akougkas.io

CLIO Coder

A local-first coding agent with typed tools, bounded workers, and receipts.

The coding agent I create and maintain inside CLIO, for the people who maintain the code science runs on. It runs against a local or remote model of your choice, coordinates bounded work through typed tools and managed coding peers, and records results for inspection.

Install CLIO Coder View the code
The CLIO Coder banner, a terminal prompt beside the words CLIO Coder, the CLIO agent for your science.
The CLIO Coder banner from the iowarp/clio-coder repository.

Why I built it

Scientific software has an execution environment, a history, and standards that matter beyond the next plausible patch. A simulation kernel may depend on a compiler at a laboratory. A numerical change may need comparison with a reference result. A repository may not be allowed to send its contents to an arbitrary provider.

CLIO Coder is where I work on the runtime around that problem: context that has a useful lifetime, explicit authority, bounded delegation, and results a person can inspect. It sits inside CLIO, the context architecture I created for IOWarp.

The road here

I began exploring this line in December 2023. Early wrappers around Claude Code helped me study the workflow. Warpio, a Gemini CLI fork, explored scientific personas and context handover. AWOC explored agent orchestration and shared memory. PanCode refined the control loop and worker model. In April 2026 I consolidated the lessons into the present CLIO Coder repository.

  1. 2023

    WarpGPT

    The natural-language interface I wrote into the IOWarp proposal.

  2. Aug 2025

    Warpio

    Scientific personas and context handover inside an agent, first as extensions for Claude Code and Gemini CLI, then as Warpio CLI.

  3. Sep 2025

    AWOC

    The fleet model. Coding agents as bounded workers to direct with typed intent, rather than a library to call.

  4. Mar 2026

    PanCode

    The runtime. A control loop, a scored worker pool, and a reproducibility receipt for every run.

  5. Apr 2026

    CLIO Coder

    The research line brought together under IOWarp: typed tools, bounded workers, sealed receipts, and local models.

The repository’s age is not the age of the idea. Those earlier systems exposed what the harness needs to own: how context reaches a model, which tools a task can use, how work is handed off, and what remains after a run. The present implementation still has to earn its use; a long design history does not remove its current limitations.

The model is a choice

CLIO Coder treats the model as the user’s choice: a local or self-hosted server, a cloud API, a subscription, or an institutional inference gateway, with the conversation and its workers free to use different ones. Separating the harness from the model lets someone keep inference on approved infrastructure, or compare models on the same work under the same rules. A local interface does not make a cloud connection local, though: data sent to a provider follows that connection.

The first-session guide at coder.iowarp.ai covers installation and current commands.

Context has a lifecycle

A working set, a handoff, and a durable lesson need different lifetimes. CLIO Coder gives each its own mechanism: a project handbook and code map for orientation, visible context use and compaction for the working set, branch-bound handoffs, and memory proposals a person reviews apart from the task. These organize what a model sees; they do not train its weights during the session.

Tools follow the same idea. The coordinator starts with a small toolkit and discovers further capabilities when a task needs them, and every tool call still passes admission. Disabling a resource cannot erase instructions the conversation has already read.

Authority and results travel with the work

Authority is explicit. Workers and external peers run at the default permission level whatever the main session allows, and dispatched workers run inside an operating-system sandbox under immutable permits. Commands in the main session still execute with the user’s access. A managed run, by a native worker or by a peer agent such as Claude Code or Codex, ends in a result and a receipt.

Verification comes from the repository’s declared checks, assessed against fingerprints of the source, the check declarations, and the project’s quality policy, so a later edit can make an earlier pass stale. A denied check is not a validation result. Neither a passing test nor a sealed receipt proves scientific correctness.

Work across machines

A local session can coordinate workers over SSH on a university cluster or a remote server, and the machine running inference and the machine running a worker’s tools are separate choices. The fleet needs matching runtimes, approved access, and the project at the same path on every node; the fleet guide lists the requirements.

Where it stands

CLIO Coder is beta software, and interface and format changes arrive through its release notes. Release gates do not establish scientific benchmark results, and model quality varies by task and configuration. Earlier versioned notes describe earlier designs; the guides at coder.iowarp.ai describe the supported workflow.

