cc-claw 0.24.1 → 0.25.0
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/README.md +34 -2
- package/dist/cli.js +3407 -1199
- package/package.json +8 -3
package/README.md
CHANGED
|
@@ -4,9 +4,9 @@
|
|
|
4
4
|
<img src="assets/cc_claw.png" alt="CC-Claw Logo" width="500" />
|
|
5
5
|
</p>
|
|
6
6
|
|
|
7
|
-
A personal AI assistant on Telegram, powered by coding CLIs. CC-Claw uses **Claude Code**, **Gemini CLI**, **Codex**, and **
|
|
7
|
+
A personal AI assistant on Telegram, powered by coding CLIs. CC-Claw uses **Claude Code**, **Gemini CLI**, **Codex**, **Cursor**, **OpenRouter**, and **Ollama** as interchangeable backends — giving you a multi-model AI assistant accessible from any device.
|
|
8
8
|
|
|
9
|
-
Send text, voice, photos, documents, or videos. Switch backends with `/claude`, `/gemini`, `/codex`, or `/
|
|
9
|
+
Send text, voice, photos, documents, or videos. Switch backends with `/claude`, `/gemini`, `/codex`, `/cursor`, `/ollama`, or `/openrouter`. Spawn sub-agents across different CLIs to work in parallel. Schedule recurring tasks. Run multi-model council debates. Generate images. Execute shell commands. All state persists in SQLite.
|
|
10
10
|
|
|
11
11
|
## What Can It Do
|
|
12
12
|
|
|
@@ -19,6 +19,15 @@ Send text, voice, photos, documents, or videos. Switch backends with `/claude`,
|
|
|
19
19
|
- **50+ CLI commands** — Full system management from terminal. Every command supports `--json` for scripting.
|
|
20
20
|
- **MCP support** — Model Context Protocol servers extend the agent with external tools and data.
|
|
21
21
|
- **Cross-channel awareness** — Actions from CLI are visible to Telegram and vice versa via the activity log.
|
|
22
|
+
- **Ollama** — Local AI inference via Ollama servers for summarization, intent classification, and full chat. Zero-cost fallback. `/ollama` to manage servers and models.
|
|
23
|
+
- **OpenRouter** — API-based backend for accessing 200+ models. Model search, per-model pricing, credential rotation.
|
|
24
|
+
- **Council debates** — Multi-model structured debates via `/council`. Quick (1 round), ranked (peer ranking), or full (synthesis by chairman). Anonymous deliberation reduces model bias.
|
|
25
|
+
- **Smart routing** — `/model auto` classifies message complexity and picks the optimal model + thinking level per request. Trivial → cheapest, complex → best.
|
|
26
|
+
- **Image generation** — `/imagine <prompt>` generates images via Gemini API. Also available via `[GENERATE_IMAGE:prompt]` in agent responses.
|
|
27
|
+
- **Shell access** — `!command` runs shell commands. `!!command` for raw output. `//<command>` passes directly to the active backend CLI.
|
|
28
|
+
- **Side quests** — `sq:question` while the agent is busy starts a parallel conversation without interrupting the current task.
|
|
29
|
+
- **Self-learning** — `/evolve` enables a reflection engine that tracks feedback signals and proposes improvements to the agent's identity and behavior files.
|
|
30
|
+
- **Interactive history** — `/history` shows a day-grouped timeline with drill-down, time filters, backend filters, and full-text search.
|
|
22
31
|
|
|
23
32
|
## Supported Backends
|
|
24
33
|
|
|
@@ -28,6 +37,8 @@ Send text, voice, photos, documents, or videos. Switch backends with `/claude`,
|
|
|
28
37
|
| **Gemini** | `gemini` | 3.1 Pro Preview, 2.5 Pro, 3 Flash, 3.1 Flash Lite |
|
|
29
38
|
| **Codex** | `codex` | GPT-5.4, GPT-5.3 Codex, GPT-5.2 Codex, GPT-5.1 Codex Max, GPT-5.4 Mini |
|
|
30
39
|
| **Cursor** | `agent` | auto (default), Opus 4.6, Sonnet 4.6, GPT-5.4, GPT-5.3 Codex, Grok 4.20, Gemini 3.1 Pro, Composer 2 + thinking variants |
|
|
40
|
+
| **Ollama** | local | Any model available on connected Ollama servers |
|
|
41
|
+
| **OpenRouter** | API | 200+ models via OpenRouter API (search with `/model search`) |
|
|
31
42
|
|
|
32
43
|
## Prerequisites
|
|
33
44
|
|
|
@@ -177,6 +188,24 @@ Read commands work offline (direct DB access). Write commands require the daemon
|
|
|
177
188
|
| `/verbose` | Tool visibility level |
|
|
178
189
|
| `/limits` | Usage limits per backend (alias for `/usage`) |
|
|
179
190
|
|
|
191
|
+
### Advanced
|
|
192
|
+
|
|
193
|
+
| Command | Description |
|
|
194
|
+
|---------|-------------|
|
|
195
|
+
| `/council` (`/debate`) | Multi-model structured debate |
|
|
196
|
+
| `/imagine <prompt>` | Generate an image |
|
|
197
|
+
| `/evolve` | Self-learning dashboard |
|
|
198
|
+
| `/reflect` | Force immediate reflection analysis |
|
|
199
|
+
| `/optimize` | Identity and skill audit |
|
|
200
|
+
| `/info` | Current chat context (chatId, topic, session) |
|
|
201
|
+
| `/history` (`/hist`) | Interactive message history timeline |
|
|
202
|
+
| `/ollama` | Manage Ollama servers and models |
|
|
203
|
+
| `/chats` | Multi-chat management |
|
|
204
|
+
| `!command` | Execute shell command |
|
|
205
|
+
| `!!command` | Raw shell output |
|
|
206
|
+
| `//command` | Pass to active backend CLI |
|
|
207
|
+
| `sq:question` | Side quest (parallel while busy) |
|
|
208
|
+
|
|
180
209
|
### Memory & Context
|
|
181
210
|
|
|
182
211
|
| Command | Description |
|
|
@@ -265,6 +294,9 @@ Set in `~/.cc-claw/.env` (created by `cc-claw setup`):
|
|
|
265
294
|
| `DASHBOARD_ENABLED` | No | `1` for web dashboard on port 3141 |
|
|
266
295
|
| `EMBEDDING_PROVIDER` | No | `ollama` (default), `gemini`, `openai`, `off` |
|
|
267
296
|
| `CC_CLAW_HOME` | No | Config directory (default: `~/.cc-claw`) |
|
|
297
|
+
| `CURSOR_API_KEY` | No | Cursor backend API key |
|
|
298
|
+
| `CC_CLAW_DASHBOARD_HOST` | No | Dashboard bind address (default: `0.0.0.0`) |
|
|
299
|
+
| `REFLECTION_CODEBASE_RECOMMENDATIONS` | No | `1` to enable codebase change proposals |
|
|
268
300
|
|
|
269
301
|
## Documentation
|
|
270
302
|
|