feat: add agent-os bootstrap bundle

2026-07-02 14:48:49 +00:00
parent d0a9a267fd
commit 5f9302abc5
20 changed files with 715 additions and 0 deletions
@@ -0,0 +1,23 @@
+# Runtime output is generated on the server and must not become source history.
+logs/
+
+# Bootstrap exports are generated bundles. Source lives in bootstrap/templates/.
+bootstrap/exports/
+
+# Claude Code compatibility memory is generated/symlinked runtime state.
+claude-code/
+
+# Local secrets and deployment state must never be committed.
+.env
+.env.*
+!.env.example
+*.log
+__pycache__/
+*.pyc
+.cache/
+data/
+uploads/
+backups/
+*.db
+*.sqlite
+*.sqlite3
@@ -0,0 +1,36 @@
+# Agent OS Project Brief
+
+## What This Project Is
+
+Agent OS is a tool-agnostic, plain-files operating layer for LLM agents. Markdown files are the shared memory, operating contract, and handoff surface.
+
+## Runtime
+
+- Server runtime root: `/opt/agent-os/`
+- Scheduled jobs: local scheduler or cron on the server
+- Agent web output: `/opt/sites/<short-name>/`
+- Agent status logs: `/opt/agent-os/logs/<agent>/last-run.json`
+
+## Required Output Contract
+
+Every scheduled or autonomous agent should write:
+
+- `last-run.json` at `/opt/agent-os/logs/<agent>/last-run.json`
+- `last-output.md` at `/opt/sites/<short-name>/last-output.md`
+
+Keep `last-output.md` concise: heading, timestamp, and useful summary.
+
+## Repository Rules
+
+- Gitea or the configured remote is the recoverable source of truth.
+- Runtime state, logs, caches, credentials, databases, uploads, and generated exports stay out of commits.
+- Review and validate changes before deployment.
+- Copy successful live fixes back to the edit clone before committing.
+
+## First-Run Checklist
+
+1. Fill in `identity.md`.
+2. Fill in stable infrastructure facts in `brain.md`.
+3. Record non-negotiable constraints in `memory/constraints.md`.
+4. Replace this project brief with environment-specific status.
+5. Add real skills under `skills/<skill-name>/`.
@@ -0,0 +1,31 @@
+# Agent OS
+
+A plain-files operating layer for agents and LLM tools.
+
+## First Read
+
+1. Read `identity.md` for owner preferences, hard limits, and communication style.
+2. Read `brain.md` for stable infrastructure and project facts.
+3. Read `memory/active-projects.md` for current work.
+4. Read `memory/constraints.md` for non-negotiable safety rules.
+5. Read `CLAUDE.md` for runtime conventions and project status.
+
+## Runtime Contract
+
+- Runtime root: `/opt/agent-os/`
+- Machine-readable agent status: `/opt/agent-os/logs/<agent>/last-run.json`
+- Human-readable agent output: `/opt/sites/<short-name>/last-output.md`
+- Credentials: reference the approved secret store only; do not write secret values into this repo.
+
+## Directory Layout
+
+| Path | Purpose |
+|---|---|
+| `identity.md` | Owner profile, communication preferences, hard limits |
+| `brain.md` | Stable facts, services, hosts, ports, standing decisions |
+| `memory/` | Persistent and recent working memory |
+| `context/` | Dated task-specific working notes |
+| `skills/` | Repeatable workflows and skill learnings |
+| `logs/` | Generated runtime status output, ignored by Git |
+
+This bundle is generic. Replace placeholders before trusting an agent to act.
@@ -0,0 +1,37 @@
+# Brain
+
+Stable facts that every agent may need.
+
+## Infrastructure
+
+| Name | Address | Purpose | Notes |
+|---|---|---|---|
+|  |  |  |  |
+
+## Services
+
+| Service | URL | Port | Owner | Notes |
+|---|---|---|---|---|
+|  |  |  |  |  |
+
+## Agents
+
+| Short Name | Full Name | Role | Status | Output |
+|---|---|---|---|---|
+|  |  |  |  |  |
+
+## Repositories
+
+| Repository | Remote | Runtime Path | Notes |
+|---|---|---|---|
+|  |  |  |  |
+
+## Standing Decisions
+
+- Keep generated runtime output out of Git.
