Navegador

docs: update README, CHANGELOG, CLAUDE.md, and version for 0.7.0 Bumps version to 0.7.0. Updates README with new language table (13 langs), 11 MCP tools, framework enrichment, structural analysis, intelligence layer, Python SDK, cluster mode, and additional integrations. Full CHANGELOG covering all 63 issues across v0.2-v0.7. Updated CLAUDE.md package layout.

lmata 2026-03-23 13:33 trunk
Commit 4966011eed927bad0fc913ffa8ef01eeab5e28623474689b8d1527212bfa0de5
Parent c054b6b37525dad…
5 files changed +79 +26 -8 +93 -1 +1 -1 +19 -2
~ CHANGELOG.md ~ CLAUDE.md ~ README.md ~ navegador/__init__.py ~ pyproject.toml
M CHANGELOG.md
+79
--- CHANGELOG.md
+++ CHANGELOG.md
@@ -1,6 +1,85 @@
11
 # Changelog
2
+
3
+## 0.7.0 — 2026-03-23
4
+
5
+### v0.2 — Foundation
6
+
7
+- **Knowledge MCP tools** — `get_rationale`, `find_owners`, `search_knowledge`
8
+- **Incremental ingestion** — content-hash-based change detection, `--incremental` flag, `--watch` mode
9
+- **Schema versioning and migrations** — `:Meta` node versioning, `navegador migrate` CLI
10
+- **Enhanced init** — `config.toml` with storage, LLM, and cluster settings
11
+- **Text-based graph export** — deterministic JSONL format for git-friendly diffs
12
+- **Editor integrations** — MCP config generation for Claude Code, Cursor, Codex, Windsurf
13
+- **CI/CD mode** — `navegador ci ingest/stats/check` with JSON output, exit codes, GitHub Actions annotations
14
+- **Python SDK** — `Navegador` class wrapping all internal modules
15
+- **Sensitive content detection** — API key, password, token redaction before graph storage
16
+- **VCS abstraction** — `GitAdapter` and `FossilAdapter` with auto-detection
17
+- **MCP security hardening** — query validation, complexity limits, `--read-only` mode
18
+- **Shell completions** — bash, zsh, fish tab completion
19
+- **LLM backend abstraction** — unified provider interface for Anthropic, OpenAI, Ollama
20
+- **AST optimizations** — LRU tree cache, incremental re-parsing, graph node diffing, parallel ingestion
21
+
22
+### v0.3 — Framework Intelligence
23
+
24
+- **Language expansion** — Kotlin, C#, PHP, Ruby, Swift, C, C++
25
+- **FrameworkEnricher base class** — auto-discovery, node promotion, semantic edges
26
+- **Framework enrichers** — Django, FastAPI, React/Next.js, Express.js, React Native, Rails, Spring Boot, Laravel
27
+- **Monorepo support** — Turborepo, Nx, Yarn, pnpm, Cargo, Go workspace detection
28
+- **Git diff integration** — map uncommitted changes to affected symbols and knowledge
29
+- **Code churn correlation** — git history analysis for behavioural coupling
30
+
31
+### v0.4 — Structural + Knowledge
32
+
33
+- **Impact analysis** — blast-radius traversal with MCP tool and CLI
34
+- **Execution flow tracing** — call chain precomputation from entry points
35
+- **Dead code detection** — unreachable functions, classes, and files
36
+- **Test coverage mapping** — link test functions to production code via TESTS edges
37
+- **Circular dependency detection** — DFS-based cycle detection in import and call graphs
38
+- **Multi-repo support** — register, ingest, and search across repositories
39
+- **Coordinated rename** — graph-assisted multi-file symbol refactoring with preview
40
+- **CODEOWNERS integration** — parse ownership files to Person and Domain nodes
41
+- **ADR ingestion** — MADR-format Architecture Decision Records
42
+- **OpenAPI / GraphQL ingestion** — API contract schemas as graph nodes
43
+- **PlanOpticon pipeline** — end-to-end meeting-to-knowledge with auto-linking
44
+- **PM tool integration** — GitHub issues ingestion (Linear/Jira stubs)
45
+- **External dependency nodes** — npm/pip/cargo package tracking
46
+- **Fossil SCM support** — full VCS implementation
47
+- **Submodule traversal** — parent + submodule linked ingestion
48
+- **Multi-repo workspace** — unified and federated knowledge graph modes
49
+
50
+### v0.5 — Intelligence Layer
51
+
52
+- **Semantic search** — embedding-based similarity search with LLM providers
53
+- **Community detection** — label propagation over heterogeneous graph
54
+- **LLM integration** — natural language queries, community naming, documentation generation
55
+- **Documentation generation** — template and LLM-powered docs from graph context
56
+
57
+### v0.6 — Cluster + Swarm
58
+
59
+- **Cluster core** — Redis↔SQLite snapshot sync for agent swarms
60
+- **Pub/sub notifications** — real-time graph change events
