django-orbit 0.10.0

AI agent-native observability and debugging for Django

Django Orbit

AI agent-native observability and debugging for Django.

Django Orbit is a reusable Django app that records what your application is doing and exposes it through a dashboard and MCP tools. It captures requests, SQL queries, logs, exceptions, cache operations, jobs, storage, mail, permissions and more, then links related events by family_hash so humans and AI agents can debug from one coherent timeline.

Unlike Django Debug Toolbar, Orbit does not inject HTML into your app. It lives at its own isolated /orbit/ URL and is designed to observe from a distance without interfering with the host project.

• Documentation
• Try the demo
• MCP / AI assistant setup

Why Orbit

Django teams increasingly debug with AI coding agents, but most local observability tools are built only for humans. Orbit is built for both:

• humans get a focused dashboard for inspecting runtime behavior;
• agents get structured MCP tools for investigation and handoff;
• captured events are grouped by request family, so evidence stays connected;
• agent output is masked, bounded and read-only by default.

Capability	Django Debug Toolbar	Django Orbit
Runs outside your app UI	No	Yes
Works with APIs and SPAs	Limited	Yes
Persistent request history	No	Yes
SQL, logs and exceptions together	Partial	Yes
Background jobs and infrastructure events	No	Yes
Agent-native MCP debugging tools	No	Yes
Request-to-fix handoff bundles	No	Yes
Plug-and-play watcher health	No	Yes

Inspired by Laravel Telescope, Spatie Ray and Django Debug Toolbar.

What Orbit Tracks

Category	Events
HTTP	Requests, responses, headers, body, status codes
Database	SQL queries, slow queries, duplicate query / N+1 signals
Logging	Python logging output, any level
Exceptions	Exception type, message, traceback and request context
Cache	GET hits/misses, SET, DELETE
Models	ORM create, update and delete events
Commands	manage.py executions with exit code
HTTP Client	Outgoing requests via supported clients
Mail	Sent email metadata and body previews
Signals	Django signal dispatches
Jobs	Celery, Django-Q, RQ and APScheduler signals/hooks
Redis	GET, SET, DEL, HGET, LPUSH and more
Permissions	Authorization checks, granted/denied
Transactions	atomic() commits and rollbacks
Storage	File save/open/delete operations

All events can be linked by family_hash, which lets you inspect every query, log and exception associated with one request or operation.

What's New in v0.10.0

Orbit v0.10.0 introduces the agent-native debugging base:

• safe MCP serialization with sensitive-key masking and deterministic truncation;
• audit_mcp_exposure to inspect the effective agent data policy;
• investigate_request for request-family diagnosis;
• investigate_exception_group for exception blast-radius analysis;
• create_incident_bundle for JSON or Markdown handoff bundles;
• build_debug_brief for matching ticket/error text to Orbit evidence;
• propose_fix_hypotheses for ranked fix directions;
• propose_test_plan for regression/performance test suggestions;
• MCP_ENABLED: False now blocks all MCP tools with a stable disabled response.

Telemetry opt-in is not part of v0.10.0. It is intentionally being kept for a separate future release.

Installation

pip install django-orbit

For AI assistant integration, install the MCP extra:

pip install django-orbit[mcp]

Quick Start

Add Orbit to INSTALLED_APPS:

INSTALLED_APPS = [
    # ...
    "orbit",
]

Add the middleware early in the stack:

MIDDLEWARE = [
    "orbit.middleware.OrbitMiddleware",
    # ...
]

Mount the dashboard URLs:

from django.urls import include, path

urlpatterns = [
    path("orbit/", include("orbit.urls")),
    # ...
]

Run migrations and start Django:

python manage.py migrate orbit
python manage.py runserver

Visit http://localhost:8000/orbit/.

Try the Demo

git clone https://github.com/astro-stack/django-orbit.git
cd django-orbit
pip install -e .
python demo.py setup
python manage.py runserver

URL	Purpose
http://localhost:8000/	Demo app
http://localhost:8000/orbit/	Orbit dashboard
http://localhost:8000/orbit/stats/	Stats dashboard
http://localhost:8000/orbit/health/	Watcher health dashboard

MCP AI Assistant Setup

Orbit exposes a local MCP server so AI assistants can query live Django runtime evidence.

pip install django-orbit[mcp]

Add this server to Claude Desktop, Cursor, Windsurf or any MCP-compatible client:

{
  "mcpServers": {
    "django-orbit": {
      "command": "python",
      "args": ["manage.py", "orbit_mcp"],
      "cwd": "/path/to/your/django/project"
    }
  }
}

The server launches on demand over stdio. It is read-only: it queries OrbitEntry data and never mutates the host app.