I create and maintain Coder; Eneko Gonzalez has contributed. The project builds on the Pi agent framework from Earendil Works, the Claude Agent SDK, the Agent Client Protocol, and other upstream work. Across the wider CLIO program, Luke Logan leads day-to-day Core engineering, Jaime Cernuda leads Agent and Relay development, and students lead the scientific tool integrations in Kit.

The next question is how well these contracts hold across longer scientific work: context that remains useful, results that remain inspectable, and automation that leaves a person able to understand and intervene.

Code, releases, papers, and records

  1. code

    iowarp/clio-coder

    Source, tests, docs, changelog, roadmap, and the full commit history since April 2026.

  2. release

    v0.7.0, November 9, 2026

    CLIO Coder v0.7.0 adds the data tool for HDF5, NetCDF, and Parquet, sealed reproduce checks judged against a tolerance, a per-project claims ledger, and the research and arena commands.

  3. package

    @iowarp/clio-coder on npm

    The install path. One command, then the configure wizard.

  4. documentation

    Product guides

    Model connections, tools, permissions, project checks, and current workflows.

  5. documentation

    Fleet dispatch

    How bounded workers run over SSH across a cluster with the same admission path and receipts.

  6. code

    akougkas/warpio-cli

    The 2025 stage of the line. A Gemini CLI fork with scientific personas and context handover.

  7. documentation

    Open research questions

    What is measured so far, and a first experiment for each question.

  8. documentation

    Install on a cluster

    Installing on a login node with old glibc, a proxy, or no internet.

Releases

  1. CLIO Coder v0.7.0

    adds the data tool for HDF5, NetCDF, and Parquet, sealed reproduce checks judged against a tolerance, a per-project claims ledger, and the research and arena commands.

People

Related notes

  1. essay

    An accountable agent says what it is waiting on

    Across the CLIO Coder 0.6 line, from v0.6.0 on October 3 to v0.6.9 on November 6, accountability narrowed to two statements an agent should be able to make at any moment: under whose authority it acts, and what it is waiting on.

    5 min
  2. essay

    A capable model in a capable harness

    Claude 3.5 Sonnet brought me back to writing code. A capable model still needs a harness that makes its progress checkable and its cost visible, and CLIO Coder is the one I built around models that many people can afford to use.

    4 min
  3. essay

    Why CLIO Coder, part 5 of 5: decisions without prose

    A coding harness makes hundreds of small decisions per turn, and a chat model is the wrong instrument for them. CLIO Coder v0.5.3 binds four decision sites to a System One model that returns a calibrated distribution over a closed answer shape, and adds a diffusion runtime for the latency-sensitive slot beside it.

    10 min
  4. essay

    Shipping a coding agent in public

    CLIO Coder reached v0.5.0 on September 20, 2026. Measuring that launch against the definition of shipped I wrote in August: what had to be true before public was the right word, what was labelled an early preview, and what is still not true.

    6 min
  5. tutorial

    A closed loop for AI-assisted research writing

    Install CLIO Coder, WTF-P, and CiteNexus on Linux and run a first supervised writing session: the agent keeps the bookkeeping, every citation stays traceable to its source, and the author keeps the judgment.

    12 min
  6. tutorial

    Run CLIO Coder against a model on your own GPU

    Install CLIO Coder from npm, point it at a local llama.cpp or LM Studio server, run one headless turn, and read the receipt it seals.

    6 min
  7. essay

    Context is part of the system

    A capable model still fails when the system hands it the wrong slice of reality. CLIO's answer is to treat context the way a database treats state, and to seal a receipt for every action.

    5 min
  8. field note

    Vibe Coding Fridays

    Twelve Fridays, three hours each, teaching a research group to work with coding agents: the frame that stuck, the bake-off at week five, the checklist, and what I would change.

    6 min
  • 2025–present

    CLIO

    A context layer for scientific AI agents and workflows.

  • 2024–present

    IOWarp

    Context management infrastructure for scientific AI.

  • 2020–present

    DeepIO

    Data movement and I/O analysis for scientific AI.