61
+- **Task queue** — FIFO work assignment for agent swarms
62
+- **Work partitioning** — community-based splitting across agents
63
+- **Session namespacing** — branch-isolated graph namespaces
64
+- **Distributed locking** — Redis SETNX-based mutual exclusion
65
+- **Checkpoint/rollback** — JSONL-based state snapshots
66
+- **Agent messaging** — async agent-to-agent communication
67
+- **Swarm observability** — dashboard metrics
68
+- **Fossil live integration** — ATTACH DATABASE for zero-copy queries
69
+
70
+### v0.7 — Human Interface
71
+
72
+- **Graph explorer** — HTTP server with browser-based force-directed visualization
73
+- **Test coverage** — 96% coverage across 1902 tests
74
+
75
+### Quality
76
+
77
+- 96% test coverage (1902 tests)
78
+- CI matrix: Ubuntu + macOS, Python 3.12 / 3.13 / 3.14
79
+
80
+---
281
382
 ## 0.1.0 — 2026-03-22
483
584
 First public release.
685
786
--- CHANGELOG.md
+++ CHANGELOG.md
@@ -1,6 +1,85 @@
1 # Changelog
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
3 ## 0.1.0 — 2026-03-22
4
5 First public release.
6
7
--- CHANGELOG.md
+++ CHANGELOG.md
@@ -1,6 +1,85 @@
1 # Changelog
2
3 ## 0.7.0 — 2026-03-23
4
5 ### v0.2 — Foundation
6
7 - **Knowledge MCP tools** — `get_rationale`, `find_owners`, `search_knowledge`
8 - **Incremental ingestion** — content-hash-based change detection, `--incremental` flag, `--watch` mode
9 - **Schema versioning and migrations** — `:Meta` node versioning, `navegador migrate` CLI
10 - **Enhanced init** — `config.toml` with storage, LLM, and cluster settings
11 - **Text-based graph export** — deterministic JSONL format for git-friendly diffs
12 - **Editor integrations** — MCP config generation for Claude Code, Cursor, Codex, Windsurf
13 - **CI/CD mode** — `navegador ci ingest/stats/check` with JSON output, exit codes, GitHub Actions annotations
14 - **Python SDK** — `Navegador` class wrapping all internal modules
15 - **Sensitive content detection** — API key, password, token redaction before graph storage
16 - **VCS abstraction** — `GitAdapter` and `FossilAdapter` with auto-detection
17 - **MCP security hardening** — query validation, complexity limits, `--read-only` mode
18 - **Shell completions** — bash, zsh, fish tab completion
19 - **LLM backend abstraction** — unified provider interface for Anthropic, OpenAI, Ollama
20 - **AST optimizations** — LRU tree cache, incremental re-parsing, graph node diffing, parallel ingestion
21
22 ### v0.3 — Framework Intelligence
23
24 - **Language expansion** — Kotlin, C#, PHP, Ruby, Swift, C, C++
25 - **FrameworkEnricher base class** — auto-discovery, node promotion, semantic edges
26 - **Framework enrichers** — Django, FastAPI, React/Next.js, Express.js, React Native, Rails, Spring Boot, Laravel
27 - **Monorepo support** — Turborepo, Nx, Yarn, pnpm, Cargo, Go workspace detection
28 - **Git diff integration** — map uncommitted changes to affected symbols and knowledge
29 - **Code churn correlation** — git history analysis for behavioural coupling
30
31 ### v0.4 — Structural + Knowledge
32
33 - **Impact analysis** — blast-radius traversal with MCP tool and CLI
34 - **Execution flow tracing** — call chain precomputation from entry points
35 - **Dead code detection** — unreachable functions, classes, and files
36 - **Test coverage mapping** — link test functions to production code via TESTS edges
37 - **Circular dependency detection** — DFS-based cycle detection in import and call graphs
38 - **Multi-repo support** — register, ingest, and search across repositories
39 - **Coordinated rename** — graph-assisted multi-file symbol refactoring with preview
40 - **CODEOWNERS integration** — parse ownership files to Person and Domain nodes
41 - **ADR ingestion** — MADR-format Architecture Decision Records
42 - **OpenAPI / GraphQL ingestion** — API contract schemas as graph nodes
43 - **PlanOpticon pipeline** — end-to-end meeting-to-knowledge with auto-linking
44 - **PM tool integration** — GitHub issues ingestion (Linear/Jira stubs)
45 - **External dependency nodes** — npm/pip/cargo package tracking
46 - **Fossil SCM support** — full VCS implementation
47 - **Submodule traversal** — parent + submodule linked ingestion
48 - **Multi-repo workspace** — unified and federated knowledge graph modes
49
50 ### v0.5 — Intelligence Layer
51
52 - **Semantic search** — embedding-based similarity search with LLM providers
53 - **Community detection** — label propagation over heterogeneous graph