Raw Telemetry Tools

Tool	Purpose
get_recent_requests	Last N requests with status, path and duration
get_slow_queries	SQL queries above the configured threshold
get_exceptions	Exceptions within a time window
get_n1_patterns	Requests with duplicate-query evidence
get_request_detail	All events for one family_hash
search_entries	Keyword search across entries
get_stats_summary	Error rate, average response time and cache stats

Agent-Native Tools

Tool	Purpose
audit_mcp_exposure	Show the effective MCP safety policy
investigate_request	Diagnose one request family: timeline, signals, queries, hypotheses and next actions
investigate_exception_group	Summarize an exception fingerprint and affected paths
create_incident_bundle	Create JSON or Markdown handoff from request, fingerprint or ticket text
build_debug_brief	Match natural-language ticket text to recent evidence
propose_fix_hypotheses	Rank likely fix directions from captured evidence
propose_test_plan	Suggest regression/performance tests for the observed issue

Agent Workflow

A typical ticket-to-fix handoff looks like this:

build_debug_brief("checkout returns 500 payment token rejected")
create_incident_bundle("fingerprint", "<fingerprint>", format="markdown")
propose_fix_hypotheses("fingerprint", "<fingerprint>")
propose_test_plan("family_hash", "<family_hash>")

The goal is not for Orbit to edit code. The goal is to give a human or coding agent enough structured, safe evidence to reproduce, test and fix the issue.

Agent Safety

Agent-facing output goes through Orbit's safe serializer:

• sensitive keys are masked using MASK_KEYS;
• payloads can be disabled with MCP_INCLUDE_PAYLOADS: False;
• result sizes are bounded by MCP_MAX_LIMIT;
• oversized payloads are replaced with truncation metadata;
• MCP_ENABLED: False blocks all MCP tools with a stable disabled response.

Example:

ORBIT_CONFIG = {
    "MCP_ENABLED": True,
    "MCP_INCLUDE_PAYLOADS": True,
    "MCP_MAX_LIMIT": 100,
    "MCP_MAX_PAYLOAD_CHARS": 12000,
}

Configuration

All settings go in ORBIT_CONFIG or ORBIT in settings.py. Most projects can start with defaults.

ORBIT_CONFIG = {
    "ENABLED": True,
    "SLOW_QUERY_THRESHOLD_MS": 500,
    "STORAGE_LIMIT": 1000,

    # Access control. Set this for shared/staging environments.
    "AUTH_CHECK": lambda request: request.user.is_staff,

    # Keep Orbit from breaking the host app if a watcher fails.
    "WATCHER_FAIL_SILENTLY": True,

    # MCP / agent exposure controls.
    "MCP_ENABLED": True,
    "MCP_INCLUDE_PAYLOADS": True,
    "MCP_MAX_LIMIT": 100,
    "MCP_MAX_PAYLOAD_CHARS": 12000,
}

All watchers can be controlled individually with RECORD_* flags such as RECORD_REQUESTS, RECORD_QUERIES, RECORD_EXCEPTIONS, RECORD_JOBS, RECORD_REDIS, RECORD_TRANSACTIONS and RECORD_STORAGE.

See the configuration docs for the full list.

Dashboard

Main Dashboard: /orbit/

The main dashboard shows a live feed of captured entries. You can filter by type, search, inspect details, export JSON and navigate related entries.

Stats Dashboard: /orbit/stats/

The stats dashboard summarizes request throughput, Apdex, percentiles, error rate, slow queries, cache hit rate, job health and security/permission signals.

Health Dashboard: /orbit/health/

Each watcher registers with Orbit's health system. Failed or missing integrations are shown without taking down the rest of Orbit.

Storage Backends

By default, Orbit stores entries in the project's default database. For production or heavier usage, route Orbit writes to a dedicated database alias:

DATABASES = {
    "default": {...},
    "orbit": {
        "ENGINE": "django.db.backends.sqlite3",
        "NAME": BASE_DIR / "orbit.sqlite3",
    },
}

ORBIT_CONFIG = {
    "STORAGE_BACKEND": "orbit.backends.django_db.DjangoDBBackend",
    "STORAGE_DB_ALIAS": "orbit",
}

python manage.py migrate orbit --database=orbit

Security Model

Orbit is powerful because it records application behavior. Treat access to /orbit/ and MCP as developer/operator access.

Recommended defaults for shared environments:

ORBIT_CONFIG = {
    "AUTH_CHECK": lambda request: request.user.is_staff,
    "MCP_ENABLED": False,  # enable only where local agent access is intended
    "WATCHER_FAIL_SILENTLY": True,
}

Orbit masks common sensitive keys in request data and agent-facing output, but you should still avoid exposing Orbit dashboards or MCP servers to untrusted users.

Roadmap

The v0.10.0 base makes Orbit agent-native. Next tracks:

• OpenTelemetry bridge for interoperability with wider observability tooling;
• AI/LLM watcher for provider/model/token/tool-call metadata;
• dashboard affordances for copying incident bundles;
• GitHub/Jira ticket handoff flows;
• deeper query and regression analysis.

See Agent-Native Roadmap.

Contributing

Contributions are welcome. See CONTRIBUTING.md.

License

MIT. See LICENSE.