monomind 2.9.22 → 2.9.23

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 (2) hide show
  1. package/README.md +31 -12
  2. package/package.json +4 -4
package/README.md CHANGED
@@ -6,7 +6,7 @@
6
6
 
7
7
  <p align="center">
8
8
  <strong>An open-source MCP server that extends Claude Code with a codebase knowledge graph, persistent memory, and multi-agent coordination.</strong><br/>
9
- Apache 2.0 licensed &middot; Fully local &middot; No data leaves your machine
9
+ Apache 2.0 licensed &middot; Your code and memory stay local — see [Trust & Security](#trust--security) for the network calls Monomind does make
10
10
  </p>
11
11
 
12
12
  <p align="center">
@@ -30,7 +30,7 @@
30
30
 
31
31
  ## What is Monomind?
32
32
 
33
- Monomind is an **open-source CLI and MCP server** that plugs into Claude Code (and [opencode](https://opencode.ai) / Antigravity) via the standard [Model Context Protocol](https://modelcontextprotocol.io/). It adds capabilities these assistants don't ship with out of the box:
33
+ Monomind is an **open-source CLI and MCP server** that plugs into Claude Code, [OpenCode](https://opencode.ai), Antigravity, Kimi Code, and Codex via the standard [Model Context Protocol](https://modelcontextprotocol.io/). It adds capabilities these assistants don't ship with out of the box:
34
34
 
35
35
  - **Codebase knowledge graph** — tree-sitter parses your code into a SQLite-backed graph of files, functions, classes, and their relationships. Query imports, callers, and blast radius before making changes.
36
36
  - **Persistent memory** — a JSON pattern store with episodic recall that survives across sessions. Agents and orgs share context without re-prompting.
@@ -54,10 +54,10 @@ Nothing extra to do — agy output is part of **default** `monomind init`: `GEMI
54
54
  <summary><strong>Using opencode instead?</strong></summary>
55
55
 
56
56
  ```bash
57
- monomind init --opencode # emits opencode.json + .opencode/ alongside Claude/Antigravity output
57
+ monomind init --target opencode # initialize only OpenCode
58
58
  ```
59
59
 
60
- `--opencode` is additive — it never touches your `.claude/` or `.gemini/` config. You get the same MCP tools, agent roster, commands, skills, and security gates, plus a `/monomind-status` command (opencode has no custom statusbar, so the statusline is on-demand). See [opencode guide →](doc/concepts/opencode.md).
60
+ `monomind init` initializes all supported coding systems. `--target opencode` initializes only OpenCode; the legacy `--opencode` flag remains an alias. You get the same MCP tools, agent roster, commands, skills, and security gates, plus a `/monomind-status` command. See [OpenCode guide →](doc/concepts/opencode.md).
61
61
 
62
62
  </details>
63
63
 
@@ -65,10 +65,29 @@ monomind init --opencode # emits opencode.json + .opencode/ alongside Clau
65
65
  <summary><strong>Using Kimi Code instead?</strong></summary>
66
66
 
67
67
  ```bash
68
- monomind init --kimicode # emits .kimi-code/ + AGENTS.md alongside Claude/Antigravity output
68
+ monomind init --target kimicode # initialize only Kimi Code
69
69
  ```
70
70
 
71
- `--kimicode` is additive — it never touches your `.claude/` or `.gemini/` config. You get the same MCP tools, agent roster, skills, and commands (as project-level flow skills). Install the generated plugin once for `/monomind:*` slash commands and security gates: `/plugins install ./.kimi-code/plugin`. If `~/.kimi-code/` exists, init also wires the monomind status bar into kimi's footer. See [Kimi Code guide →](doc/concepts/kimicode.md).
71
+ `monomind init` includes Kimi Code by default. `--target kimicode` initializes only Kimi Code; the legacy `--kimicode` flag remains an alias. You get the same MCP tools, agent roster, skills, and commands (as project-level flow skills). Install the generated plugin once for `/monomind:*` slash commands and security gates: `/plugins install ./.kimi-code/plugin`. See [Kimi Code guide →](doc/concepts/kimicode.md).
72
+
73
+ </details>
74
+
75
+ <details>
76
+ <summary><strong>Using Codex?</strong></summary>
77
+
78
+ ```bash
79
+ codex login
80
+ monomind init --codex
81
+ ```
82
+
83
+ This emits a project-scoped `.codex/config.toml` that registers Monomind's MCP
84
+ server, plus `AGENTS.md` with Codex-specific guidance. Codex must trust the
85
+ project before it loads project-scoped configuration. To run persistent
86
+ Monomind organizations through Codex, set `"runtime": "codex"` in the org
87
+ definition.
88
+
89
+ Use `monomind init` with no target to initialize every supported coding system.
90
+ Use `monomind init --target codex` (or `--codex`) to initialize only Codex. See [Codex guide →](doc/concepts/codex.md).
72
91
 
