Navegador v0.7

The project knowledge graph for AI coding agents.

Navegador builds and maintains a queryable graph of your software project — combining static code analysis with human-curated business knowledge — so that AI coding agents always have precise, structured context instead of raw file dumps.

navegador — Spanish for navigator / sailor. It helps agents navigate your code.

Current version: 0.7.0

Two layers, one graph

┌─────────────────────────────────────────────────────────────────┐
│  KNOWLEDGE LAYER                                                │
│  Concepts · Rules · Decisions · WikiPages · People · Domains   │
│                                                                 │
│         ↕  GOVERNS / IMPLEMENTS / DOCUMENTS / ANNOTATES        │
│                                                                 │
│  CODE LAYER                                                     │
│  Repository · File · Module · Class · Function · Method        │
│  Variable · Import · Decorator · (call graphs, hierarchies)    │
└─────────────────────────────────────────────────────────────────┘
              stored in FalkorDB  (SQLite local / Redis prod)

The code layer is populated automatically by ingesting source trees. 13 languages are supported via tree-sitter (Python, TypeScript, JavaScript, Go, Rust, Java, Kotlin, C#, PHP, Ruby, Swift, C, C++). The knowledge layer is populated by manual curation (navegador add), GitHub wiki ingestion, and Planopticon output (meeting and video knowledge graphs).

Quick start

pip install navegador              # Python 3.12+ required
navegador ingest ./my-repo         # parse + index the codebase
navegador explain AuthService      # what is this thing?
navegador search "rate limit" --all  # search code + knowledge together

Or use the Python SDK:

from navegador import Navegador

nav = Navegador(".navegador/navegador.db")
nav.ingest("./my-repo")
bundle = nav.explain("AuthService")
print(bundle.to_markdown())

What goes in the graph

Agent integration

=== "CLI"

The simplest integration: call `navegador explain` or `navegador context` from any shell script or agent tool definition.

```bash
# get context for the file the agent just edited
navegador context src/auth/service.py --format json

# look up a function before editing it
navegador function validate_token --depth 2 --format json

# find everything annotated with a business concept
navegador concept PaymentProcessing --format json
```

=== "MCP"

Run navegador as a Model Context Protocol server. Configure it once in your agent settings and all navegador commands become callable tools with structured input/output.

```json
{
  "mcpServers": {
    "navegador": {
      "command": "navegador",
      "args": ["mcp"]
    }
  }
}
```

11 tools available. See [MCP Integration](guide/mcp-integration.md) for the full tool list and per-agent config snippets. Use `--read-only` mode to restrict agents to query-only access.

=== "Bootstrap"

One command to install navegador, ingest a repo, and wire the agent hook for your preferred AI coding assistant.

```bash
./bootstrap.sh --repo owner/repo --wiki --agent claude
```

Supports `--agent claude`, `--agent gemini`, and `--agent openai`. See [Agent Hooks](guide/agent-hooks.md) for what the hook does and how to configure it manually.

=== "Editor integration"

Wire navegador into your editor with one command:

```bash
navegador editor setup claude-code
navegador editor setup cursor
navegador editor setup codex
navegador editor setup windsurf
```

=== "CI/CD"

Run navegador in CI pipelines for automated context checks:

```bash
navegador ci ingest
navegador ci stats
navegador ci check
```

What's new in 0.7.0

License

Navegador is open source under the MIT License. Copyright 2026 CONFLICT LLC.