+- Keep credentials in the approved secret store only.
+- Prefer reviewed edit-clone changes over live-only edits.
+
+## Open Questions
+
+-
@@ -0,0 +1,29 @@
+# Identity
+
+## Owner
+
+- Name:
+- Organization:
+- Role:
+- Primary timezone:
+- Preferred working hours:
+
+## Communication Preferences
+
+- Preferred tone:
+- Detail level:
+- Escalation style:
+- Decision-making preferences:
+
+## Hard Limits
+
+- Do not expose credentials, private keys, or customer data.
+- Do not perform destructive or high-impact actions without explicit approval.
+- Do not restart or redeploy production services unless the requested change requires it and validation is ready.
+
+## Useful Context
+
+- Important people:
+- Important systems:
+- Standing priorities:
+- Things to avoid:
@@ -0,0 +1,7 @@
+# Active Projects
+
+Update this file when work starts, pauses, completes, or changes owner.
+
+| Project | Status | Owner | Next Action |
+|---|---|---|---|
+|  |  |  |  |
@@ -0,0 +1,19 @@
+# Constraints
+
+Rules in this file override convenience.
+
+## Security
+
+- Never write credential values into code, logs, docs, generated reports, or chat output.
+- Use placeholder examples for configuration shape.
+- Treat customer data and private infrastructure details as sensitive.
+
+## Operations
+
+- Confirm target path, branch, remote, and worktree status before deployment.
+- Keep live fixes synchronized back to the edit clone.
+- Validate syntax and intended behavior before service reloads or restarts.
+
+## Environment-Specific Limits
+
+-
@@ -0,0 +1,7 @@
+# Notes From Last Run
+
+Clear or roll up this file at the start of each new session.
+
+## Notes
+
+-
@@ -0,0 +1,19 @@
+# Persistent Memory
+
+Facts that are expected to remain true for a long time.
+
+## People
+
+-
+
+## Systems
+
+-
+
+## Preferences
+
+-
+
+## Lessons
+
+-
@@ -0,0 +1,7 @@
+# Recent Decisions
+
+Record decisions from the last 30 days or the current work cycle.
+
+| Date | Decision | Reason | Follow-Up |
+|---|---|---|---|
+|  |  |  |  |
@@ -0,0 +1,21 @@
+# Handoff
+
+## Objective
+
+-
+
+## Completed
+
+-
+
+## Validation
+
+-
+
+## Risks
+
+-
+
+## Next Action
+
+-
@@ -0,0 +1,17 @@
+{
+  "schema_version": 1,
+  "criteria": [
+    {
+      "name": "correctness",
+      "description": "The skill produces the requested result without inventing facts."
+    },
+    {
+      "name": "safety",
+      "description": "The skill respects credentials, approvals, and operational limits."
+    },
+    {
+      "name": "handoff_quality",
+      "description": "The skill writes clear output and next steps for humans or other agents."
+    }
+  ]
+}
@@ -0,0 +1,5 @@
+# Learnings
+
+Append stable lessons from real runs. Keep this concise and actionable.
+
+-
@@ -0,0 +1,26 @@
+# Skill Name
+
+## Purpose
+
+Describe what this skill does and when an agent should use it.
+
+## Inputs
+
+-
+
+## Workflow
+
+1. Read the relevant context.
+2. Perform the smallest safe action that satisfies the request.
+3. Write outputs to the documented runtime paths.
+4. Record useful learnings in `learnings.md`.
+
+## Outputs
+
+- `/opt/agent-os/logs/<agent>/last-run.json`
+- `/opt/sites/<short-name>/last-output.md`
+
+## Safety
+
+- Do not expose secrets.
+- Ask for approval before destructive or high-impact actions.