AI Decision System
Replayable, offline-verifiable records for AI-assisted go/no-go decisions: experiment promotions, typed model answers and human-approved actions.
Less than 20% of companies get real ROI from AI coding tools. OpenTrace gives your AI the system context it needs — dependencies, ownership, history, blast radius — so engineers can trust what it buil
Developer toolsJavaScript · TypeScriptGitHub @opentraceOnlineOwner unconfirmed
Have you tried it? One tap is enough. No sign-in needed.
Owners of public repositories under a personal GitHub account can sign in to verify ownership and manage the introduction themselves. No administrator approval is needed.
Sign in, generate a verification file, and commit it to this repository’s default branch within 30 minutes. Files on other branches or forks do not count. Then check the file below to manage the project without administrator approval. Keep the file to retain your access.
If needed, you will go to sign-in. After signing in, return here and press your chosen verification button again.
Run /nomorevibe verify in your project folder to verify ownership and manage the introduction yourself.
Verify in one minuteAsk about other verification options
OpenTrace is a knowledge graph platform that maps system architecture, code structure, and service relationships giving you a visual, queryable map of how your codebase and infrastructure connect.
Taken from the repository README
Loading the full README. The saved excerpt is shown below.
A knowledge graph that maps your codebase structure, service architecture, and system relationships — then exposes it all through MCP so AI tools can understand your systems.
Index any repo, any size, in seconds. Build a knowledge graph and watch your LLM fetch true codebase context in realtime.
OpenTrace indexes source code and builds a queryable knowledge graph. Point it at a repo and it will:Read the full README ↗A knowledge graph that maps your codebase structure, service architecture, and system relationships — then exposes it all through MCP so AI tools can understand your systems.
OpenTrace indexes source code and builds a queryable knowledge graph. Point it at a repo and it will:
uvx opentraceai index . # Index a local project for use with MCP etc
/plugin marketplace add https://github.com/opentrace/opentrace
/plugin install opentrace-oss@opentrace-oss
/reload-plugins
More info: https://opentrace.github.io/opentrace/getting-started/install-plugin/
Add to ~/.config/opencode/opencode.json:
{
"$schema": "https://opencode.ai/config.json",
"plugin": ["@opentrace/opencode"]
}
More info: https://opentrace.github.io/opentrace/getting-started/install-opencode/
gemini mcp add opentraceai uvx opentraceai mcp
No install: app.opentrace.ai
git clone https://github.com/opentrace/opentrace.git && cd opentrace
make install && make ui # Runs on http://localhost:5173/
To enable knowledge vaults (LLM-compiled markdown wikis), also run the
agent's REST server in a second terminal and open the UI with a ?server=
query param so it reads from the backend:
uv --project agent run opentraceai serve # listens on http://localhost:8787
# then open: http://localhost:5173/?server=http://localhost:8787
See Wiki & Vaults for the compile flow and Wiki Providers for the supported LLM providers (Anthropic, Gemini, OpenAI, local).
Full documentation: opentrace.github.io/opentrace — install guides, architecture, and reference.
Prerequisites: plugins and CLI need uv; OpenCode plugin runs in Bun (provided by OpenCode itself). Source build also needs Node 22+ and Python 3.12+. See Troubleshooting if anything fails.
The plugin gives Claude Code 5 agents, 4 slash commands, and MCP graph tools.
| Agent | Description |
|---|---|
@opentrace | Default catch-all — any codebase question routed to the knowledge graph |
@code-explorer | Explore indexed code structure — find classes, functions, files, and relationships |
@dependency-analyzer | Analyze dependencies and blast radius for code changes |
@find-usages | Find all callers, references, and usages of a component |
@explain-service | Top-down walkthrough of how a service or module works |
| Command | Description |
|---|---|
/index | Index (or re-index) the current project into the knowledge graph |
/graph-status | Show overview of indexed nodes by type |
/explore <name> | Quick exploration of a named component in the graph |
/interrogate | Answer a question about the codebase without making changes |
Full details: Claude Code Plugin reference.
The plugin gives OpenCode 9 native tools and three hooks (system-prompt, tool-execute, auth) — calls the opentraceai CLI directly rather than going through MCP.
| Tool | Description |
|---|---|
opentrace_source_search | Symbol-level search across indexed code |
opentrace_semantic_search | Embedding-based search over node descriptions |
opentrace_source_read | Read source for a graph node by ID |
opentrace_source_grep | Grep across indexed source content |
opentrace_repo_index | Index a local path or remote git URL into the graph |
opentrace_find_usages | Find all callers and references of a component |
opentrace_impact_analysis | Blast radius analysis for a proposed change |
opentrace_graph_explore | BFS traversal with direction and depth controls |
opentrace_graph_stats | Node and edge counts by type |
Full details: OpenCode Plugin reference.
Full extraction (symbols + calls + imports): Python, TypeScript/JavaScript, Go Structural extraction (symbols only): Rust, Java, Kotlin, C#, C/C++, Ruby, Swift Indexed as file nodes: JSON, YAML, TOML, Protobuf, SQL, GraphQL, Bash
Full language matrix: Supported Languages.
┌───────────────────────────────────────────────────────────┐
│ UI (React/TS) │
│ Browser-based indexer + graph explorer │
│ localhost:5173 / app.opentrace.ai │
│ │
│ ┌───────────────┐ ┌─────────────────┐ ┌──────────────┐ │
│ │ Web Worker │ │ LadybugDB WASM │ │ Chat Agent │ │
│ │ tree-sitter │ │ (embedded │ │ LLM-powered │ │
│ │ WASM parsers │ │ graph store) │ │ graph tools │ │
│ └───────────────┘ └─────────────────┘ └──────────────┘ │
└───────────────────────────────────────────────────────────┘
┌───────────────────────────────────────────────────────────┐
│ Claude Code Plugin (MCP) │
│ Python agent exposes graph tools via MCP protocol │
│ uvx opentraceai mcp → stdio transport │
└───────────────────────────────────────────────────────────┘
┌───────────────────────────────────────────────────────────┐
│ OpenCode Plugin (native) │
│ TS plugin in OpenCode's Bun runtime — 9 tools + │
│ system-prompt, tool-execute, auth hooks │
│ opentraceai CLI → spawn (no MCP) │
└───────────────────────────────────────────────────────────┘
See Architecture Overview for details.
ui/ — React/TypeScript frontend (graph explorer + browser indexer)
agent/ — Python agent (CLI + MCP server for Claude Code)
proto/ — Protobuf definitions (shared schema)
plugins/ — Editor / AI integrations
claude-code/ — Claude Code plugin (agents, commands, skills, hooks)
opencode/ — OpenCode plugin (native TS, Bun runtime)
docs/ — Documentation site (mkdocs-material)
tests/ — Cross-validation test fixtures
benchmark/ — Accuracy benchmarks
See Development Setup for prerequisites, commands, and the full dev workflow.
See CONTRIBUTING.md for guidelines on how to contribute.
Apache License 2.0 — see LICENSE for details.