Follow CONTRIBUTING.md and the component's instructions. For validation and shipping, use docs/validation-and-release.md. For product names, terminology, and visible copy, follow the Naming System. - Measure the user's request through completion. Record implementation, validation, merge, publication, and waiting separately; an Actions duration is not the total. - Choose the necessary checks before starting them. Run affected tests and relevant integration checks; use full suites for broad changes. Start independent checks together within the machine's capacity. Do not add a second full…
1.4k17d agoReviewMountCreate a free account to mount
Read this before changing anything under cli/. The repository-wide process rules (validation, merging, releases) are in ../AGENTS.md. The design, and why, is in ../docs/design/2026-10-03-harnessd.md. The one-page picture for new contributors is ../docs/design/2026-10-04-harnessd-before-after.md. The master runs the core and every service process (SERVICE_HOSTS in src/harnessd/services.ts). Each service process runs one or more services, each on its own link to the core. In Activity Monitor and ps they show as harnessd, harnessd-core and harnessd-<process> (src/harnessd/processName.ts). HARNESSDSERVICES names a subset to run in…
Steady38 mentions in 2 weeks
No other project uses it yet
1.4k17d agoReviewMountCreate a free account to mount
Use CLAUDE.md for architecture, build commands, and testing. For DSH dashboards, follow the DSH workspace contract: 70% viewer on the left, 30% real agent chat on the right, including loading, missing dependencies, failures, retries, and restoration. Reserve the chat slot before startup; never let an unavailable conversation become a full-width viewer. The Swarm's Your devices is a dashboard-only exception: fill its center pane, keep the sidebars visible, and do not start or reserve a Devices conversation. Standalone Devices retains its…
Steady38 mentions in 2 weeks
No other project uses it yet
1.4k17d agoReviewMountCreate a free account to mount
Harness Desktop — a Flutter app that lists Harness machines and attaches xterm terminals to the agents running on them. macOS and Linux (Ubuntu) are both real, released targets — first-run provisioning (lib/bootstrap/environmentprovisioner.dart), self-update (lib/update/desktopupdater.dart), and packaging (scripts/upload-desktop.sh / scripts/upload-desktop-linux.sh, see RELEASE.md) all branch per-OS internally rather than being separate code paths. Windows is a local desktop too, not a viewer (lib/core/viewermode.dart): homeDir() (lib/core/homedir.dart) reads USERPROFILE there even when Git Bash set HOME, console children start through lib/core/hiddenprocess.dart so no…
1.4k17d agoReviewMountCreate a free account to mount
Before creating or changing a DSH, read the authoring guide and the DSH workspace contract. A DSH dashboard always has the real agent chat to its right, initially 70% viewer and 30% chat. Loading or failed setup must keep that chat slot and show recovery there. Verify the whole workspace, including failures, rather than only the viewer. Package AGENTS.md files describe the materialized agent's job; they do not replace this desktop integration contract.
Steady38 mentions in 2 weeks
1 project uses a version of this
1.4k17d agoReviewMountCreate a free account to mount
Follow CONTRIBUTING.md and the component's instructions. For validation and shipping, use docs/validation-and-release.md. For product names, terminology, and visible copy, follow the Naming System. - Measure the user's request through completion. Record implementation, validation, merge, publication, and waiting separately; an Actions duration is not the total. - Choose the necessary checks before starting them. Run affected tests and relevant integration checks; use full suites for broad changes. Start independent checks together within the machine's capacity. Do not add a second full…
Steady38 mentions in 2 weeks
No other project uses it yet
1.4k17d agoReviewMountCreate a free account to mount
Harness Desktop — a Flutter app that lists Harness machines and attaches xterm terminals to the agents running on them. macOS and Linux (Ubuntu) are both real, released targets — first-run provisioning (lib/bootstrap/environmentprovisioner.dart), self-update (lib/update/desktopupdater.dart), and packaging (scripts/upload-desktop.sh / scripts/upload-desktop-linux.sh, see RELEASE.md) all branch per-OS internally rather than being separate code paths. Windows is a local desktop too, not a viewer (lib/core/viewermode.dart): homeDir() (lib/core/homedir.dart) reads USERPROFILE there even when Git Bash set HOME, console children start through lib/core/hiddenprocess.dart so no…
Steady38 mentions in 2 weeks
No other project uses it yet
1.4k17d agoReviewMountCreate a free account to mount
Plain text files in a repository that tell a coding agent how the project works: commands to run, conventions to follow and things to avoid. CLAUDE.md, AGENTS.md, cursor rules and skills are the common kinds.
CLAUDE.md or AGENTS.md?
CLAUDE.md is read by Claude Code. AGENTS.md is an open format that Codex, Cursor and other agents read. Many projects keep one and point the other at it.
What is a skill?
A folder with a SKILL.md that describes one capability, such as filling PDFs or reviewing code. The agent loads it only when the task calls for it.
Can I search my own team's files too?
Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.
autonomous-aiAGENTS.md