docs: open source prep — README, CODE_OF_CONDUCT, issue templates
- README rewritten to lead with knowledge layer, add binary install
section, full graph schema, and contributing link
- CODE_OF_CONDUCT.md added
- Bug report and feature request issue templates added
+We are committed to making participation in this project a harassment-free experience for everyone, regardless of age, background, disability, ethnicity, gender identity, level of experience, nationality, personal appearance, race, religion, or sexual identity.
6
+
7
+## Our standards
8
+
9
+**Expected behaviour:**
10
+- Be respectful and constructive in discussions
11
+- Accept feedback gracefully and give it generously
12
+- Focus on what is best for the project and its users
13
+- Show empathy toward other contributors
14
+
15
+**Unacceptable behaviour:**
16
+- Harassment, insults, or personal attacks
17
+- Trolling or deliberately disruptive behaviour
18
+- Publishing others' private information without permission
19
+- Any conduct that would be inappropriate in a professional setting
20
+
21
+## Enforcement
22
+
23
+Instances of unacceptable behaviour may be reported to **[email protected]**. All reports will be reviewed and investigated promptly and fairly. Project maintainers have the right to remove, edit, or reject contributions that do not align with this Code of Conduct.
24
+
25
+## Attribution
26
+
27
+Adapted from the [Contributor Covenant](https://www.contributor-covenant.org), version 2.1.
--- a/CODE_OF_CONDUCT.md
+++ b/CODE_OF_CONDUCT.md
@@ -0,0 +1,27 @@
--- a/CODE_OF_CONDUCT.md
+++ b/CODE_OF_CONDUCT.md
@@ -0,0 +1,27 @@
1
# Code of Conduct
2
3
## Our pledge
4
5
We are committed to making participation in this project a harassment-free experience for everyone, regardless of age, background, disability, ethnicity, gender identity, level of experience, nationality, personal appearance, race, religion, or sexual identity.
6
7
## Our standards
8
9
**Expected behaviour:**
10
- Be respectful and constructive in discussions
11
- Accept feedback gracefully and give it generously
12
- Focus on what is best for the project and its users
13
- Show empathy toward other contributors
14
15
**Unacceptable behaviour:**
16
- Harassment, insults, or personal attacks
17
- Trolling or deliberately disruptive behaviour
18
- Publishing others' private information without permission
19
- Any conduct that would be inappropriate in a professional setting
20
21
## Enforcement
22
23
Instances of unacceptable behaviour may be reported to **[email protected]**. All reports will be reviewed and investigated promptly and fairly. Project maintainers have the right to remove, edit, or reject contributions that do not align with this Code of Conduct.
24
25
## Attribution
26
27
Adapted from the [Contributor Covenant](https://www.contributor-covenant.org), version 2.1.
-**AST + knowledge graph context engine for AI coding agents.**
3
+**Your codebase + everything your team knows about it — in one queryable graph.**
4
4
5
-Navegador parses your codebase into a property graph and makes it queryable. AI coding agents can ask "what calls this function?", "what does this file depend on?", or "show me everything related to auth" — and get structured, precise answers instead of raw file dumps.
5
+Navegador parses your source code into a property graph and layers your team's knowledge on top: decisions, concepts, rules, people, wiki pages, and meeting outputs. AI coding agents get structured, precise context instead of raw file dumps.
-AI coding agents load context by reading raw files. They don't know what calls what, what depends on what, or which 5 functions out of 500 are actually relevant. Navegador builds a structured map — then exposes it via MCP so any agent can navigate your code with precision.
33
+The **code layer** is built automatically by ingesting source trees. The **knowledge layer** is populated by your team — manually, via wiki ingestion, or from [PlanOpticon](https://github.com/ConflictHQ/PlanOpticon) meeting analysis output.
