gen-system Understand MCP server

gen-system

Parser facts about a codebase, and Go services from local models that must compile before they ship.

The Studio on examples/payroll. Left: what MAIN-PARA calls, two levels deep. Right: the control flow graph of CALC-TAX. The EVALUATE on the pay grade fans out into four arms, then the region check adds a branch.

A model that writes code for an existing system has to guess about it. What does this routine call? Which data does it write? What does a COBOL paragraph pull in from a copybook? gen-system answers those questions with parsers, one hand written parser each for Go, COBOL with copybooks, CA Gen, Java, TypeScript and Python. They build the syntax tree, the symbol index, the call graph and the control flow graph of each routine. No model takes part in that step, so the same code always gives the same graph.

For each routine, gen-system then lists the inputs, the calls, the data it writes and the action its name suggests. It calls each line a belief. A local model may add claims, and gen-system marks any claim the parser contradicts and never uses it. You can correct any belief. Only beliefs a person verified steer generation.

The Beliefs page for examples/payroll. A COBOL paragraph has no parameters, so gen-system reads its inputs and the data it writes from its statements: CALC-TAX reads the grade, the region, the gross pay and the rate, and writes the tax and the rate. Each line has Verify and Correct.

The generation half plans a Go service with qwen3:14b and writes each operation with qwen2.5-coder:14b. Each operation must compile on its own before it enters the service file. A body that still fails after two repairs becomes a not implemented stub, and the run counts it. Then go vet, go build and go test run on the whole service, and the parsers read the result again.

I measured the parsers on 2026-09-09, on four public repositories pinned to a commit: 405 files, 268 of them COBOL. They hit 0 parse errors and resolved 100% of the calls between each project's own symbols. They built 1,302 control flow graphs, and none had an issue. On 60 SWE-bench Verified tasks, gen-system took the names in each issue and walked two hops through the call graph. The walk reached 0.674 of the files the real fix touched, and a median of 422 files per task. That is localization recall, not a solve rate: gen-system writes no fix. The raw files are in results/2026-09-09/.

What you get

The read only half (understand-server, understand-mcp) links no generation code and no model client. An architecture test (internal/archtest) fails the build if that changes.

Install

You need Go 1.25 or newer. The generation half also needs Ollama and one GPU with 16 GB. I run it on an RTX 4060 Ti with 16 GB, on Linux and on Windows.

Shortened. The full README is on GitHub.