SOTA / live

The Graff harness is out. 83 ± 3 on Terminal Bench. State of the art.

Early access / agents

The self-improving coding harness for AI agents

Graff is an evolutionary coding harness and agent evaluation system: run real repository tasks, score outcomes, retain stronger variants, and iterate. 83 ± 3 on Terminal Bench, 48ms cold starts, and the same MCP interface your agent already knows.

83%

Terminal Bench (±3)

harness eval · May 2026

48ms

cold start p50

create + first exec, intra-datacenter

21x

faster than fork/exec

0.7ms in-process vs 15ms spawn

100%

task isolation

per-run ephemeral environments

Sandbox cold start / ms to first command

Graff sandboxcreate + first exec (p50)
48ms
Competitor Ameasured Apr 2026
420ms
Competitor Bmeasured Apr 2026
1100ms
Local processfork/exec, no isolation
15ms

intra-datacenter / Apr 2026 / 10 trials each

Pay as you go

Instant sandboxes. Pay as you go.

Spin up sandboxes in milliseconds, shut them down just as fast. Usage-based pricing, billed per second. Volume discounts as you scale.

ResourceUnitPer secondPer hour
ComputevCPU$0.0000196$0.071
MemoryGiB$0.0000063$0.023
StorageGiB$0.00000004$0.0002

* Storage: 5 GB free, then billed per GiB/s. All prices in USD.

$200 free compute included
No credit card required
Volume discounts available

Why it's different

Cold start matters more than throughput

Agents iterate in tight loops. A 1s sandbox startup compounds into minutes of dead time per task. At 48ms, agents feel instant.

Isolation without overhead

Every agent run gets a clean environment. No state bleed between tasks, no permission sprawl. Tear-down is automatic.

Tuned for terminal tasks

Terminal Bench measures what matters: file I/O, shell commands, grep, patch, compile. Not synthetic throughput. Real agent work.

Terminal Bench

What it measures. Real shell tasks: write a file, run a test, apply a patch, search a codebase. The benchmark an agent actually has to pass.

Our score.83 ± 3 on Terminal Bench. Ahead of every published harness we've seen. Full run is on GitHub.

Why it matters. Throughput benchmarks hide latency. Terminal Bench surfaces the pause an agent actually feels between steps.

Web crawl sandbox

The same sandbox can crawl almost any public webpage: docs, marketing sites, dashboards, forms, changelogs, and JS-heavy apps. Auth walls, robots rules, and rate limits are respected.

agent sandbox crawl https://docs.example.com

render page - extract links - queue useful pages - return map

01

Open a clean browser context

A fresh sandbox navigates to the target URL without sharing cookies, files, or state.

02

Render and read the page

Kuri captures text, links, forms, screenshots, and stable action refs from the loaded page.

03

Follow the useful links

The agent queues same-site pages, docs, pricing, changelogs, forms, and API calls instead of crawling noise.

04

Return an inspectable map

You get markdown, screenshots, network traces, and the exact actions the agent took.

Coming next

Agent-to-agent chats

The next thing landing on top of the sandbox: a structured chat plane between agents. One planner, many workers, every exchange typed and replayable. The whole thing sits on the same 48ms sandbox runtime you already get today.

planner -> worker[crawl]: { intent: "summarise docs", url: "..." }

worker[crawl] -> planner: { status: "done", refs: [...], summary: "..." }

planner -> worker[edit]: { intent: "apply patch", file: "..." }

Agents that talk to each other

A planner agent breaks a task into subtasks and dispatches them to specialist agents. Each one runs in its own sandbox, reports back over a typed message channel, and the planner re-plans on partial results.

Typed message channel

Not raw stdout. Every message is a structured envelope: sender, role, intent, payload, citations. The planner can route, retry, or fan out without parsing freeform text.

Inspectable transcripts

Every conversation is a durable, replayable trail. Step through the exchange, fork from any point, or rerun with a different model. No more guessing why an agent gave up.

Per-agent sandboxes

Each participant lives in its own 48ms sandbox: clean filesystem, scoped writes, isolated network. A worker agent crashing or going off-script never leaks state into the planner.

Same waitlist. Early access flips on for sandboxes first, then chats. Drop your email below.

Coming soon

Specialist agents

Same 48ms sandbox, role-tuned for the work. Each ships with a curated tool surface, prompts, and evals. Drop one in over MCP.

Design agent

Soon

Ship UI faster than your designer can comp it.

From a one-line prompt to a production-ready component. Reads your design tokens, picks accessible color, and iterates against real preview screenshots until the diff matches the spec.

  • Tailwind / shadcn aware
  • Screenshot-driven iteration
  • Figma import (preview)

Finance agent

Soon

An analyst that doesn't sleep through close.

Reads ledgers, reconciles books, runs scenario models, and writes the variance commentary. Ships PDF and Excel, and cites every number back to its source row.

  • Spreadsheet + DB native
  • Cited variance reports
  • SOX-friendly audit trail

Early access

Join the waitlist

We're rolling out in batches. Drop your email and we'll reach out when your slot opens.

By joining you agree to receive product updates and marketing emails from Codegraff. We'll never share your address. You can unsubscribe at any time. See our Privacy Policy.