54 - **LLM integration** — natural language queries, community naming, documentation generation
55 - **Documentation generation** — template and LLM-powered docs from graph context
56
57 ### v0.6 — Cluster + Swarm
58
59 - **Cluster core** — Redis↔SQLite snapshot sync for agent swarms
60 - **Pub/sub notifications** — real-time graph change events
61 - **Task queue** — FIFO work assignment for agent swarms
62 - **Work partitioning** — community-based splitting across agents
63 - **Session namespacing** — branch-isolated graph namespaces
64 - **Distributed locking** — Redis SETNX-based mutual exclusion
65 - **Checkpoint/rollback** — JSONL-based state snapshots
66 - **Agent messaging** — async agent-to-agent communication
67 - **Swarm observability** — dashboard metrics
68 - **Fossil live integration** — ATTACH DATABASE for zero-copy queries
69
70 ### v0.7 — Human Interface
71
72 - **Graph explorer** — HTTP server with browser-based force-directed visualization
73 - **Test coverage** — 96% coverage across 1902 tests
74
75 ### Quality
76
77 - 96% test coverage (1902 tests)
78 - CI matrix: Ubuntu + macOS, Python 3.12 / 3.13 / 3.14
79
80 ---
81
82 ## 0.1.0 — 2026-03-22
83
84 First public release.
85
86
M CLAUDE.md
+26 -8
--- CLAUDE.md
+++ CLAUDE.md
@@ -4,27 +4,39 @@
44
55
 AST + knowledge graph context engine for AI coding agents. Parses codebases into a FalkorDB property graph. Agents query via MCP or Python API.
66
77
 ## Stack
88
9
-- **Python 3.10+**, standalone (no Django dependency)
10
-- **tree-sitter** for multi-language AST parsing (`tree-sitter-python`, `tree-sitter-typescript`)
9
+- **Python 3.12+**, standalone (no Django dependency)
10
+- **tree-sitter** for multi-language AST parsing (13 languages)
1111
 - **FalkorDB** graph DB with **falkordblite** (SQLite via redislite) for local use
12
-- **MCP** (`mcp` Python SDK) for AI agent integration
12
+- **MCP** (`mcp` Python SDK) for AI agent integration (11 tools)
1313
 - **Click + Rich** for CLI
1414
 - **Pydantic** for data models
1515
 - **Ruff** for linting/formatting
1616
1717
 ## Package layout
1818
1919
 ```
2020
 navegador/
21
- cli/ — Click commands (ingest, context, search, stats, mcp)
22
- graph/ — GraphStore + schema + Cypher query templates
23
- ingestion/ — RepoIngester + language parsers (python.py, typescript.py)
24
- context/ — ContextLoader + ContextBundle (JSON/markdown output)
25
- mcp/ — MCP server with 7 tools
21
+ cli/ — Click commands (50+ subcommands)
22
+ graph/ — GraphStore + schema + queries + migrations + export
23
+ ingestion/ — RepoIngester + 13 language parsers + optimization
24
+ context/ — ContextLoader + ContextBundle (JSON/markdown)
25
+ mcp/ — MCP server with 11 tools + security hardening
26
+ enrichment/ — FrameworkEnricher base + 8 framework enrichers
27
+ analysis/ — impact, flow tracing, dead code, cycles, test mapping
28
+ intelligence/ — semantic search, community detection, NLP, doc generation
29
+ cluster/ — Redis pub/sub, task queue, locking, sessions, messaging
30
+ sdk.py — Python SDK (Navegador class)
31
+ llm.py — LLM provider abstraction (Anthropic, OpenAI, Ollama)
32
+ vcs.py — VCS abstraction (Git, Fossil)
33
+ diff.py — Git diff → graph impact mapping
34
+ churn.py — Behavioural coupling from git history
35
+ monorepo.py — Workspace detection + ingestion
36
+ security.py — Sensitive content detection + redaction
37
+ explorer/ — HTTP server + browser-based graph visualization
2638
 ```
2739
2840
 ## FalkorDB connection
2941
3042
 ```python
@@ -43,10 +55,16 @@
4355
 1. Create `navegador/ingestion/<lang>.py` subclassing `LanguageParser`
4456
 2. Implement `parse_file(path, repo_root, store) -> dict[str, int]`
4557
 3. Add the extension + language key to `LANGUAGE_MAP` in `parser.py`
4658
 4. Register in `RepoIngester._get_parser()`
4759
60
+## Adding a new framework enricher
61
+
62
+1. Create `navegador/enrichment/<framework>.py` subclassing `FrameworkEnricher`
63
+2. Implement `framework_name`, `detection_patterns`, `enrich()`
64
+3. The CLI auto-discovers enrichers via `pkgutil` — no registration needed
65
+
4866
 ## Adding a new MCP tool
4967
5068
 1. Add a `Tool(...)` entry in `list_tools()` in `mcp/server.py`
5169
 2. Add a handler branch in `call_tool()`
5270
5371
--- CLAUDE.md
+++ CLAUDE.md
@@ -4,27 +4,39 @@
4
5 AST + knowledge graph context engine for AI coding agents. Parses codebases into a FalkorDB property graph. Agents query via MCP or Python API.