19
34
20
35
---
21
36
22
37
## Quick start
23
38
@@ -28,22 +43,25 @@
28
43
navegador ingest ./myrepo
29
44
30
45
# Load context for a file
31
46
navegador context src/auth.py
32
47
33
-# Search for a symbol
34
-navegador search "get_user"
48
+# Search across code + knowledge
49
+navegador search "rate limit" --all
50
+
51
+# Explain a symbol
52
+navegador explain AuthService
35
53
36
54
# Check graph stats
37
55
navegador stats
38
56
```
39
57
40
58
---
41
59
42
60
## MCP integration
43
61
44
-Add to your Claude / Cursor MCP config:
62
+Add to your Claude / Cursor / Gemini MCP config:
45
63
46
64
```json
47
65
{
48
66
"mcpServers": {
49
67
"navegador": {
@@ -65,36 +83,58 @@
65
83
| `search_symbols` | Fuzzy search for functions/classes by name |
66
84
| `query_graph` | Raw Cypher passthrough |
67
85
| `graph_stats` | Node and edge counts |
68
86
69
87
---
88
+
89
+## Knowledge layer
90
+
91
+Beyond code structure, navegador stores what your team knows:
92
+
93
+```bash
94
+# Record an architectural decision
95
+navegador add decision "Use FalkorDB for graph storage" \
+See [CONTRIBUTING.md](.github/CONTRIBUTING.md). Bug reports and feature requests welcome via [GitHub Issues](https://github.com/ConflictHQ/navegador/issues).
185
+
110
186
---
111
187
112
188
## License
113
189
114
190
MIT — [CONFLICT](https://weareconflict.com)
115
191
--- README.md
+++ README.md
@@ -1,23 +1,38 @@
1
# Navegador
2
3
**AST + knowledge graph context engine for AI coding agents.**
4
5
Navegador parses your codebase into a property graph and makes it queryable. AI coding agents can ask "what calls this function?", "what does this file depend on?", or "show me everything related to auth" — and get structured, precise answers instead of raw file dumps.
AI coding agents load context by reading raw files. They don't know what calls what, what depends on what, or which 5 functions out of 500 are actually relevant. Navegador builds a structured map — then exposes it via MCP so any agent can navigate your code with precision.
19
20
---
21
22
## Quick start
23
@@ -28,22 +43,25 @@
28
navegador ingest ./myrepo
29
30
# Load context for a file
31
navegador context src/auth.py
32
33
# Search for a symbol
34
navegador search "get_user"
35
36
# Check graph stats
37
navegador stats
38
```
39
40
---
41
42
## MCP integration
43
44
Add to your Claude / Cursor MCP config:
45
46
```json
47
{
48
"mcpServers": {
49
"navegador": {
@@ -65,36 +83,58 @@
65
| `search_symbols` | Fuzzy search for functions/classes by name |
store = GraphStore.redis("redis://localhost:6379")
96
```
97
98
---
99
100
## Language support
@@ -105,10 +145,46 @@
105
| TypeScript / JavaScript | ✅ |
106
| Go | ✅ |
107
| Rust | ✅ |
108
| Java | ✅ |
109
110
---
111
112
## License
113
114
MIT — [CONFLICT](https://weareconflict.com)
115
--- README.md
+++ README.md
@@ -1,23 +1,38 @@
1
# Navegador
2
3
**Your codebase + everything your team knows about it — in one queryable graph.**
4
5
Navegador parses your source code into a property graph and layers your team's knowledge on top: decisions, concepts, rules, people, wiki pages, and meeting outputs. AI coding agents get structured, precise context instead of raw file dumps.
The **code layer** is built automatically by ingesting source trees. The **knowledge layer** is populated by your team — manually, via wiki ingestion, or from [PlanOpticon](https://github.com/ConflictHQ/PlanOpticon) meeting analysis output.
34
35
---
36
37
## Quick start
38
@@ -28,22 +43,25 @@
43
navegador ingest ./myrepo
44
45
# Load context for a file
46
navegador context src/auth.py
47
48
# Search across code + knowledge
49
navegador search "rate limit" --all
50
51
# Explain a symbol
52
navegador explain AuthService
53
54
# Check graph stats
55
navegador stats
56
```
57
58
---
59
60
## MCP integration
61
62
Add to your Claude / Cursor / Gemini MCP config:
63
64
```json
65
{
66
"mcpServers": {
67
"navegador": {
@@ -65,36 +83,58 @@
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
91
Beyond code structure, navegador stores what your team knows:
92
93
```bash
94
# Record an architectural decision
95
navegador add decision "Use FalkorDB for graph storage" \
See [CONTRIBUTING.md](.github/CONTRIBUTING.md). Bug reports and feature requests welcome via [GitHub Issues](https://github.com/ConflictHQ/navegador/issues).