@verboo/code 0.7.0

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/LICENSE ADDED
@@ -0,0 +1,29 @@
1
+ NOTICE
2
+
3
+ This repository contains code derived from Anthropic's Claude Code CLI.
4
+
5
+ The original Claude Code source is proprietary software:
6
+ Copyright (c) Anthropic PBC. All rights reserved.
7
+ Subject to Anthropic's Commercial Terms of Service.
8
+
9
+ Modifications and additions by OpenClaude contributors are offered under
10
+ the MIT License where legally permissible:
11
+
12
+ MIT License
13
+ Copyright (c) 2026 OpenClaude contributors (modifications only)
14
+
15
+ Permission is hereby granted, free of charge, to any person obtaining
16
+ a copy of the modifications made by OpenClaude contributors, to deal
17
+ in those modifications without restriction, including without limitation
18
+ the rights to use, copy, modify, merge, publish, distribute, sublicense,
19
+ and/or sell copies, subject to the following conditions:
20
+
21
+ The above copyright notice and this permission notice shall be included
22
+ in all copies or substantial portions of the modifications.
23
+
24
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND.
25
+
26
+ The underlying derived code remains subject to Anthropic's copyright.
27
+ This project does not have Anthropic's authorization to distribute
28
+ their proprietary source. Users and contributors should evaluate their
29
+ own legal position.
package/README.md ADDED
@@ -0,0 +1,362 @@
1
+ # Verboo Code
2
+
3
+ Verboo Code is an open-source coding-agent CLI for cloud and local model providers.
4
+
5
+ Use OpenAI-compatible APIs, Gemini, GitHub Models, Codex OAuth, Codex, Ollama, Atomic Chat, and other supported backends while keeping one terminal-first workflow: prompts, tools, agents, MCP, slash commands, and streaming output.
6
+
7
+ [![PR Checks](https://github.com/verbeux/verboo/actions/workflows/pr-checks.yml/badge.svg?branch=main)](https://github.com/verbeux/verboo/actions/workflows/pr-checks.yml)
8
+ [![Release](https://img.shields.io/github/v/tag/verbeux/verboo?label=release&color=0ea5e9)](https://github.com/verbeux/verboo/tags)
9
+ [![Discussions](https://img.shields.io/badge/discussions-open-7c3aed)](https://github.com/verbeux/verboo/discussions)
10
+ [![Security Policy](https://img.shields.io/badge/security-policy-0f766e)](SECURITY.md)
11
+ [![License](https://img.shields.io/badge/license-MIT-2563eb)](LICENSE)
12
+
13
+ Verboo Code is a fork of [openclaude](https://github.com/Gitlawb/openclaude), which itself originated from the Claude Code codebase. It is maintained by the Verboo team for the Verboo platform.
14
+
15
+ [Quick Start](#quick-start) | [Setup Guides](#setup-guides) | [Providers](#supported-providers) | [Source Build](#source-build-and-local-development) | [VS Code Extension](#vs-code-extension) | [Sponsors](#sponsors) | [Community](#community)
16
+
17
+ ## Sponsors
18
+
19
+ <p align="center">
20
+ <a href="https://gitlawb.com">
21
+ <img src="https://gitlawb.com/logo.png" alt="GitLawb logo" width="96">
22
+ </a>
23
+ &nbsp;&nbsp;&nbsp;&nbsp;
24
+ <a href="https://bankr.bot">
25
+ <img src="https://bankr.bot/favicon.svg" alt="Bankr.bot logo" width="96">
26
+ </a>
27
+ </p>
28
+
29
+ <p align="center">
30
+ <a href="https://gitlawb.com"><strong>GitLawb</strong></a>
31
+ &nbsp;&nbsp;&nbsp;&nbsp;
32
+ <a href="https://bankr.bot"><strong>Bankr.bot</strong></a>
33
+ </p>
34
+
35
+ ## Star History
36
+
37
+ [![Star History Chart](https://api.star-history.com/chart?repos=gitlawb/verboo&type=date&legend=top-left)](https://www.star-history.com/?repos=gitlawb%2Fverboo&type=date&legend=top-left)
38
+
39
+ ## Why Verboo Code
40
+
41
+ - Use one CLI across cloud APIs and local model backends
42
+ - Save provider profiles inside the app with `/provider`
43
+ - Run with OpenAI-compatible services, Gemini, GitHub Models, Codex OAuth, Codex, Ollama, Atomic Chat, and other supported providers
44
+ - Keep coding-agent workflows in one place: bash, file tools, grep, glob, agents, tasks, MCP, and web tools
45
+ - Use the bundled VS Code extension for launch integration and theme support
46
+
47
+ ## Quick Start
48
+
49
+ ### Install
50
+
51
+ ```bash
52
+ npm install -g @verboo/code
53
+ ```
54
+
55
+ If the install later reports `ripgrep not found`, install ripgrep system-wide and confirm `rg --version` works in the same terminal before starting Verboo Code.