6
7 ## Stack
8
9 - **Python 3.10+**, standalone (no Django dependency)
10 - **tree-sitter** for multi-language AST parsing (`tree-sitter-python`, `tree-sitter-typescript`)
11 - **FalkorDB** graph DB with **falkordblite** (SQLite via redislite) for local use
12 - **MCP** (`mcp` Python SDK) for AI agent integration
13 - **Click + Rich** for CLI
14 - **Pydantic** for data models
15 - **Ruff** for linting/formatting
16
17 ## Package layout
18
19 ```
20 navegador/
21 cli/ — Click commands (ingest, context, search, stats, mcp)
22 graph/ — GraphStore + schema + Cypher query templates
23 ingestion/ — RepoIngester + language parsers (python.py, typescript.py)
24 context/ — ContextLoader + ContextBundle (JSON/markdown output)
25 mcp/ — MCP server with 7 tools
 
 
 
 
 
 
 
 
 
 
 
 
26 ```
27
28 ## FalkorDB connection
29
30 ```python
@@ -43,10 +55,16 @@
43 1. Create `navegador/ingestion/<lang>.py` subclassing `LanguageParser`
44 2. Implement `parse_file(path, repo_root, store) -> dict[str, int]`
45 3. Add the extension + language key to `LANGUAGE_MAP` in `parser.py`
46 4. Register in `RepoIngester._get_parser()`
47
 
 
 
 
 
 
48 ## Adding a new MCP tool
49
50 1. Add a `Tool(...)` entry in `list_tools()` in `mcp/server.py`
51 2. Add a handler branch in `call_tool()`
52
53
--- CLAUDE.md
+++ CLAUDE.md
@@ -4,27 +4,39 @@
4
5 AST + knowledge graph context engine for AI coding agents. Parses codebases into a FalkorDB property graph. Agents query via MCP or Python API.
6
7 ## Stack
8
9 - **Python 3.12+**, standalone (no Django dependency)
10 - **tree-sitter** for multi-language AST parsing (13 languages)
11 - **FalkorDB** graph DB with **falkordblite** (SQLite via redislite) for local use
12 - **MCP** (`mcp` Python SDK) for AI agent integration (11 tools)
13 - **Click + Rich** for CLI
14 - **Pydantic** for data models
15 - **Ruff** for linting/formatting
16
17 ## Package layout
18
19 ```
20 navegador/
21 cli/ — Click commands (50+ subcommands)
22 graph/ — GraphStore + schema + queries + migrations + export
23 ingestion/ — RepoIngester + 13 language parsers + optimization
24 context/ — ContextLoader + ContextBundle (JSON/markdown)
25 mcp/ — MCP server with 11 tools + security hardening
26 enrichment/ — FrameworkEnricher base + 8 framework enrichers
27 analysis/ — impact, flow tracing, dead code, cycles, test mapping
28 intelligence/ — semantic search, community detection, NLP, doc generation
29 cluster/ — Redis pub/sub, task queue, locking, sessions, messaging
30 sdk.py — Python SDK (Navegador class)
31 llm.py — LLM provider abstraction (Anthropic, OpenAI, Ollama)
32 vcs.py — VCS abstraction (Git, Fossil)
33 diff.py — Git diff → graph impact mapping
34 churn.py — Behavioural coupling from git history
35 monorepo.py — Workspace detection + ingestion
36 security.py — Sensitive content detection + redaction
37 explorer/ — HTTP server + browser-based graph visualization
38 ```
39
40 ## FalkorDB connection
41
42 ```python
@@ -43,10 +55,16 @@
55 1. Create `navegador/ingestion/<lang>.py` subclassing `LanguageParser`
56 2. Implement `parse_file(path, repo_root, store) -> dict[str, int]`
57 3. Add the extension + language key to `LANGUAGE_MAP` in `parser.py`
58 4. Register in `RepoIngester._get_parser()`
59
60 ## Adding a new framework enricher
61
62 1. Create `navegador/enrichment/<framework>.py` subclassing `FrameworkEnricher`
63 2. Implement `framework_name`, `detection_patterns`, `enrich()`
64 3. The CLI auto-discovers enrichers via `pkgutil` — no registration needed
