@codified/cli 0.3.6 → 0.3.7

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (3) hide show
  1. package/README.md +115 -0
  2. package/dist/index.js +388 -341
  3. package/package.json +4 -2
package/README.md ADDED
@@ -0,0 +1,115 @@
1
+ # Codify
2
+
3
+ **Living context graph for AI-native teams.**
4
+
5
+ Codify mines your project history into a structured graph that captures decisions, features, customer signals, code artifacts, and their relationships. It then gives Claude Code ambient access to that context via MCP, so your AI assistant understands not just what your code does but *why* it was built that way.
6
+
7
+ A built-in Gap Engine proactively detects missing context, stale assumptions, and untested decisions. Gaps get addressed automatically through graph mining and evidence collection.
8
+
9
+ ## Prerequisites
10
+
11
+ - Node.js 22+
12
+ - Docker (for PostgreSQL, NATS, Redis)
13
+ - `ANTHROPIC_API_KEY` environment variable (for bootstrap, explain, and collect commands)
14
+
15
+ ## Install
16
+
17
+ ```bash
18
+ npm install -g @codified/cli
19
+ ```
20
+
21
+ ## Quickstart
22
+
23
+ ```bash
24
+ cd your-project
25
+ codify up
26
+ ```
27
+
28
+ `codify up` runs three steps in sequence:
29
+
30
+ 1. **init** -- Starts Docker services (PostgreSQL + AGE + pgvector, NATS, Redis), runs database migrations, and installs the MCP server config into Claude Code.
31
+ 2. **bootstrap** -- Mines your git history with Claude, extracting decisions, features, and relationships into the context graph.
32
+ 3. **start** -- Launches the MCP server on stdio. Claude Code connects automatically.
33
+
34
+ After this, open Claude Code in your project. It now has full context about your codebase.
35
+
36
+ ## Commands
37
+
38
+ ### Getting Started
39
+
40
+ | Command | Description |
41
+ |---------|-------------|
42
+ | `codify up` | One-command setup and start (init + bootstrap + start) |
43
+ | `codify init` | Set up infrastructure and configure project |
44
+ | `codify bootstrap` | Mine git history into the context graph |
45
+ | `codify start` | Start the MCP server for Claude Code |
46
+
47
+ ### Working with Context
48
+
49
+ | Command | Description |
50
+ |---------|-------------|
51
+ | `codify explain <question>` | Ask Claude a question about your project |
52
+ | `codify search <query>` | Search the context graph by keyword |
53
+ | `codify add` | Record a decision, signal, or other context |
54
+ | `codify graph` | Visualize the context graph (Mermaid diagram) |
55
+ | `codify status` | Show project health dashboard |
56
+
57
+ ### Gaps and Quality
58
+
59
+ | Command | Description |
60
+ |---------|-------------|
61
+ | `codify gaps` | Show gaps detected by the Gap Engine |
62
+ | `codify triage` | Interactively resolve gaps |
63
+ | `codify collect` | Mine the graph for evidence to fill gaps |
64
+ | `codify check <file>` | Check files for related context (CI-ready) |
65
+
66
+ ### Projects and Maintenance
67
+
68
+ | Command | Description |
69
+ |---------|-------------|
70
+ | `codify project create/list/switch` | Manage multiple projects |
71
+ | `codify timeline` | Show what changed in the graph over time |
72
+ | `codify export` | Backup the graph to JSON |
73
+ | `codify import` | Restore the graph from a JSON backup |
74
+ | `codify watch` | Start continuous ingest polling |
75
+ | `codify connect` | Connect external data sources |
76
+ | `codify reset` | Reset the context graph (drop all data) |
77
+
78
+ Run `codify <command> --help` for detailed options on any command.
79
+
80
+ ## MCP Integration
81
+
82
+ Codify auto-installs its MCP server config during `codify init`. Claude Code connects automatically -- no manual configuration required.
83
+
84
+ The MCP server exposes tools that Claude can call directly:
85
+
86
+ - **codify_get_context** -- Retrieve context nodes by type or ID
87
+ - **codify_search** -- Search the graph by keyword
88
+ - **codify_explain** -- Claude-powered narrative synthesis from graph data
89
+ - **codify_get_gaps** -- List detected context gaps
90
+ - **codify_resolve_gap** -- Mark a gap as resolved with evidence
91
+ - **codify_add_context** -- Add new context nodes to the graph
92
+ - **codify_get_decision_trail** -- Trace the reasoning chain behind a decision
93
+ - **codify_traverse** -- Walk the graph from any node
94
+ - **codify_status** -- Graph health and statistics
95
+ - **codify_collect** -- Mine evidence for open gaps
96
+ - **codify_get_context_package** -- Get a bundled context snapshot for a topic
97
+
98
+ ## How It Works
99
+
100
+ Codify uses PostgreSQL as its single storage engine:
101
+
102
+ - **Apache AGE** for graph traversal (nodes, edges, relationships)
103
+ - **pgvector** for semantic search (embedding-based similarity)
104
+ - **NATS JetStream** for event-driven gap detection and metabolism
105
+ - **Redis** for caching
106
+
107
+ The context graph stores nodes (Decision, Feature, CustomerSignal, CodeArtifact, Gap, etc.) and typed edges representing their relationships. A Metabolism service continuously maintains graph health through freshness decay, contradiction detection, and deduplication.
108
+
109
+ ## Links
110
+
111
+ - GitHub: [github.com/kurtxu88/codify](https://github.com/kurtxu88/codify)
112
+
113
+ ## License
114
+
115
+ MIT