanitizer.

Conventional commits (feat:, fix:, docs:) — the changelog is generated from them.

Code of conduct

Quelltest follows the Contributor Covenant v2.1. Be respectful, assume good faith, and keep discussions technical. Harassment of any kind means removal from the project spaces. Violations can be reported privately to conduct@quelltest.com.

CODE_OF_CONDUCT.md →CONTRIBUTING.md →