65
66 ## Adding a new MCP tool
67
68 1. Add a `Tool(...)` entry in `list_tools()` in `mcp/server.py`
69 2. Add a handler branch in `call_tool()`
70
71
M README.md
+93 -1
--- README.md
+++ README.md
@@ -79,12 +79,16 @@
7979
 | `ingest_repo` | Parse and load a repo into the graph |
8080
 | `load_file_context` | All symbols in a file + their relationships |
8181
 | `load_function_context` | What a function calls and what calls it |
8282
 | `load_class_context` | Class methods, inheritance, subclasses |
8383
 | `search_symbols` | Fuzzy search for functions/classes by name |
84
-| `query_graph` | Raw Cypher passthrough |
84
+| `query_graph` | Raw Cypher passthrough (with security hardening) |
8585
 | `graph_stats` | Node and edge counts |
86
+| `get_rationale` | Decision rationale, alternatives, and status |
87
+| `find_owners` | People assigned to any node |
88
+| `search_knowledge` | Search concepts, rules, decisions, wiki |
89
+| `blast_radius` | Impact analysis — what's affected by a change |
8690
8791
 ---
8892
8993
 ## Knowledge layer
9094
@@ -144,10 +148,98 @@
144148
 | Python | ✅ |
145149
 | TypeScript / JavaScript | ✅ |
146150
 | Go | ✅ |
147151
 | Rust | ✅ |
148152
 | Java | ✅ |
153
+| Kotlin | ✅ |
154
+| C# | ✅ |
155
+| PHP | ✅ |
156
+| Ruby | ✅ |
157
+| Swift | ✅ |
158
+| C / C++ | ✅ |
159
+
160
+---
161
+
162
+## Framework enrichment
163
+
164
+After ingesting code, navegador can promote generic AST nodes to framework-specific semantic types:
165
+
166
+```bash
167
+navegador enrich # auto-detect frameworks
168
+navegador enrich --framework django # target a specific framework
169
+```
170
+
171
+Supported frameworks: **Django**, **FastAPI**, **React / Next.js**, **Express.js**, **React Native**, **Rails**, **Spring Boot**, **Laravel**
172
+
173
+---
174
+
175
+## Structural analysis
176
+
177
+```bash
178
+navegador impact AuthService --depth 3 # blast radius
179
+navegador trace handle_request # execution flow from entry point
180
+navegador deadcode # unreachable functions/classes
181
+navegador cycles # circular dependencies
182
+navegador testmap # link tests to production code
183
+navegador diff # map uncommitted changes to graph
184
+navegador churn . # behavioural coupling from git history
185
+```
186
+
187
+---
188
+
189
+## Intelligence layer
190
+
191
+```bash
192
+navegador semantic-search "authentication flow" # embedding-based search
193
+navegador communities # detect code communities
194
+navegador ask "what calls the payment service?" # natural language queries
195
+navegador docs src/auth.py # generate documentation
196
+```
197
+
198
+Requires an LLM provider: `pip install navegador[llm]`
199
+
200
+---
201
+
202
+## Python SDK
203
+
204
+```python
205
+from navegador import Navegador
206
+
207
+nav = Navegador.sqlite(".navegador/graph.db")
208
+nav.ingest("./myrepo")
209
+nav.add_concept("Payment", description="Payment processing", domain="billing")
210
+
211
+results = nav.search("auth")
212
+bundle = nav.explain("AuthService")
213
+owners = nav.find_owners("AuthService")
214
+```
215
+
216
+---
217
+
218
+## Cluster mode (agent swarms)
219
+
220
+For multi-agent setups sharing a Redis-backed graph:
221
+
222
+```bash
223
+navegador init --redis redis://host:6379 --cluster
224
+```
225
+
226
+Features: shared graph with local snapshots, pub/sub notifications, task queues, distributed locking, session namespacing, checkpoints, agent messaging, observability dashboard.