73
92
  </details>
74
93
 
@@ -77,7 +96,7 @@ monomind init --kimicode # emits .kimi-code/ + AGENTS.md alongside Claude/
77
96
  | Concern | Answer |
78
97
  |---|---|
79
98
  | **License** | [Apache 2.0](LICENSE) — use it however you want |
80
- | **Data privacy** | Everything runs locally — your code and memory store never leave your machine. The one exception: crash reporting is on by default (`monomind crash-reporting disable` to opt out) — a hard crash in monomind/mono-agent/monotask/mono-clip files a GitHub issue on that tool's own repo via the GitHub API. That's the only network call Monomind itself makes; it never phones a monoes-controlled server. |
99
+ | **Data privacy** | Your code and memory store stay local. Monomind does make outbound network calls, all to third-party services — never to a monoes-controlled server: crash reporting (on by default, `monomind crash-reporting disable` to opt out) files a GitHub issue via the GitHub API on a hard crash; `security cve` queries the OSV vulnerability database; `update` checks the npm registry for new versions; the embedding model is downloaded from the HuggingFace CDN on first use. Neural pattern export/import (`hooks intelligence export`/`import`) is local-file-only. |
81
100
  | **Dependencies** | Standard npm packages (tree-sitter, better-sqlite3, sql.js, zod). tree-sitter and better-sqlite3 are native (prebuilt) Node addons, not pure JS/WASM — sql.js is WASM. No post-install scripts that download code. |
82
101
  | **Permissions** | Registers as an MCP server — Claude Code controls what tools are available and prompts you before executing anything sensitive. |
83
102
  | **Source** | Fully open. Read every line at [github.com/monoes/monomind](https://github.com/monoes/monomind). |
@@ -313,21 +332,21 @@ Before touching any file, Monomind queries **Monograph** — a SQLite-backed kno
313
332
 
314
333
  ## 🎣 Hooks & Workers
315
334
 
316
- Monomind wires 29 hook subcommands into Claude Code across edit, task, command, and session lifecycle events — logging patterns, routing agents, and feeding the intelligence system.
335
+ Monomind wires 28 hook subcommands into Claude Code across edit, task, command, and session lifecycle events — logging patterns, routing agents, and feeding the intelligence system.
317
336
 
318
337
  ```mermaid
319
338
  flowchart LR
320
339
  CE["Claude Code\nEvent"] --> H["Hook Router"]
321
340
  H --> P["pre-edit\npre-task\npre-command"]
322
341
  H --> SS["session-start\nsession-end\nnotify"]
323
- H --> I["route\nlearn\nbuild-agents"]
342
+ H --> I["route\nlearn"]
324
343
  H --> T["teammate-idle\ntask-completed"]
325
344
 
326
345
  I --> DB[("patterns.json\nmemory store")]
327
346
  DB -->|next session| CE
328
347
  ```
329
348
 
330
- **8 on-demand workers** run at session start (staleness-gated, refreshed when older than 6 hours): `health` · `ddd` · `security` · `cache` · `progress` · `map` · `audit` · `consolidate`.
349
+ **9 on-demand workers** run at session start (staleness-gated, refreshed when older than 6 hours): `health` · `ddd` · `security` · `cache` · `progress` · `map` · `audit` · `consolidate` · `reflexion`.
331
350
 
