@just-every/code 0.4.20 → 0.5.0
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 +18 -18
- package/package.json +6 -6
package/README.md
CHANGED
|
@@ -1,19 +1,19 @@
|
|
|
1
|
-
# CODE
|
|
1
|
+
# Every CODE
|
|
2
2
|
|
|
3
3
|
 
|
|
4
4
|
|
|
5
|
-
<
|
|
6
|
-
<img src="docs/logo.png" alt="Code Logo" width="400">
|
|
7
|
-
</p>
|
|
5
|
+
<img src="docs/every-logo.png" alt="Every Code Logo" width="400">
|
|
8
6
|
|
|
9
7
|
 
|
|
10
8
|
|
|
11
|
-
**Code** is a fast, local coding agent for your terminal. It's a community-driven fork of `openai/codex` focused on real developer ergonomics: Browser integration, multi-agents, theming, and reasoning control — all while staying compatible with upstream.
|
|
9
|
+
**Every Code** (Code for short) is a fast, local coding agent for your terminal. It's a community-driven fork of `openai/codex` focused on real developer ergonomics: Browser integration, multi-agents, theming, and reasoning control — all while staying compatible with upstream.
|
|
12
10
|
|
|
13
11
|
 
|
|
14
|
-
## What's new in v0.
|
|
12
|
+
## What's new in v0.5.0 (November 21st 2025)
|
|
15
13
|
|
|
14
|
+
- **Renamed to Every Code** – new name for better discoverability while keeping the `code` shorthand.
|
|
16
15
|
- **Auto Drive upgraded** – hand `/auto` a task and it now plans, coordinates agents, reruns checks, and recovers from hiccups without babysitting.
|
|
16
|
+
- **Many QoL improvements** – `/resume` and `/undo` work reliably. All major upstream features have been ported across including compaction v2 and -max and -mini models.
|
|
17
17
|
- **Unified settings** – `/settings` centralizes limits, model routing, themes, and CLI integrations so you can audit configuration in one place.
|
|
18
18
|
- **Card-based activity** – Agents, browser sessions, web search, and Auto Drive render as compact cards with drill-down overlays for full logs.
|
|
19
19
|
- **Turbocharged performance** – History rendering and streaming were optimized to stay smooth even during long multi-agent sessions.
|
|
@@ -22,7 +22,7 @@
|
|
|
22
22
|
Read the full notes in `release-notes/RELEASE_NOTES.md`.
|
|
23
23
|
|
|
24
24
|
 
|
|
25
|
-
## Why Code
|
|
25
|
+
## Why Every Code
|
|
26
26
|
|
|
27
27
|
- 🚀 **Auto Drive orchestration** – Multi-agent automation that now self-heals and ships complete tasks.
|
|
28
28
|
- 🌐 **Browser Integration** – CDP support, headless browsing, screenshots captured inline.
|
|
@@ -79,7 +79,7 @@ Note: If another tool already provides a `code` command (e.g. VS Code), our CLI
|
|
|
79
79
|
|
|
80
80
|
### Install Claude & Gemini (optional)
|
|
81
81
|
|
|
82
|
-
Code supports orchestrating other AI CLI tools. Install these and config to use alongside Code.
|
|
82
|
+
Every Code supports orchestrating other AI CLI tools. Install these and config to use alongside Code.
|
|
83
83
|
|
|
84
84
|
```bash
|
|
85
85
|
# Ensure Node.js 20+ is available locally (installs into ~/.n)
|
|
@@ -175,7 +175,7 @@ Options:
|
|
|
175
175
|
 
|
|
176
176
|
## Memory & project docs
|
|
177
177
|
|
|
178
|
-
Code can remember context across sessions:
|
|
178
|
+
Every Code can remember context across sessions:
|
|
179
179
|
|
|
180
180
|
1. **Create an `AGENTS.md` or `CLAUDE.md` file** in your project root:
|
|
181
181
|
```markdown
|
|
@@ -191,7 +191,7 @@ This is a React TypeScript application with:
|
|
|
191
191
|
- `/server/` - Backend services
|
|
192
192
|
```
|
|
193
193
|
|
|
194
|
-
2. **Session memory**: Code maintains conversation history
|
|
194
|
+
2. **Session memory**: Every Code maintains conversation history
|
|
195
195
|
3. **Codebase analysis**: Automatically understands project structure
|
|
196
196
|
|
|
197
197
|
 
|
|
@@ -213,7 +213,7 @@ code --config output_format=json "list all TODO comments"
|
|
|
213
213
|
 
|
|
214
214
|
## Model Context Protocol (MCP)
|
|
215
215
|
|
|
216
|
-
Code supports MCP for extended capabilities:
|
|
216
|
+
Every Code supports MCP for extended capabilities:
|
|
217
217
|
|
|
218
218
|
- **File operations**: Advanced file system access
|
|
219
219
|
- **Database connections**: Query and modify databases
|
|
@@ -234,7 +234,7 @@ args = ["-y", "@modelcontextprotocol/server-filesystem", "/path/to/project"]
|
|
|
234
234
|
Main config file: `~/.code/config.toml`
|
|
235
235
|
|
|
236
236
|
> [!NOTE]
|
|
237
|
-
> Code reads from both `~/.code/` and `~/.codex/` for backwards compatibility, but it only writes updates to `~/.code/`. If you switch back to Codex and it fails to start, remove `~/.codex/config.toml`. If Code appears to miss settings after upgrading, copy your legacy `~/.codex/config.toml` into `~/.code/`.
|
|
237
|
+
> Every Code reads from both `~/.code/` and `~/.codex/` for backwards compatibility, but it only writes updates to `~/.code/`. If you switch back to Codex and it fails to start, remove `~/.codex/config.toml`. If Every Code appears to miss settings after upgrading, copy your legacy `~/.codex/config.toml` into `~/.code/`.
|
|
238
238
|
|
|
239
239
|
```toml
|
|
240
240
|
# Model settings
|
|
@@ -273,7 +273,7 @@ model_reasoning_summary = "detailed"
|
|
|
273
273
|
> This fork adds browser integration, multi-agent commands (`/plan`, `/solve`, `/code`), theme system, and enhanced reasoning controls while maintaining full compatibility.
|
|
274
274
|
|
|
275
275
|
**Can I use my existing Codex configuration?**
|
|
276
|
-
> Yes. Code reads from both `~/.code/` (primary) and legacy `~/.codex/` directories. We only write to `~/.code/`, so Codex will keep running if you switch back; copy or remove legacy files if you notice conflicts.
|
|
276
|
+
> Yes. Every Code reads from both `~/.code/` (primary) and legacy `~/.codex/` directories. We only write to `~/.code/`, so Codex will keep running if you switch back; copy or remove legacy files if you notice conflicts.
|
|
277
277
|
|
|
278
278
|
**Does this work with ChatGPT Plus?**
|
|
279
279
|
> Absolutely. Use the same "Sign in with ChatGPT" flow as the original.
|
|
@@ -284,7 +284,7 @@ model_reasoning_summary = "detailed"
|
|
|
284
284
|
 