227
+
228
+---
229
+
230
+## Additional integrations
231
+
232
+```bash
233
+navegador codeowners ./myrepo # parse CODEOWNERS → ownership graph
234
+navegador adr ingest docs/decisions/ # Architecture Decision Records
235
+navegador api ingest openapi.yaml # OpenAPI / GraphQL schemas
236
+navegador deps ingest package.json # external dependency tracking
237
+navegador pm ingest --github org/repo # GitHub issues → knowledge graph
238
+navegador editor setup claude-code # generate MCP config for editors
239
+navegador explore # browser-based graph visualization
240
+```
149241
150242
 ---
151243
152244
 ## Installation
153245
154246
--- README.md
+++ README.md
@@ -79,12 +79,16 @@
79 | `ingest_repo` | Parse and load a repo into the graph |
80 | `load_file_context` | All symbols in a file + their relationships |
81 | `load_function_context` | What a function calls and what calls it |
82 | `load_class_context` | Class methods, inheritance, subclasses |
83 | `search_symbols` | Fuzzy search for functions/classes by name |
84 | `query_graph` | Raw Cypher passthrough |
85 | `graph_stats` | Node and edge counts |
 
 
 
 
86
87 ---
88
89 ## Knowledge layer
90
@@ -144,10 +148,98 @@
144 | Python | ✅ |
145 | TypeScript / JavaScript | ✅ |
146 | Go | ✅ |
147 | Rust | ✅ |
148 | Java | ✅ |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
149
150 ---
151
152 ## Installation
153
154
--- README.md
+++ README.md
@@ -79,12 +79,16 @@
79 | `ingest_repo` | Parse and load a repo into the graph |
80 | `load_file_context` | All symbols in a file + their relationships |
81 | `load_function_context` | What a function calls and what calls it |
82 | `load_class_context` | Class methods, inheritance, subclasses |
83 | `search_symbols` | Fuzzy search for functions/classes by name |
84 | `query_graph` | Raw Cypher passthrough (with security hardening) |
85 | `graph_stats` | Node and edge counts |
86 | `get_rationale` | Decision rationale, alternatives, and status |
87 | `find_owners` | People assigned to any node |
88 | `search_knowledge` | Search concepts, rules, decisions, wiki |
89 | `blast_radius` | Impact analysis — what's affected by a change |
90
91 ---
92
93 ## Knowledge layer
94
@@ -144,10 +148,98 @@
148 | Python | ✅ |
149 | TypeScript / JavaScript | ✅ |
150 | Go | ✅ |
151 | Rust | ✅ |
152 | Java | ✅ |
153 | Kotlin | ✅ |
154 | C# | ✅ |
155 | PHP | ✅ |
156 | Ruby | ✅ |
157 | Swift | ✅ |
158 | C / C++ | ✅ |
159
160 ---
161
162 ## Framework enrichment
163
164 After ingesting code, navegador can promote generic AST nodes to framework-specific semantic types:
165
166 ```bash
167 navegador enrich # auto-detect frameworks
168 navegador enrich --framework django # target a specific framework
169 ```
170
171 Supported frameworks: **Django**, **FastAPI**, **React / Next.js**, **Express.js**, **React Native**, **Rails**, **Spring Boot**, **Laravel**
172
173 ---
174
175 ## Structural analysis
176
177 ```bash
178 navegador impact AuthService --depth 3 # blast radius
179 navegador trace handle_request # execution flow from entry point
180 navegador deadcode # unreachable functions/classes
181 navegador cycles # circular dependencies
182 navegador testmap # link tests to production code
183 navegador diff # map uncommitted changes to graph
184 navegador churn . # behavioural coupling from git history
185 ```
186
187 ---
188
189 ## Intelligence layer
190
191 ```bash
192 navegador semantic-search "authentication flow" # embedding-based search
193 navegador communities # detect code communities
194 navegador ask "what calls the payment service?" # natural language queries
195 navegador docs src/auth.py # generate documentation
196 ```
197
198 Requires an LLM provider: `pip install navegador[llm]`
199
200 ---
201
202 ## Python SDK
203
204 ```python
205 from navegador import Navegador
206
207 nav = Navegador.sqlite(".navegador/graph.db")
208 nav.ingest("./myrepo")
209 nav.add_concept("Payment", description="Payment processing", domain="billing")
210
211 results = nav.search("auth")
212 bundle = nav.explain("AuthService")
213 owners = nav.find_owners("AuthService")
214 ```
215
216 ---
217
218 ## Cluster mode (agent swarms)
219
220 For multi-agent setups sharing a Redis-backed graph:
221
222 ```bash
223 navegador init --redis redis://host:6379 --cluster
224 ```
225
226 Features: shared graph with local snapshots, pub/sub notifications, task queues, distributed locking, session namespacing, checkpoints, agent messaging, observability dashboard.