332
351
  ---
333
352
 
@@ -394,7 +413,7 @@ Everything runs from inside Claude Code via slash commands. Here's the highlight
394
413
  | `@monoes/monomindcli` | [![npm](https://img.shields.io/npm/v/@monoes/monomindcli?style=flat-square&color=4F46E5)](https://www.npmjs.com/package/@monoes/monomindcli) | CLI engine (32 commands, MCP server) |
395
414
  | `@monoes/monograph` | [![npm](https://img.shields.io/npm/v/@monoes/monograph?style=flat-square&color=F59E0B)](https://www.npmjs.com/package/@monoes/monograph) | Code knowledge graph (tree-sitter + SQLite) |
396
415
  | `@monoes/memory` | [![npm](https://img.shields.io/npm/v/@monoes/memory?style=flat-square&color=8B5CF6)](https://www.npmjs.com/package/@monoes/memory) | Persistent memory backends (SQLite + vectors) |
397
- | `@monoes/hooks` | [![npm](https://img.shields.io/npm/v/@monoes/hooks?style=flat-square&color=10B981)](https://www.npmjs.com/package/@monoes/hooks) | Hook registry + 8 on-demand workers |
416
+ | `@monoes/hooks` | [![npm](https://img.shields.io/npm/v/@monoes/hooks?style=flat-square&color=10B981)](https://www.npmjs.com/package/@monoes/hooks) | Hook registry + 9 on-demand workers |
398
417
  | `@monoes/mcp` | [![npm](https://img.shields.io/npm/v/@monoes/mcp?style=flat-square&color=3B82F6)](https://www.npmjs.com/package/@monoes/mcp) | MCP server framework (stdio/HTTP/WebSocket) |
399
418
  | `@monoes/routing` | [![npm](https://img.shields.io/npm/v/@monoes/routing?style=flat-square&color=F97316)](https://www.npmjs.com/package/@monoes/routing) | Semantic task-to-agent routing |
400
419
  | `@monoes/monobrowse` | [![npm](https://img.shields.io/npm/v/@monoes/monobrowse?style=flat-square&color=06B6D4)](https://www.npmjs.com/package/@monoes/monobrowse) | Browser automation via CDP |
@@ -432,7 +451,7 @@ graph TD
432
451
  style ORG fill:#F59E0B22,stroke:#F59E0B
433
452
  ```
434
453
 
435
- **Claude Code's Task tool drives in-session multi-agent work; `monomind org run` drives persistent background orgs.** Your data never leaves your machine.
454
+ **Claude Code's Task tool drives in-session multi-agent work; `monomind org run` drives persistent background orgs.** Your code and memory stay local — see [Trust & Security](#trust--security) for the network calls Monomind does make.
436
455
 
437
456
  ---
438
457
 
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "monomind",
3
- "version": "2.9.22",
3
+ "version": "2.9.23",
4
4
  "description": "Open-source CLI extension for Claude Code and Antigravity (agy). Adds an MCP server with a codebase knowledge graph, persistent memory, multi-agent coordination, and reusable slash commands. Apache 2.0 licensed, runs locally, no data leaves your machine.",
5
5
  "type": "module",
6
6
  "bin": {
@@ -21,7 +21,7 @@
21
21
  "LICENSE"
22
22
  ],
23
23
  "dependencies": {
24
- "@monoes/monomindcli": "2.9.22"
24
+ "@monoes/monomindcli": "2.9.23"
25
25
  },
26
26
  "overrides": {
27
27
  "hono": ">=4.12.34",
@@ -44,7 +44,7 @@
44
44
  "@biomejs/biome": "^2.5.8",
45
45
  "@types/better-sqlite3": "^7.6.13",
46
46
  "@types/node": "^20.0.0",
47
- "better-sqlite3": "^12.0.0",
47
+ "better-sqlite3": ">=12.0.0",
48
48
  "tsx": "^4.21.0",
49
49
  "typescript": "^7.0.2",
50
50
  "vite": ">=8.0.16",
@@ -98,7 +98,7 @@
98
98
  },
99
99
  "scripts": {
100
100
  "postinstall": "node -e \"if(process.platform!=='win32'){try{require('child_process').execSync('find node_modules -name ._* -delete 2>/dev/null',{stdio:'ignore'})}catch{}}\"",
101
- "dev": "tsx watch src/index.ts",
101
+ "dev": "cd packages/@monomind/cli && tsx watch src/index.ts",
102
102
  "build": "tsc",
103
103
  "build:ts": "cd packages/@monomind/cli && npm run build",
104
104
  "check:versions": "node scripts/check-publish-versions.mjs",