56
+
57
+ ### Start
58
+
59
+ ```bash
60
+ verboo
61
+ ```
62
+
63
+ Inside Verboo Code:
64
+
65
+ - run `/provider` for guided provider setup and saved profiles
66
+ - run `/onboard-github` for GitHub Models onboarding
67
+
68
+ ### Fastest OpenAI setup
69
+
70
+ macOS / Linux:
71
+
72
+ ```bash
73
+ export CLAUDE_CODE_USE_OPENAI=1
74
+ export OPENAI_API_KEY=sk-your-key-here
75
+ export OPENAI_MODEL=gpt-4o
76
+
77
+ verboo
78
+ ```
79
+
80
+ Windows PowerShell:
81
+
82
+ ```powershell
83
+ $env:CLAUDE_CODE_USE_OPENAI="1"
84
+ $env:OPENAI_API_KEY="sk-your-key-here"
85
+ $env:OPENAI_MODEL="gpt-4o"
86
+
87
+ verboo
88
+ ```
89
+
90
+ ### Fastest local Ollama setup
91
+
92
+ macOS / Linux:
93
+
94
+ ```bash
95
+ export CLAUDE_CODE_USE_OPENAI=1
96
+ export OPENAI_BASE_URL=http://localhost:11434/v1
97
+ export OPENAI_MODEL=qwen2.5-coder:7b
98
+
99
+ verboo
100
+ ```
101
+
102
+ Windows PowerShell:
103
+
104
+ ```powershell
105
+ $env:CLAUDE_CODE_USE_OPENAI="1"
106
+ $env:OPENAI_BASE_URL="http://localhost:11434/v1"
107
+ $env:OPENAI_MODEL="qwen2.5-coder:7b"
108
+
109
+ verboo
110
+ ```
111
+
112
+ ### Using Ollama's launch command
113
+
114
+ If you have [Ollama](https://ollama.com) installed, you can skip the env var setup entirely:
115
+
116
+ ```bash
117
+ ollama launch verboo --model qwen2.5-coder:7b
118
+ ```
119
+
120
+ This automatically sets `ANTHROPIC_BASE_URL`, model routing, and auth so all API traffic goes through your local Ollama instance. Works with any model you have pulled — local or cloud.
121
+
122
+ ## Setup Guides
123
+
124
+ Beginner-friendly guides:
125
+
126
+ - [Non-Technical Setup](docs/non-technical-setup.md)
127
+ - [Windows Quick Start](docs/quick-start-windows.md)
128
+ - [macOS / Linux Quick Start](docs/quick-start-mac-linux.md)
129
+
130
+ Advanced and source-build guides:
131
+
132
+ - [Advanced Setup](docs/advanced-setup.md)
133
+ - [Android Install](ANDROID_INSTALL.md)
134
+
135
+ ## Supported Providers
136
+
137
+ | Provider | Setup Path | Notes |
138
+ | --- | --- | --- |
139
+ | OpenAI-compatible | `/provider` or env vars | Works with OpenAI, OpenRouter, DeepSeek, Groq, Mistral, LM Studio, and other compatible `/v1` servers |
140
+ | Gemini | `/provider` or env vars | Supports API key, access token, or local ADC workflow on current `main` |
141
+ | GitHub Models | `/onboard-github` | Interactive onboarding with saved credentials |
142
+ | Codex OAuth | `/provider` | Opens ChatGPT sign-in in your browser and stores Codex credentials securely |
143
+ | Codex | `/provider` | Uses existing Codex CLI auth, Verboo Code secure storage, or env credentials |
144
+ | Ollama | `/provider`, env vars, or `ollama launch` | Local inference with no API key |
145
+ | Atomic Chat | `/provider`, env vars, or `bun run dev:atomic-chat` | Local Model Provider; auto-detects loaded models |
146
+ | Bedrock / Vertex / Foundry | env vars | Additional provider integrations for supported environments |
147
+
148
+ ## What Works
149
+
150
+ - **Tool-driven coding workflows**: Bash, file read/write/edit, grep, glob, agents, tasks, MCP, and slash commands
151
+ - **Streaming responses**: Real-time token output and tool progress
152
+ - **Tool calling**: Multi-step tool loops with model calls, tool execution, and follow-up responses
153
+ - **Images**: URL and base64 image inputs for providers that support vision
154
+ - **Provider profiles**: Guided setup plus saved `.verboo-profile.json` support
155
+ - **Local and remote model backends**: Cloud APIs, local servers, and Apple Silicon local inference
156
+
157
+ ## Provider Notes
158
+
159
+ Verboo Code supports multiple providers, but behavior is not identical across all of them.
