---
title: "Agent context"
description: "Carry repository context, project configuration, and user preferences into each agent run."
canonical_url: "https://hoplite.sh/docs/agent"
markdown_url: "https://hoplite.sh/docs/agent.md"
---

# Agent context
URL: /docs/agent
LLM index: /llms.txt
Description: Carry repository context, project configuration, and user preferences into each agent run.
Related: /docs/agent/models, /docs/agent/tools, /docs/threads

# Agent context

Hoplite assembles each run's context from its thread, repository, project configuration, and initiating user, so follow-up work can build on the task's history and your team's conventions. Repository access and connected tools are scoped separately from personal preferences.

## Repository and project context

The root `AGENTS.md` is loaded before the first model call. `CLAUDE.md` is a compatibility fallback when `AGENTS.md` is absent. The agent reads nested instructions as it works in the relevant directories.

[Project instructions](/docs/agent/instructions) are included in every project run. [Skills](/docs/agent/skills) are discovered from the repository and the initiating user's hosted library, then read when needed.

Repository agents can retrieve history from the same project, including threads owned by other members. They cannot widen that search to another project. See [access boundaries](/docs/workspace/security#conversation-and-artifact-access).

## Personalize agent output

Under **Settings → Agent personalization**, **Agent verbosity** controls how much detail the agent writes back: low, medium, or high. **Code comments** controls the comments it adds to authored code: off, brief, or verbose. The defaults are medium verbosity and brief comments, and repository conventions still take precedence when they require a different style.

These are per-user settings enforced for every run you start. Automatic continuations such as PR autofix keep the output preferences of the thread owner whose work they continue.

## Large tool outputs

Free workspaces automatically condense large tool outputs with a second model to reduce context usage, including runs without a thread owner. This behavior cannot be disabled on Free.

On paid plans, **Settings → Agent personalization → Advanced → Condense large tool output** is a per-user opt-in, off by default. Runs with an owner use that owner’s preference, including automatic continuations; ownerless paid runs do not inherit a personal preference.

## Personal memories

Under **Settings → Agent personalization → Agent memories**, you can review,
create, edit, and delete durable personal memories. They are available only to
agents you start; unattended automation runs without an initiating user do not
inherit anyone's private context.

The agent can save or update a concise, stable cross-thread preference without
interrupting you for per-write approval. After a successful run, Hoplite may
also curate an explicitly stated stable preference from your opening message.
It does not infer preferences from agent output, tool results, repository
content, or external data, and it rejects secrets, credentials, sensitive
personal data, raw conversation text, repository or project facts, commands,
branches, tickets, and temporary task state.

Memory changes apply to later runs. A run already in progress keeps the
immutable memory snapshot it started with, even if you edit or delete a memory
from settings while that run is active.

## Sitemap

Sitemap discovery is not enabled for this deployment.