opentrace/opentrace · indexed live

Your AI coding tools see files.
Not your system.

OpenTrace maps your entire codebase into one living knowledge graph — every function, dependency, and call path. Watch it build itself, from OpenTrace's own source.

0nodes mapped
0relationships
0sto index
Get Started Free Visualize your repo
Scroll to explore ↓
Architecture, discovered

It finds the
real modules.

OpenTrace runs community detection over the graph and the codebase organizes itself into cohesive modules — scored by how tightly they hang together. Real structure that emerges from how the code actually connects: calls, imports, and dependencies.

One graph

It all folds into
one living graph.

The modules snap back together into a single knowledge graph that stays current as your code changes — one complete map your AI can query, instead of a pile of disconnected files.

Ask your system anything
▶ opentrace.query(…)

Trace any path
through your system.

OpenTrace walks the real call graph — not a guess. Here it traces the exact chain from … down to …, hop by hop.

Blast radius
▶ opentrace.impact(requestRender)

Change one function.
See what breaks.

Your AI can't see this. OpenTrace traces every downstream caller of requestRender() across the whole system — instantly, before a single line ships.

0
dependents in the blast radius
One graph, every repo

This is one repo.
Now picture your org.

Point OpenTrace at your whole org and it connects every repo into one graph through their shared dependencies. Here opentrace/opentrace joins two more real, indexed repos — 19 shared dependencies between them.

Connect your AI

One graph.
Every AI tool.

Pipe this context straight into your coding agents through MCP. They stop guessing about your architecture and start working from how it actually runs.

Claude Code Cursor Copilot Codex OpenCode
Get Started Free Become a Design Partner
OpenTrace OSS

Open Source Knowledge Graph — Free to Use

The OpenTrace OSS knowledge graph tool is free under the Apache 2.0 license. Index your repositories, explore architecture, and analyse codebases — self-hosted on your own infrastructure, with full access to the source code.

Free to use
Self-host on your infrastructure
No vendor lock-in
Community-driven
Try it Live — No Account Needed Star on GitHub

Explore an example repo instantly — no sign-up required.

claude code
> If I rename chargeCard(), what breaks?
⏺ Calling opentrace.find_usages…
⎿ 12 call sites across 4 services

chargeCard() is called from 12 sites across billing-api, order-service, payments-svc, and notification-svc. Hot path is POST /checkout (~14k req/s, p99 42ms). Three callers live outside this repo. I'll draft a rename with a deprecation shim.

Claude Code

Claude Code,
with your system's context

Install the OpenTrace plugin for Claude Code and give Anthropic's coding agent live access to your architecture graph: dependencies, runtime data, ownership, and history. Stop pasting stack traces. Start asking.

  • Official Claude Code plugin Two commands to install from the OpenTrace marketplace. Claude Code can then query your entire system, from repo structure to prod metrics.
  • Grounded code generation Claude sees how your services actually connect, so its suggestions match real architecture instead of plausible-looking fiction.
  • Safe refactors by default Before proposing a change, Claude checks the blast radius, dependents, and recent incidents for the code it's touching.
claude plugin marketplace add https://github.com/opentrace/opentrace claude plugin install opentrace-oss@opentrace-oss
Setup Guide
How It Works

Index once. Query forever.

OpenTrace unifies three layers of truth into one graph — then keeps it live. Your AI queries the whole picture through a single MCP connection.

01

Code Layer

Continuously maps repositories, services, classes, and dependencies in real-time via Git commits. Understands not just what your code is, but how it connects.

GitHub GitLab Bitbucket 
// Auto-detected dependency graph
payment-api
  ├── imports auth-middleware
  ├── calls user-service/v2
  ├── queries billing-db
  └── emits payment.completed
02

Runtime Layer

Unifies deployments, traces, logs, infrastructure state, performance metrics, and tickets into a single operational view. See what's actually happening, not what should be.

AWS GCP Azure Kubernetes Datadog Grafana
Latency p99 42ms -12%
Error Rate 0.02% -8%
Throughput 14k/s +23%
Services 47 stable
03

Context Layer

Links code and runtime data into a unified knowledge graph, providing actionable system insight to AI tools and engineers. The connective tissue that makes everything queryable.

