~/reading

51

Issue 51/October 26, 2026/5 tools · 3 headlines

MicroVM isolation and harness routers overtake single-agent CLIs

Power users are cloning local microVM sandboxes and self-hosted control planes that isolate any coding agent and route tasks across interchangeable harnesses. The through-line is runtime ownership: branchable VMs, unified protocols, and eval gates that sit under the model loop.

01 — Power tools

The stack

  1. 01toolGitHub
    coop↗

    trailofbits

    Rust CLI that spins disposable Firecracker or Lima VMs so coding agents get full Docker, git and compiler access with zero host risk.

    Use caseUse it to launch Claude Code, Codex or Grok Build inside a fresh isolated VM per project and tear it down when done.

    microvmisolationclifirecracker
  2. 02toolGitHub
    agents-sandbox↗

    inoio

    Launcher that places supported coding agents inside per-project microVMs while keeping secrets and host paths under operator control.

    Use caseUse it to keep your existing agent CLI workflow yet isolate each repo and inject secrets only as placeholders.

    sandboxmicrovmsecretslauncher
  3. 03harnessGitHub
    Runtm↗

    runtm-ai

    Open-source sandboxes and control plane where coding agents build, test and deploy software with live HTTPS URLs, logs and previews.

    Use caseUse it to let any coding agent ship real software inside isolated environments that expose instant preview endpoints.

    sandboxdeployruntimecontrol-plane
  4. 04harnessGitHub
    agentplane↗

    hupe1980

    Durable, replayable Rust agent runtime whose journal is the single plan of record for every step and decision.

    Use caseUse it to run agents that can be fully audited, replayed and resumed from a cryptographically consistent log.

    runtimejournalrustreplay
  5. 05harnessGitHub
    agent-reliability↗

    kladak

    Reliability platform with schema-validated tool routing, JSONL traces, deterministic graders and CI regression gates.

    Use caseUse it to add offline eval reports and fail-the-build gates to any tool-using agent loop.

    evalreliabilitytracesci

02 — In the wild

Articles and releases

  1. articleFlowtivity
    Google just open-sourced self-improving agents. The harness beat the model.↗

    AJ Awan

    Google Cloud AI Research released Harness2, a framework that lets an agent rewrite its own system prompt, tools, memory and skills while the model stays frozen. One improvement step was enough for GLM-5 under the new harness to outscore a stronger baseline model on WorkBuddy-Bench.

    harnessself-improvinggooglebenchmark

    Read

  2. releaseDocker Blog
    Harbor + Docker Sandboxes: Run Safe, Reproducible Agent Evals↗

    Docker

    Harbor can now execute every evaluation task inside Docker Sandboxes, which are microVM environments with their own kernel. Configurable network policies let setup download dependencies then lock down the agent for fair, reproducible scoring both locally and in the cloud.

    evalsandboxdockermicrovm

    Shipped

  3. articleKeyhole Software
    Agentic Harness Architecture: 2026 White Paper↗

    Zach Gardner

    The paper maps the six core components of an agentic harness and shows measured score and cost swings when only the harness changes. It closes with vendor comparisons and a concrete reference design aimed at data-engineering workloads.

    architecturesurveyharnesswhitepaper

    Read

Get the daily tools digest

RSS