160
+
161
+ - Anthropic-specific features may not exist on other providers
162
+ - Tool quality depends heavily on the selected model
163
+ - Smaller local models can struggle with long multi-step tool flows
164
+ - Some providers impose lower output caps than the CLI defaults, and Verboo Code adapts where possible
165
+
166
+ For best results, use models with strong tool/function calling support.
167
+
168
+ ## Agent Routing
169
+
170
+ Verboo Code can route different agents to different models through settings-based routing. This is useful for cost optimization or splitting work by model strength.
171
+
172
+ Add to `~/.verboo.json`:
173
+
174
+ ```json
175
+ {
176
+ "agentModels": {
177
+ "deepseek-v4-flash": {
178
+ "base_url": "https://api.deepseek.com/v1",
179
+ "api_key": "sk-your-key"
180
+ },
181
+ "gpt-4o": {
182
+ "base_url": "https://api.openai.com/v1",
183
+ "api_key": "sk-your-key"
184
+ }
185
+ },
186
+ "agentRouting": {
187
+ "Explore": "deepseek-v4-flash",
188
+ "Plan": "gpt-4o",
189
+ "general-purpose": "gpt-4o",
190
+ "frontend-dev": "deepseek-v4-flash",
191
+ "default": "gpt-4o"
192
+ }
193
+ }
194
+ ```
195
+
196
+ When no routing match is found, the global provider remains the fallback.
197
+
198
+ > **Note:** `api_key` values in `settings.json` are stored in plaintext. Keep this file private and do not commit it to version control.
199
+
200
+ ## Web Search and Fetch
201
+
202
+ By default, `WebSearch` works on non-Anthropic models using DuckDuckGo. This gives GPT-4o, DeepSeek, Gemini, Ollama, and other OpenAI-compatible providers a free web search path out of the box.
203
+
204
+ > **Note:** DuckDuckGo fallback works by scraping search results and may be rate-limited, blocked, or subject to DuckDuckGo's Terms of Service. If you want a more reliable supported option, configure Firecrawl.
205
+
206
+ For Anthropic-native backends and Codex responses, Verboo Code keeps the native provider web search behavior.
207
+
208
+ `WebFetch` works, but its basic HTTP plus HTML-to-markdown path can still fail on JavaScript-rendered sites or sites that block plain HTTP requests.
209
+
210
+ Set a [Firecrawl](https://firecrawl.dev) API key if you want Firecrawl-powered search/fetch behavior:
211
+
212
+ ```bash
213
+ export FIRECRAWL_API_KEY=your-key-here
214
+ ```
215
+
216
+ With Firecrawl enabled:
217
+
218
+ - `WebSearch` can use Firecrawl's search API while DuckDuckGo remains the default free path for non-Claude models
219
+ - `WebFetch` uses Firecrawl's scrape endpoint instead of raw HTTP, handling JS-rendered pages correctly
220
+
221
+ Free tier at [firecrawl.dev](https://firecrawl.dev) includes 500 credits. The key is optional.
222
+
223
+ ---
224
+
225
+ ## Headless gRPC Server
226
+
227
+ Verboo Code can be run as a headless gRPC service, allowing you to integrate its agentic capabilities (tools, bash, file editing) into other applications, CI/CD pipelines, or custom user interfaces. The server uses bidirectional streaming to send real-time text chunks, tool calls, and request permissions for sensitive commands.