Claude Linear Jira Slack
Code Traces Deploys
Logs Tickets Metrics Infra
Code Review

Reviews that actually
know your code

Most AI code reviewers only see the diff. OpenTrace sees the full picture: every dependency, every downstream consumer, every production metric behind the code you're changing.

  • Blast radius detection Automatically maps which services, endpoints, and data flows are affected by a change
  • Runtime-aware feedback Surfaces latency, error rates, and traffic patterns for the code paths you're modifying
  • Architectural context Understands ownership, deprecation plans, and historical incidents, not just syntax
Try Now
payments/checkout.ts 3 services affected
42 - const timeout = 5000;
42 + const timeout = 15000;
OpenTrace

This timeout change affects billing-api, order-service, and notification-svc. Current p99 latency for this path is 3.2s. Increasing to 15s may mask upstream failures. Last incident on this path: 12 days ago (PAY-1847).

<20% of companies are getting real gains and ROI from AI coding tools Gartner
90% of enterprise engineers will use AI coding assistants by 2028 Gartner
200x more frequent deploys with deep system context Google Cloud DORA Report
3x fewer failures with architecture-aware deployments Google Cloud DORA Report
Integrations

Works with the AI tools you already use

OpenTrace plugs directly into Claude Code, Cursor, Copilot, and more via MCP — enriching every AI tool in your stack with deep system context, instantly.

Source Control

Indexes code, PRs, and dependency graphs across your repositories in real time.

GitHub
GitHub
GitLab
GitLab
Bitbucket
Bitbucket
Infrastructure

Maps deployments, services, and infrastructure topology as they run.

AWS
AWS
Kubernetes
Kubernetes
Observability

Connects spans, traces, and logs back to the code and services that produce them.

Grafana
Grafana
Tempo
Tempo
AI & Workflow

Surfaces messages, tickets, and decisions, giving AI agents direct access via MCP.

Slack
Slack
Linear
Linear
Claude
Claude
Codex
Codex
Gemini CLI
Gemini CLI
MCP
MCP
Use Cases

From chaos to clarity

Ship Complex Changes

Large refactors and migrations become data-driven. Know the blast radius before you push, not after the pager goes off.

Velocity Without Blind Spots

Eliminate manual code archaeology. Turn days of investigation into seconds with instant system queries.

Reduce Operational Incidents

Identify weak links and failure chains before they cascade. Your architecture becomes a living safety net.

Ready to make your AI actually
work for your organisation?

Join the teams already using OpenTrace to unlock the real ROI from their AI coding tools — with full system context, confidence, and control.

Get Started Free Apply for Design Partner Program

No credit card required. Design Partners get direct access to the founders and shape the product roadmap.

Frequently Asked Questions

What is OpenTrace?

OpenTrace is the context layer for AI-assisted engineering. It builds a living knowledge graph of your entire system — code structure, service dependencies, ownership, runtime behaviour, and operational history — and connects it to your AI coding tools via MCP. This gives tools like Claude Code, Cursor, and Copilot the situational awareness they need to work safely and effectively in your codebase.

Why aren't companies getting ROI from AI coding tools?

According to Gartner, less than 20% of companies are getting real gains and ROI from AI coding tools. The core reason is that AI tools lack system context — they don't know your dependencies, who owns what, what has broken before, or what the blast radius of a change is. OpenTrace provides this context, enabling AI to work confidently and safely in your systems.

How does OpenTrace integrate with Claude Code, Cursor, and Copilot?

OpenTrace connects to AI coding tools via MCP (Model Context Protocol). Once connected, your AI tools can query your knowledge graph in real time — understanding service dependencies, ownership, blast radius, and operational history before making any change.

Does OpenTrace have an open source version?

Yes. OpenTrace OSS is a free, open-source knowledge graph tool available under the Apache 2.0 licence. It lets engineering teams index repositories, analyse codebases, and explore architecture — self-hosted on your own infrastructure. A hosted platform with additional engineering agent capabilities is also available.

What is situational awareness in AI engineering?

Situational awareness in AI engineering means giving AI systems the same contextual understanding that experienced engineers carry — knowing which services are critical, who owns what, what has broken before, what the blast radius of a change is, and what operational constraints exist. Without situational awareness, AI tools produce changes that are technically correct but operationally wrong.