aegiscode 4.0.12 → 4.0.19
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 +70 -38
- package/bin/cli.js +621 -622
- package/package.json +6 -5
- package/scripts/ensure-node-version.mjs +1 -1
package/README.md
CHANGED
|
@@ -42,15 +42,13 @@ cd aegiscodex-
|
|
|
42
42
|
bash install.sh
|
|
43
43
|
```
|
|
44
44
|
|
|
45
|
-
`install.sh` builds the project and creates an `aegis` wrapper in `~/.local/bin` — no sudo needed.
|
|
46
|
-
|
|
47
|
-
Either way, the command is `aegis`.
|
|
45
|
+
`install.sh` builds the project and creates an `aegis-cli` wrapper in `~/.local/bin` — no sudo needed.
|
|
48
46
|
|
|
49
47
|
---
|
|
50
48
|
|
|
51
49
|
## First run
|
|
52
50
|
|
|
53
|
-
Run `aegis` — the first thing it does is open your browser for a one-time login to your free aegiscloud.org account (Google sign-in). This is required even for fully local/Ollama-only use; once logged in, the session is cached and you won't see it again.
|
|
51
|
+
Run `aegis-cli` — the first thing it does is open your browser for a one-time login to your free aegiscloud.org account (Google sign-in). This is required even for fully local/Ollama-only use; once logged in, the session is cached and you won't see it again.
|
|
54
52
|
|
|
55
53
|
After login, if no API keys are configured, an interactive setup guide launches automatically:
|
|
56
54
|
|
|
@@ -90,7 +88,7 @@ Already paying for Claude Code? Use your subscription instead of a pay-per-token
|
|
|
90
88
|
|
|
91
89
|
```bash
|
|
92
90
|
claude setup-token # generates a Claude Code OAuth token (sk-ant-oat...)
|
|
93
|
-
aegis login --claude-pro # paste it in
|
|
91
|
+
aegis-cli login --claude-pro # paste it in
|
|
94
92
|
```
|
|
95
93
|
|
|
96
94
|
The token is saved to `~/.aegiscode/.env` as `CLAUDE_CODE_OAUTH_TOKEN` and takes priority over `ANTHROPIC_API_KEY` for any Anthropic model. Anthropic only allows OAuth subscription tokens to make API calls through the official `claude` binary, so aegiscode shells out to it instead of calling the API directly — the `claude` CLI must be installed and on `PATH`. Tool calls (file edits, shell commands) run through `claude`'s own permission system, following whichever permission mode you've set in aegiscode.
|
|
@@ -100,14 +98,14 @@ The token is saved to `~/.aegiscode/.env` as `CLAUDE_CODE_OAUTH_TOKEN` and takes
|
|
|
100
98
|
## Quick start
|
|
101
99
|
|
|
102
100
|
```bash
|
|
103
|
-
aegis # interactive mode
|
|
104
|
-
aegis "refactor this file" # start with a message
|
|
105
|
-
aegis --model deepseek-chat # use a specific model
|
|
106
|
-
aegis --router # start with the auto-router on
|
|
107
|
-
aegis --continue # resume last session
|
|
108
|
-
aegis --resume <session-id> # resume specific session
|
|
109
|
-
aegis --print "what does this repo do?" # headless — print response, exit
|
|
110
|
-
aegis --print --output-format json "summarize this" # headless JSON output, for scripts
|
|
101
|
+
aegis-cli # interactive mode
|
|
102
|
+
aegis-cli "refactor this file" # start with a message
|
|
103
|
+
aegis-cli --model deepseek-chat # use a specific model
|
|
104
|
+
aegis-cli --router # start with the auto-router on
|
|
105
|
+
aegis-cli --continue # resume last session
|
|
106
|
+
aegis-cli --resume <session-id> # resume specific session
|
|
107
|
+
aegis-cli --print "what does this repo do?" # headless — print response, exit
|
|
108
|
+
aegis-cli --print --output-format json "summarize this" # headless JSON output, for scripts
|
|
111
109
|
```
|
|
112
110
|
|
|
113
111
|
---
|
|
@@ -153,39 +151,73 @@ Any OpenAI-compatible API can be added as a custom model.
