# hiveloom 1.0.0 documentation

> An agent is a model plus its harness. hiveloom confines an agent to one task by declaring its tools, context, loop policy, budgets, guardrails, and deterministic acceptance checks in a portable folder.

This documentation is designed for direct agent access. Every page below is raw Markdown; fetch https://docs.hiveloom.cloud/v1.0.0/llms-full.txt for a single-context version. The current stable release and available documentation editions are listed in https://docs.hiveloom.cloud/versions.json.

## Start here

- [Introduction](https://docs.hiveloom.cloud/v1.0.0/index.md): Confine an agent to one job — and make success provable.
- [Task confinement](https://docs.hiveloom.cloud/v1.0.0/task-confinement.md): A hiveloom harness confines an agent to one job and makes success provable.
- [Install](https://docs.hiveloom.cloud/v1.0.0/install.md): hiveloom 1.0.0 is released and available through Python package indexes. It requires Python 3.11 or newer.
- [Quickstart](https://docs.hiveloom.cloud/v1.0.0/quickstart.md): This builds a real harness from nothing, runs it without an API call, then runs it for real. Every mutation is validated and rolls back on error.
- [Evaluations](https://docs.hiveloom.cloud/v1.0.0/evals.md): Three checked-in evaluations live in evals/, each with its harnesses, scoring code, and committed results. They answer three different questions, and the answers are not the same. 

## Reference

- [Harness spec](https://docs.hiveloom.cloud/v1.0.0/spec.md): The harness spec is the task-confinement contract: a declarative YAML document (harness.yaml) that fixes the task, available capabilities, autonomy limits, acceptance checks, and e
- [Architecture](https://docs.hiveloom.cloud/v1.0.0/architecture.md): hiveloom starts from a simple definition: agent = model + harness. It confines that agent to one job and makes its success provable. The harness declares the task, tools, context, 
- [Models and providers](https://docs.hiveloom.cloud/v1.0.0/models.md): A harness names the model it executes with in two fields:
- [Extending](https://docs.hiveloom.cloud/v1.0.0/extending.md): hiveloom's catalog is open: tools, guardrails, validators, loop policies, compaction methods, event hooks, and model providers are catalog entries, and extensions register new entr

## Build and debug

- [The workbench](https://docs.hiveloom.cloud/v1.0.0/workbench.md): The workbench is hiveloom's development UI: a chat-first environment for building, running, debugging, and improving harnesses without first learning the CLI or the specification l
- [Journal and forks](https://docs.hiveloom.cloud/v1.0.0/journal.md): Every run writes an append-only JSONL journal into the harness's .hiveloom/traces/. From 1.0.0 that journal is progressive, self-describing, and tamper-evident — complete enough to

## Operate

- [Deploying and evolving](https://docs.hiveloom.cloud/v1.0.0/deploying-and-evolving.md): For the proposed one-click, sandboxed chat/API deployment path, including controlled LLM internet access and shared-token protection, see One-click harness deployment with OpenShel
- [Control plane](https://docs.hiveloom.cloud/v1.0.0/control-plane.md): hiveloom control-plane <harness-dir> exposes a deployed harness's CLI surface over HTTP, bearer-authenticated with the ed25519 keys described below — a selected operational subset,
- [Link/sync protocol](https://docs.hiveloom.cloud/v1.0.0/sync-protocol.md): hiveloom cloud link pairs a local harness directory with a server, and hiveloom cloud sync (or --sync on hiveloom run) keeps the two sides converged. The protocol was built for hiv

## Source

- [Repository](https://github.com/FrancescoMrn/hiveloom)
- [Evaluations](https://github.com/FrancescoMrn/hiveloom/blob/main/evals/README.md)