|
|
285
285
|
## Contributing
|
|
286
286
|
|
|
287
|
-
We welcome contributions!
|
|
287
|
+
We welcome contributions! Every Code maintains compatibility with upstream while adding community-requested features.
|
|
288
288
|
|
|
289
289
|
### Development workflow
|
|
290
290
|
|
|
@@ -316,10 +316,10 @@ npm install
|
|
|
316
316
|
|
|
317
317
|
### License & attribution
|
|
318
318
|
- This project is a community fork of `openai/codex` under **Apache-2.0**. We preserve upstream LICENSE and NOTICE files.
|
|
319
|
-
- **Code** is **not** affiliated with, sponsored by, or endorsed by OpenAI.
|
|
319
|
+
- **Every Code** (Code) is **not** affiliated with, sponsored by, or endorsed by OpenAI.
|
|
320
320
|
|
|
321
321
|
### Your responsibilities
|
|
322
|
-
Using OpenAI, Anthropic or Google services through Code means you agree to **their Terms and policies**. In particular:
|
|
322
|
+
Using OpenAI, Anthropic or Google services through Every Code means you agree to **their Terms and policies**. In particular:
|
|
323
323
|
- **Don't** programmatically scrape/extract content outside intended flows.
|
|
324
324
|
- **Don't** bypass or interfere with rate limits, quotas, or safety mitigations.
|
|
325
325
|
- Use your **own** account; don't share or rotate accounts to evade limits.
|
|
@@ -330,14 +330,14 @@ Using OpenAI, Anthropic or Google services through Code means you agree to **the
|
|
|
330
330
|
- Inputs/outputs you send to AI providers are handled under their Terms and Privacy Policy; consult those documents (and any org-level data-sharing settings).
|
|
331
331
|
|
|
332
332
|
### Subject to change
|
|
333
|
-
AI providers can change eligibility, limits, models, or authentication flows. Code supports **both** ChatGPT sign-in and API-key modes so you can pick what fits (local/hobby vs CI/automation).
|
|
333
|
+
AI providers can change eligibility, limits, models, or authentication flows. Every Code supports **both** ChatGPT sign-in and API-key modes so you can pick what fits (local/hobby vs CI/automation).
|
|
334
334
|
|
|
335
335
|
 
|
|
336
336
|
## License
|
|
337
337
|
|
|
338
338
|
Apache 2.0 - See [LICENSE](LICENSE) file for details.
|
|
339
339
|
|
|
340
|
-
|
|
340
|
+
Every Code is a community fork of the original Codex CLI. We maintain compatibility while adding enhanced features requested by the developer community.
|
|
341
341
|
|
|
342
342
|
 
|
|
343
343
|
---
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@just-every/code",
|
|
3
|
-
"version": "0.
|
|
3
|
+
"version": "0.5.0",
|
|
4
4
|
"license": "Apache-2.0",
|
|
5
5
|
"description": "Lightweight coding agent that runs in your terminal - fork of OpenAI Codex",
|
|
6
6
|
"bin": {
|
|
@@ -35,10 +35,10 @@
|
|
|
35
35
|
"prettier": "^3.3.3"
|
|
36
36
|
},
|
|
37
37
|
"optionalDependencies": {
|
|
38
|
-
"@just-every/code-darwin-arm64": "0.
|
|
39
|
-
"@just-every/code-darwin-x64": "0.
|
|
40
|
-
"@just-every/code-linux-x64-musl": "0.
|
|
41
|
-
"@just-every/code-linux-arm64-musl": "0.
|
|
42
|
-
"@just-every/code-win32-x64": "0.
|
|
38
|
+
"@just-every/code-darwin-arm64": "0.5.0",
|
|
39
|
+
"@just-every/code-darwin-x64": "0.5.0",
|
|
40
|
+
"@just-every/code-linux-x64-musl": "0.5.0",
|
|
41
|
+
"@just-every/code-linux-arm64-musl": "0.5.0",
|
|
42
|
+
"@just-every/code-win32-x64": "0.5.0"
|
|
43
43
|
}
|
|
44
44
|
}
|