@codified/cli 0.4.7 → 0.5.1

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.
package/README.md CHANGED
@@ -1,114 +1,114 @@
1
- # Codify
1
+ # @codified/cli
2
2
 
3
- **Living context graph for AI-native teams.**
3
+ **Living Context Graph for AI-Native Teams**
4
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.
5
+ Codify mines your project history into a structured context graph -- decisions, features, customer signals, code artifacts, and their relationships. Claude Code gets ambient access via MCP, so your AI assistant understands not just *what* your code does but *why* it was built that way.
6
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
7
+ ## Quick Start
16
8
 
17
9
  ```bash
18
10
  npm install -g @codified/cli
19
- ```
20
-
21
- ## Quickstart
22
-
23
- ```bash
24
11
  cd your-project
12
+ export ANTHROPIC_API_KEY=sk-ant-...
25
13
  codify up
26
14
  ```
27
15
 
28
- `codify up` runs three steps in sequence:
16
+ `codify up` runs three steps in sequence -- infrastructure setup, git history mining, and MCP server launch. After it completes, open Claude Code. Codify connects automatically and Claude gains access to 23 MCP tools and 4 MCP resources covering your project's full context.
29
17
 
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.
18
+ ## Prerequisites
33
19
 
34
- After this, open Claude Code in your project. It now has full context about your codebase.
20
+ - Node.js 22+
21
+ - Docker Desktop
22
+ - `ANTHROPIC_API_KEY` environment variable
23
+ - `VOYAGE_API_KEY` (optional, enables semantic search via Voyage AI embeddings)
35
24
 
36
- ## Commands
25
+ ## CLI Commands (30)
37
26
 
38
- ### Getting Started
27
+ ### Setup
39
28
 
40
29
  | Command | Description |
41
30
  |---------|-------------|
42
31
  | `codify up` | One-command setup and start (init + bootstrap + start) |
43
- | `codify init` | Set up infrastructure and configure project |
32
+ | `codify init` | Set up Docker services, run migrations, install MCP config |
44
33
  | `codify bootstrap` | Mine git history into the context graph |
45
34
  | `codify start` | Start the MCP server for Claude Code |
35
+ | `codify project` | Manage multiple projects (create, list, switch) |
46
36
 
47
- ### Working with Context
37
+ ### Context and Search
48
38
 
49
39
  | Command | Description |
50
40
  |---------|-------------|
51
- | `codify explain <question>` | Ask Claude a question about your project |
52
- | `codify search <query>` | Search the context graph by keyword |
41
+ | `codify search <query>` | Search the context graph |
42
+ | `codify explain <question>` | Claude-powered narrative answer about your project |
43
+ | `codify briefing <topic>` | Synthesized context briefing on a topic |
44
+ | `codify decide <question>` | Assemble decision-point context (evidence, gaps, risks) |
53
45
  | `codify add` | Record a decision, signal, or other context |
54
46
  | `codify graph` | Visualize the context graph (Mermaid diagram) |
55
- | `codify status` | Show project health dashboard |
47
+ | `codify check <file>` | Check files for related context (CI-ready, exit 0/1) |
56
48
 
57
- ### Gaps and Quality
49
+ ### Gap Management
58
50
 
59
51
  | Command | Description |
60
52
  |---------|-------------|
53
+ | `codify status` | Show project health dashboard |
61
54
  | `codify gaps` | Show gaps detected by the Gap Engine |
62
55
  | `codify triage` | Interactively resolve gaps |
63
56
  | `codify collect` | Mine the graph for evidence to fill gaps |
64
- | `codify check <file>` | Check files for related context (CI-ready) |
57
+ | `codify evolve` | Manage structural evolution proposals |
58
+
59
+ ### Connectors
60
+
61
+ | Command | Description |
62
+ |---------|-------------|
63
+ | `codify connect` | Connect external data sources (Slack, GitHub, Linear, Notion, docs) |
64
+ | `codify connectors` | List all connectors with health status |
65
+ | `codify watch` | Start continuous ingest polling with heartbeat |
65
66
 
66
- ### Projects and Maintenance
67
+ ### Analytics
67
68
 
68
69
  | Command | Description |
69
70
  |---------|-------------|
70
- | `codify project create/list/switch` | Manage multiple projects |
71
+ | `codify digest` | Daily context digest -- graph growth, gaps, metabolism |
72
+ | `codify metrics` | Collection pipeline analytics |
73
+ | `codify audit` | Metabolism audit trail (decay, prune, promote events) |
74
+
75
+ ### Maintenance
76
+
77
+ | Command | Description |
78
+ |---------|-------------|
79
+ | `codify refresh-freshness` | Recalculate freshness scores for all nodes |
71
80
  | `codify timeline` | Show what changed in the graph over time |
72
- | `codify export` | Backup the graph to JSON |
81
+ | `codify cleanup` | Fix legacy data quality issues |
82
+ | `codify embed` | Backfill embeddings for semantic search |
83
+ | `codify export` | Backup the graph to a JSON file |
73
84
  | `codify import` | Restore the graph from a JSON backup |
74
- | `codify watch` | Start continuous ingest polling |
75
- | `codify connect` | Connect external data sources |
76
85
  | `codify reset` | Reset the context graph (drop all data) |
77
86
 
78
87
  Run `codify <command> --help` for detailed options on any command.
79
88
 
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:
89
+ ## MCP Tools (23)
85
90
 
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
91
+ When the MCP server is running, Claude Code gets access to 23 tools:
97
92
 
98
- ## How It Works
93
+ | Category | Tools |
94
+ |----------|-------|
95
+ | Search and Navigate | `codify_get_context`, `codify_search`, `codify_traverse`, `codify_get_decision_trail`, `codify_explain`, `codify_get_context_package`, `codify_decision_context`, `codify_get_digest` |
96
+ | Gap Engine | `codify_get_gaps`, `codify_resolve_gap`, `codify_collect` |
97
+ | Collection | `codify_get_collection_plans`, `codify_get_collection_metrics` |
98
+ | Metabolism | `codify_get_metabolism_audit`, `codify_get_evolution_proposals`, `codify_execute_evolution` |
99
+ | Graph Mutation | `codify_add_context`, `codify_bootstrap`, `codify_status`, `codify_subscribe_events` |
100
+ | Branching | `codify_create_branch`, `codify_merge_branch`, `codify_list_branches` |
99
101
 
100
- Codify uses PostgreSQL as its single storage engine:
102
+ Plus 4 MCP resources: `codify://schema`, `codify://quickstart`, `codify://context/{topic}`, `codify://gaps/active`.
101
103
 
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
104
+ ## Architecture
106
105
 
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.
106
+ PostgreSQL as a single storage engine with Apache AGE (graph), pgvector (semantic search), NATS JetStream (events), and Redis (caching). TypeScript monorepo with 8 packages.
108
107
 
109
108
  ## Links
110
109
 
111
110
  - GitHub: [github.com/kurtxu88/codify](https://github.com/kurtxu88/codify)
111
+ - [Full documentation](https://github.com/kurtxu88/codify/blob/main/docs/getting-started.md)
112
112
 
113
113
  ## License
114
114