228
+
229
+ ### 1. Start the gRPC Server
230
+
231
+ Start the core engine as a gRPC service on `localhost:50051`:
232
+
233
+ ```bash
234
+ npm run dev:grpc
235
+ ```
236
+
237
+ #### Configuration
238
+
239
+ | Variable | Default | Description |
240
+ |-----------|-------------|------------------------------------------------|
241
+ | `GRPC_PORT` | `50051` | Port the gRPC server listens on |
242
+ | `GRPC_HOST` | `localhost` | Bind address. Use `0.0.0.0` to expose on all interfaces (not recommended without authentication) |
243
+
244
+ ### 2. Run the Test CLI Client
245
+
246
+ We provide a lightweight CLI client that communicates exclusively over gRPC. It acts just like the main interactive CLI, rendering colors, streaming tokens, and prompting you for tool permissions (y/n) via the gRPC `action_required` event.
247
+
248
+ In a separate terminal, run:
249
+
250
+ ```bash
251
+ npm run dev:grpc:cli
252
+ ```
253
+
254
+ *Note: The gRPC definitions are located in `src/proto/verboo.proto`. You can use this file to generate clients in Python, Go, Rust, or any other language.*
255
+
256
+ ---
257
+
258
+ ## Source Build And Local Development
259
+
260
+ ```bash
261
+ bun install
262
+ bun run build
263
+ node dist/cli.mjs
264
+ ```
265
+
266
+ Helpful commands:
267
+
268
+ - `bun run dev`
269
+ - `bun test`
270
+ - `bun run test:coverage`
271
+ - `bun run security:pr-scan -- --base origin/main`
272
+ - `bun run smoke`
273
+ - `bun run doctor:runtime`
274
+ - `bun run verify:privacy`
275
+ - focused `bun test ...` runs for the areas you touch
276
+
277
+ ## Testing And Coverage
278
+
279
+ Verboo Code uses Bun's built-in test runner for unit tests.
280
+
281
+ Run the full unit suite:
282
+
283
+ ```bash
284
+ bun test
285
+ ```
286
+
287
+ Generate unit test coverage:
288
+
289
+ ```bash
290
+ bun run test:coverage
291
+ ```
292
+
293
+ Open the visual coverage report:
294
+
295
+ ```bash
296
+ open coverage/index.html
297
+ ```
298
+
299
+ If you already have `coverage/lcov.info` and only want to rebuild the UI:
300
+
301
+ ```bash
302
+ bun run test:coverage:ui
303
+ ```
304
+
305
+ Use focused test runs when you only touch one area:
306
+
307
+ - `bun run test:provider`
308
+ - `bun run test:provider-recommendation`
309
+ - `bun test path/to/file.test.ts`
310
+
311
+ Recommended contributor validation before opening a PR:
312
+
313
+ - `bun run build`
314
+ - `bun run smoke`
315
+ - `bun run test:coverage` for broader unit coverage when your change affects shared runtime or provider logic
316
+ - focused `bun test ...` runs for the files and flows you changed
317
+
318
+ Coverage output is written to `coverage/lcov.info`, and Verboo Code also generates a git-activity-style heatmap at `coverage/index.html`.
319
+ ## Repository Structure
320
+
321
+ - `src/` - core CLI/runtime
322
+ - `scripts/` - build, verification, and maintenance scripts
323
+ - `docs/` - setup, contributor, and project documentation
324
+ - `python/` - standalone Python helpers and their tests
325
+ - `vscode-extension/verboo-vscode/` - VS Code extension
326
+ - `.github/` - repo automation, templates, and CI configuration
327
+ - `bin/` - CLI launcher entrypoints
328
+
329
+ ## VS Code Extension
330
+
331
+ The repo includes a VS Code extension in [`vscode-extension/verboo-vscode`](vscode-extension/verboo-vscode) for Verboo Code launch integration, provider-aware control-center UI, and theme support.
332
+
333
+ ## Security
334
+
335
+ If you believe you found a security issue, see [SECURITY.md](SECURITY.md).
