Demos

Is your agent’s self-modification
actually working?

agentvcs holds an agent’s whole history — every iteration, with a quality score attached. That lets it answer things a live runtime can’t: is the loop improving or quietly rotting? Is a branch worth keeping? Is a shared memory safe?

Two narrated, runnable walkthroughs. Both use real evaluations under the hood — nothing here is faked.

Start here · plain English

Business cases

Five everyday situations anyone running an AI product recognizes — a support bot that gets a little worse every week, a client fork nobody merged back, paying for context that changes nothing, one bad fact poisoning a fleet. Each ends in a one-line recommendation, with no math on screen.

Read the five stories →
The technical companion

Evolution diagnostics

The same five capabilities, shown with the real numbers and the theory behind them: the Price equation catching an error catastrophe, Muller’s ratchet on an isolated branch, the information value of context in bits, and branching-process containment. Every claim is asserted against --json.

Read the five acts →

What each demo shows

SituationCommandThe call it makes
A self-updating agent quietly getting worseagentvcs priceStop — the loop is net-negative; roll back
The same agent, branch-and-keep-the-bestagentvcs priceKeep going — it’s genuinely improving
A fork maintained alone for too longagentvcs branchMerge it back before it rots further
A prompt stuffed with context that changes nothingagentvcs infobitsTrim the context — cut cost & latency
A shared memory that could spread a mistakeagentvcs containVerify N% of reads, or shrink the fleet

Run them yourself: bash examples/business-cases/run.sh · bash examples/evolution-diagnostics/run.sh — full guide in docs/DEMOS.md.