|
|
|
153
151
|
|
|
154
152
|
Full reference with copy-paste examples: **[aegiscloud.org/aegiscode/commands](https://aegiscloud.org/aegiscode/commands)**
|
|
155
153
|
|
|
154
|
+
### Session & Help
|
|
155
|
+
|
|
156
156
|
| Command | Alias | Description |
|
|
157
157
|
|---------|-------|-------------|
|
|
158
158
|
| `/help [command]` | `/?` `/h` | Show all commands, or detailed help for one |
|
|
159
|
-
| `/
|
|
159
|
+
| `/clear` | `/cls` | Clear chat history, same session ID |
|
|
160
|
+
| `/compact` | | Manually compress conversation to free up context window |
|
|
161
|
+
| `/status` | `/st` | Session info — current model, permission mode, message count, context usage |
|
|
162
|
+
| `/tokens` | `/tok` | Token usage graph and estimated dollar spend |
|
|
163
|
+
| `/version` | `/v` | Show installed aegiscode version |
|
|
164
|
+
|
|
165
|
+
### Models & Routing
|
|
166
|
+
|
|
167
|
+
| Command | Alias | Description |
|
|
168
|
+
|---------|-------|-------------|
|
|
169
|
+
| `/model [id]` | `/m` | Interactive model switcher, or jump to a model by ID |
|
|
160
170
|
| `/model list` | | List all configured models |
|
|
161
171
|
| `/model add <id> <name> <model> <baseURL> <apiKey>` | | Add a custom model |
|
|
162
172
|
| `/model remove <id>` | | Remove a model |
|
|
163
|
-
| `/router [on\|off\|stats]` | |
|
|
173
|
+
| `/router [on\|off\|stats]` | | Auto-pick the cheapest model per task based on complexity |
|
|
164
174
|
| `/router set <tier> <id>` | | Pin a model to the simple/medium/complex tier |
|
|
165
175
|
| `/effort [off\|low\|medium\|high\|max]` | | Set Claude's extended-thinking effort level |
|
|
166
|
-
| `/confirm [on\|off] [model-id]` | `/confirmations` | Toggle tool-call confirmation prompt |
|
|
167
|
-
| `/yolo [on\|off]` | | Toggle auto-approve for all tool calls |
|
|
168
|
-
|
|
169
|
-
|
|
170
|
-
|
|
171
|
-
|
|
|
172
|
-
|
|
173
|
-
| `/
|
|
174
|
-
| `/copy [n\|last\|list]` | `/cp` | Copy a code block to clipboard |
|
|
175
|
-
| `/multi <task>` | | Run task across multiple agents in parallel |
|
|
176
|
+
| `/confirm [on\|off] [model-id\|claude\|deepseek\|all]` | `/confirmations` | Toggle tool-call confirmation prompt per model |
|
|
177
|
+
| `/yolo [on\|off]` | | Toggle auto-approve for all tool calls (no prompts) |
|
|
178
|
+
|
|
179
|
+
### Multi-Agent
|
|
180
|
+
|
|
181
|
+
| Command | Alias | Description |
|
|
182
|
+
|---------|-------|-------------|
|
|
183
|
+
| `/multi <task>` | | Orchestrate multiple AI agents on a complex task |
|
|
176
184
|
| `/multiyolo <task>` | | Same as `/multi` with auto-approved tool calls |
|
|
177
185
|
| `/build <description>` | `/forge` | Build an app with multiple AI models in parallel |
|
|
178
|
-
| `/clone <url> [--name <project>]` | `/fetch-site` `/websnap` | Clone a website using DeepSeek |
|
|
179
|
-
| `/council <question>` | |
|
|
180
|
-
| `/debate <topic> [--rounds N]` | `/db` | Structured multi-
|
|
181
|
-
| `/research <question>` | | Multi-agent research |
|
|
182
|
-
|
|
183
|
-
|
|
184
|
-
|
|
185
|
-
|
|
|
186
|
-
|
|
187
|
-
| `/
|
|
188
|
-
| `/
|
|