336
+
337
+ ## Community
338
+
339
+ - Use [GitHub Discussions](https://github.com/verbeux/verboo/discussions) for Q&A, ideas, and community conversation
340
+ - Use [GitHub Issues](https://github.com/verbeux/verboo/issues) for confirmed bugs and actionable feature work
341
+
342
+ ## Contributing
343
+
344
+ Contributions are welcome.
345
+
346
+ For larger changes, open an issue first so the scope is clear before implementation. Helpful validation commands include:
347
+
348
+ - `bun run build`
349
+ - `bun run test:coverage`
350
+ - `bun run smoke`
351
+ - focused `bun test ...` runs for files and flows you changed
352
+
353
+
354
+ ## Disclaimer
355
+
356
+ Verboo Code is an independent community project and is not affiliated with, endorsed by, or sponsored by Anthropic.
357
+
358
+ Verboo Code originated from the Claude Code codebase and has since been substantially modified to support multiple providers and open use. "Claude" and "Claude Code" are trademarks of Anthropic PBC. See [LICENSE](LICENSE) for details.
359
+
360
+ ## License
361
+
362
+ See [LICENSE](LICENSE).
@@ -0,0 +1,13 @@
1
+ import { join, win32 } from 'path'
2
+ import { pathToFileURL } from 'url'
3
+
4
+ export function getDistImportSpecifier(baseDir) {
5
+ if (/^[A-Za-z]:\\/.test(baseDir)) {
6
+ const distPath = win32.join(baseDir, '..', 'dist', 'cli.mjs')
7
+ return `file:///${distPath.replace(/\\/g, '/')}`
8
+ }
9
+
10
+ const joinImpl = join
11
+ const distPath = joinImpl(baseDir, '..', 'dist', 'cli.mjs')
12
+ return pathToFileURL(distPath).href
13
+ }
package/bin/openclaude ADDED
@@ -0,0 +1,34 @@
1
+ #!/usr/bin/env node
2
+
3
+ /**
4
+ * VERBOO-BRAND: Legacy alias for `verboo` binary. Kept for backward compat
5
+ * during transition — prefer `bin/verboo` going forward.
6
+ *
7
+ * If dist/cli.mjs exists (built), run that.
8
+ * Otherwise, tell the user to build first or use `bun run dev`.
9
+ */
10
+
11
+ import { existsSync } from 'fs'
12
+ import { join, dirname } from 'path'
13
+ import { fileURLToPath, pathToFileURL } from 'url'
14
+
15
+ const __dirname = dirname(fileURLToPath(import.meta.url))
16
+ const distPath = join(__dirname, '..', 'dist', 'cli.mjs')
17
+
18
+ if (existsSync(distPath)) {
19
+ process.env.VERBOO_CLI_BRAND = 'openclaude';
20
+ await import(pathToFileURL(distPath).href)
21
+ } else {
22
+ console.error(`
23
+ verboo (openclaude alias): dist/cli.mjs not found.
24
+
25
+ Build first:
26
+ bun run build
27
+
28
+ Or run directly with Bun:
29
+ bun run dev
30
+
31
+ See README.md for setup instructions.
32
+ `)
33
+ process.exit(1)
34
+ }
package/bin/verboo ADDED
@@ -0,0 +1,32 @@
1
+ #!/usr/bin/env node
2
+
3
+ /**
4
+ * VERBOO-BRAND: Verboo Code — coding agent for the Verboo platform.
5
+ *
6
+ * If dist/cli.mjs exists (built), run that.
7
+ * Otherwise, tell the user to build first or use `bun run dev`.
8
+ */
9
+
10
+ import { existsSync } from 'fs'
11
+ import { join, dirname } from 'path'
12
+ import { fileURLToPath, pathToFileURL } from 'url'
13
+
14
+ const __dirname = dirname(fileURLToPath(import.meta.url))
15
+ const distPath = join(__dirname, '..', 'dist', 'cli.mjs')
16
+
17
+ if (existsSync(distPath)) {
18
+ await import(pathToFileURL(distPath).href)
19
+ } else {
20
+ console.error(`
21
+ verboo: dist/cli.mjs not found.
22
+
23
+ Build first:
24
+ bun run build
25
+
26
+ Or run directly with Bun:
27
+ bun run dev
28
+
29
+ See README.md for setup instructions.
30
+ `)
31
+ process.exit(1)
32
+ }