227
228 ---
229
230 ## Additional integrations
231
232 ```bash
233 navegador codeowners ./myrepo # parse CODEOWNERS → ownership graph
234 navegador adr ingest docs/decisions/ # Architecture Decision Records
235 navegador api ingest openapi.yaml # OpenAPI / GraphQL schemas
236 navegador deps ingest package.json # external dependency tracking
237 navegador pm ingest --github org/repo # GitHub issues → knowledge graph
238 navegador editor setup claude-code # generate MCP config for editors
239 navegador explore # browser-based graph visualization
240 ```
241
242 ---
243
244 ## Installation
245
246
M navegador/__init__.py
+1 -1
--- navegador/__init__.py
+++ navegador/__init__.py
@@ -1,10 +1,10 @@
11
 """
22
 Navegador — AST + knowledge graph context engine for AI coding agents.
33
 """
44
5
-__version__ = "0.1.0"
5
+__version__ = "0.7.0"
66
 __author__ = "CONFLICT LLC"
77
88
 from navegador.sdk import Navegador
99
1010
 __all__ = ["Navegador"]
1111
--- navegador/__init__.py
+++ navegador/__init__.py
@@ -1,10 +1,10 @@
1 """
2 Navegador — AST + knowledge graph context engine for AI coding agents.
3 """
4
5 __version__ = "0.1.0"
6 __author__ = "CONFLICT LLC"
7
8 from navegador.sdk import Navegador
9
10 __all__ = ["Navegador"]
11
--- navegador/__init__.py
+++ navegador/__init__.py
@@ -1,10 +1,10 @@
1 """
2 Navegador — AST + knowledge graph context engine for AI coding agents.
3 """
4
5 __version__ = "0.7.0"
6 __author__ = "CONFLICT LLC"
7
8 from navegador.sdk import Navegador
9
10 __all__ = ["Navegador"]
11
M pyproject.toml
+19 -2
--- pyproject.toml
+++ pyproject.toml
@@ -2,19 +2,19 @@
22
 requires = ["setuptools>=69.0", "wheel"]
33
 build-backend = "setuptools.build_meta"
44
55
 [project]
66
 name = "navegador"
7
-version = "0.1.0"
7
+version = "0.7.0"
88
 description = "AST + knowledge graph context engine for AI coding agents"
99
 readme = "README.md"
1010
 license = "MIT"
1111
 requires-python = ">=3.12"
1212
 authors = [
1313
 { name = "CONFLICT LLC" },
1414
 ]
15
-keywords = ["ast", "knowledge-graph", "code-analysis", "ai-agents", "mcp", "context-management", "falkordb", "go", "rust", "java", "typescript"]
15
+keywords = ["ast", "knowledge-graph", "code-analysis", "ai-agents", "mcp", "context-management", "falkordb", "go", "rust", "java", "typescript", "kotlin", "csharp", "php", "ruby", "swift", "c", "cpp"]
1616
 classifiers = [
1717
 "Development Status :: 3 - Alpha",
1818
 "Intended Audience :: Developers",
1919
 "Operating System :: OS Independent",
2020
 "Programming Language :: Python :: 3",
@@ -50,10 +50,25 @@
5050
 [project.optional-dependencies]
5151
 redis = [
5252
 # Use Redis-backed FalkorDB in production
5353
 "redis>=5.0.0",
5454
 ]
55
+languages = [
56
+ # Additional tree-sitter grammars (core 6 are in dependencies)
57
+ "tree-sitter-kotlin>=0.23.0",
58
+ "tree-sitter-c-sharp>=0.23.0",
59
+ "tree-sitter-php>=0.23.0",
60
+ "tree-sitter-ruby>=0.23.0",
61
+ "tree-sitter-swift>=0.23.0",
62
+ "tree-sitter-c>=0.23.0",
63
+ "tree-sitter-cpp>=0.23.0",
64
+]
65
+llm = [
66
+ # LLM provider SDKs (install the ones you use)
67
+ "anthropic>=0.39.0",
68
+ "openai>=1.0.0",
69
+]
5570
 dev = [
5671
 "pytest>=7.3.0",
5772
 "pytest-cov>=4.1.0",
5873
 "pytest-asyncio>=0.23.0",
5974
 "ruff>=0.1.0",
@@ -64,10 +79,12 @@
6479