186
|
+
| `/clone <url> [--name <project>]` | `/fetch-site` `/websnap` | Clone a website's structure and styling using DeepSeek |
|
|
187
|
+
| `/council <question>` | | Send to every configured model, surface the majority answer |
|
|
188
|
+
| `/debate <topic> [--models id1,id2] [--rounds N]` | `/db` | Structured multi-round debate between models |
|
|
189
|
+
| `/research <question>` | | Multi-agent deliberation research |
|
|
190
|
+
|
|
191
|
+
### Agent Apps (prebuilt pipelines)
|
|
192
|
+
|
|
193
|
+
| Command | Description |
|
|
194
|
+
|---------|-------------|
|
|
195
|
+
| `/audit` | Full security audit — Scanner → Risk Analyzer → Reporter (3 agents) |
|
|
196
|
+
| `/refactor` | Analyze and apply refactoring — Analyzer → Planner → Implementer (3 agents) |
|
|
197
|
+
| `/test-gen` | Generate comprehensive test suite — Explorer → Designer → Writer (3 agents) |
|
|
198
|
+
|
|
199
|
+
### Memory & Cloud
|
|
200
|
+
|
|
201
|
+
| Command | Alias | Description |
|
|
202
|
+
|---------|-------|-------------|
|
|
203
|
+
| `/memory activate <token>` | | Activate persistent cross-session semantic memory |
|
|
204
|
+
| `/memory stats` | | Show memory usage and quota |
|
|
205
|
+
| `/memory clear` | | Wipe stored memory |
|
|
206
|
+
| `/memory load <url\|path>` | | Load content into memory index |
|
|
207
|
+
| `/memory upload` | | Upload memory to cloud |
|
|
208
|
+
| `/cloud [status\|key <k>\|activate\|deactivate]` | | Manage AEGIS Cloud sync — sessions browsable at aegiscloud.org/dashboard |
|
|
209
|
+
| `/billing` | | Show subscription tier, next billing date, memory quota |
|
|
210
|
+
|
|
211
|
+
### Customization
|
|
212
|
+
|
|
213
|
+
| Command | Alias | Description |
|
|
214
|
+
|---------|-------|-------------|
|
|
215
|
+
| `/theme [name]` | `/t` | Show or switch UI theme |
|
|
216
|
+
| `/thinking` | | Toggle extended-thinking blocks expanded/collapsed |
|
|
217
|
+
| `/copy [n\|last\|list\|raw]` | `/cp` | Copy a code block to clipboard |
|
|
218
|
+
| `/skills [name\|refresh]` | `/sk` | List, show, or refresh discovered skills |
|
|
219
|
+
| `/hooks [status\|list]` | | View configured hooks and their status |
|
|
220
|
+
| `/mcp [tools\|<server-name>]` | | Show connected MCP server status and tools |
|
|
189
221
|
|
|
190
222
|
---
|
|
191
223
|
|
|
@@ -296,8 +328,8 @@ Once active, the AI remembers your stack, past decisions, and project context ac
|
|
|
296
328
|
Sessions are stored locally as JSONL files. Resume a previous session:
|
|
297
329
|
|
|
298
330
|
```bash
|
|
299
|
-
aegis --continue # resume most recent
|
|
300
|
-
aegis --resume <session-id> # resume by ID
|
|
331
|
+
aegis-cli --continue # resume most recent
|
|
332
|
+
aegis-cli --resume <session-id> # resume by ID
|
|
301
333
|
```
|
|
302
334
|
|
|
303
335
|
If cloud sync is active (`/cloud activate`, requires an aegiscloud.org API key), every session is also uploaded and browsable from **[aegiscloud.org/dashboard](https://aegiscloud.org/dashboard)** — search, folders, notes, and bulk export, from any browser. The desktop GUI's Cloud tab links straight there.
|