Describe the job. Approve the plan. Get an AI workflow that's proven to survive failure — before you ever trust it in production.
They fix what the AI knows. We fix whether the job finishes.
None show up in the demo. All of them show up in week two — so GraphSmith hardens each one at generation time.
Crashes at step 7 of 10 and restarts from step 1 — redoing paid API calls, re-scraping, re-generating.
Every step saves progress; a crash resumes at the exact step it stopped, never from zero.
A retry after a half-finished step sends the same email twice, charges the same card twice.
Recorded effects run once, even after power loss; an uncertain send halts loudly instead of re-firing.
Ask about your own codebase and it invents functions, files, and APIs that don't exist.
Every claim cites a real file via KnoSky, or is flagged as a guess. Your code never leaves your machine.
A workflow that's 85% reliable per step fails four times out of five across ten steps.
A plain-English goal goes into the forge — a hardened, self-defending workflow comes out. Then watch it take a crash and finish anyway.
Say the outcome in plain English. The skill activates on its own.
One screen: workers, handoffs, save points, stop rules. Nothing is built until you approve.
A runnable, zero-dependency project. Runs immediately with no API keys.
A chaos test kills the run mid-flight and verifies it recovered — no duplicated work.
It SIGKILLs the run mid-flight, restarts, and asserts it resumed from the last save point with zero duplicated effects. Verification is executable — not "the AI says it's fine."
They held the release twice until every finding was fixed or disclosed. Full reports — dissents preserved — live in the repo.
Verified integrity · immutable, gated core · isolated evaluation · local-by-default · observable & killable. A deterministic check runs at every boundary.
Capability profiles — resumable, effect-reconciled, integrity-verified, adversarially-tested — with linked evidence, via a GitHub Action or GitLab template.
One install. Nine capabilities across the full lifecycle — all local, all readable in minutes. Pick a stage:
A runnable, zero-dependency project: deterministic manager, worker steps, save points, resume, capped retries, structured logs — runs immediately with no API keys.
A one-screen plan — workers, handoffs, save points, stop rules — that you approve before a single line is written.
Scans existing JS / TS / Python for the classic failure patterns — unbounded loops, missing persistence, unsafe side effects — ranked by severity, self-tested against a bundled corpus.
Maps "it forgets / duplicates / loops forever" to the exact broken rule, with file and line — and proposes the minimal fix without rewriting what works.
Kills the run mid-flight and asserts recovery: kill test, double-run, power-loss probe, lock probes, and a loud safety-halt path.
Capability profiles (resumable, effect-reconciled, integrity-verified, adversarially-tested) enforceable on every PR via a GitHub Action or GitLab template.
A local pointer index your AI cites from — claims about your code carry a real file reference, or are flagged as guesses. A map, not an oracle. Nothing leaves your machine.
KnoSky re-indexes each session and degrades gracefully offline — pinned and content-hash verified, never a silent global install.
Lanes (one writer each), task claims with leases, frozen contracts, no self-certification, and risk-tiered human gates — so parallel agents never collide.
Optional, for production teams: registry, PRD-to-task traceability, adversarial QA charter, release & rollback runbooks, and agent eval scorecards.
A broken workflow gets a diagnosis and a smallest-fix repair, staged with evidence and one-command rollback — never a silent rewrite of your logic.
Bounded, project-local improvements that must clear an executable gate and a human before adoption. It can't learn past its own safety rules.
Architectural, unit, smoke, regression & adversarial batteries against your workflows, with tamper-evident evidence.
Tells you exactly when to move up to SQLite, a framework checkpointer, or a durable engine — and when not to.
Not sure where to start? Ask the assistant in the corner — it answers what GraphSmith can do, how to install it, and more.
v0.2.0 turns the discipline into a protocol — five invariants a deterministic check enforces at every boundary.
A deterministic check runs at every boundary; injected text can't reach control flow.
A constitutional core no automated process can edit; every change passes a four-gate pipeline.
Every candidate change is tried first in a disposable, mocked-effect copy.
Healing, learning, evolution stay on your machine. No telemetry, ever.
Every run declares budgets, streams to a live view, and is safe to kill and resume.
Researches new leads and drafts emails. A crash never re-pays for the enrichment calls it already made.
Exactly-once so a retry never double-charges — and an uncertain send halts for a human instead of guessing.
Resumes at the failed step instead of re-scraping and re-enriching the whole dataset from zero.
KnoSky citations mean it never edits a file or API it hallucinated into existence.
Lanes, task claims with leases, and frozen contracts — parallel speed without parallel chaos.
Risk-tiered human gates and evidence packets for the workflows you can't afford to get wrong.
Works identically via the Agent Skills open standard — plain Node 18+, macOS, Linux, and Windows.
npx skills add SathiaAI/graphsmith
Then, in any agent: “Build me an agent that researches new leads and drafts outreach emails.” · Free. MIT. No API keys. No telemetry.