 "mkdocstrings[python]>=0.24.0",
6580
 "pymdown-extensions>=10.0",
6681
 ]
6782
 all = [
6883
 "navegador[redis]",
84
+ "navegador[languages]",
85
+ "navegador[llm]",
6986
 "navegador[dev]",
7087
 "navegador[docs]",
7188
 ]
7289
7390
 [project.urls]
7491
--- pyproject.toml
+++ pyproject.toml
@@ -2,19 +2,19 @@
2 requires = ["setuptools>=69.0", "wheel"]
3 build-backend = "setuptools.build_meta"
4
5 [project]
6 name = "navegador"
7 version = "0.1.0"
8 description = "AST + knowledge graph context engine for AI coding agents"
9 readme = "README.md"
10 license = "MIT"
11 requires-python = ">=3.12"
12 authors = [
13 { name = "CONFLICT LLC" },
14 ]
15 keywords = ["ast", "knowledge-graph", "code-analysis", "ai-agents", "mcp", "context-management", "falkordb", "go", "rust", "java", "typescript"]
16 classifiers = [
17 "Development Status :: 3 - Alpha",
18 "Intended Audience :: Developers",
19 "Operating System :: OS Independent",
20 "Programming Language :: Python :: 3",
@@ -50,10 +50,25 @@
50 [project.optional-dependencies]
51 redis = [
52 # Use Redis-backed FalkorDB in production
53 "redis>=5.0.0",
54 ]
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
55 dev = [
56 "pytest>=7.3.0",
57 "pytest-cov>=4.1.0",
58 "pytest-asyncio>=0.23.0",
59 "ruff>=0.1.0",
@@ -64,10 +79,12 @@
64 "mkdocstrings[python]>=0.24.0",
65 "pymdown-extensions>=10.0",
66 ]
67 all = [
68 "navegador[redis]",
 
 
69 "navegador[dev]",
70 "navegador[docs]",
71 ]
72
73 [project.urls]
74
--- pyproject.toml
+++ pyproject.toml
@@ -2,19 +2,19 @@
2 requires = ["setuptools>=69.0", "wheel"]
3 build-backend = "setuptools.build_meta"
4
5 [project]
6 name = "navegador"
7 version = "0.7.0"
8 description = "AST + knowledge graph context engine for AI coding agents"
9 readme = "README.md"
10 license = "MIT"
11 requires-python = ">=3.12"
12 authors = [
13 { name = "CONFLICT LLC" },
14 ]
15 keywords = ["ast", "knowledge-graph", "code-analysis", "ai-agents", "mcp", "context-management", "falkordb", "go", "rust", "java", "typescript", "kotlin", "csharp", "php", "ruby", "swift", "c", "cpp"]
16 classifiers = [
17 "Development Status :: 3 - Alpha",
18 "Intended Audience :: Developers",
19 "Operating System :: OS Independent",
20 "Programming Language :: Python :: 3",
@@ -50,10 +50,25 @@
50 [project.optional-dependencies]
51 redis = [
52 # Use Redis-backed FalkorDB in production
53 "redis>=5.0.0",
54 ]
55 languages = [
56 # Additional tree-sitter grammars (core 6 are in dependencies)
57 "tree-sitter-kotlin>=0.23.0",
58 "tree-sitter-c-sharp>=0.23.0",
59 "tree-sitter-php>=0.23.0",
60 "tree-sitter-ruby>=0.23.0",
61 "tree-sitter-swift>=0.23.0",
62 "tree-sitter-c>=0.23.0",
63 "tree-sitter-cpp>=0.23.0",
64 ]
65 llm = [
66 # LLM provider SDKs (install the ones you use)
67 "anthropic>=0.39.0",
68 "openai>=1.0.0",
69 ]
70 dev = [
71 "pytest>=7.3.0",
72 "pytest-cov>=4.1.0",
73 "pytest-asyncio>=0.23.0",
74 "ruff>=0.1.0",
@@ -64,10 +79,12 @@
79 "mkdocstrings[python]>=0.24.0",
80 "pymdown-extensions>=10.0",
81 ]
82 all = [
83 "navegador[redis]",
84 "navegador[languages]",
85 "navegador[llm]",
86 "navegador[dev]",
87 "navegador[docs]",
88 ]
89
90 [project.urls]
91

Keyboard Shortcuts

Open search /
Next entry (timeline) j
Previous entry (timeline) k
Open focused entry Enter
Show this help ?
Toggle theme Top nav button