@magnitudedev/cli 0.0.1-alpha.5 → 0.0.1-alpha.6
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 +32 -47
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -2,13 +2,18 @@
|
|
|
2
2
|
<img src="wordmark.svg" alt="Magnitude" width="100%" />
|
|
3
3
|
</p>
|
|
4
4
|
|
|
5
|
-
<p align="center"><b>Open source coding agent</b></p>
|
|
6
|
-
|
|
7
5
|
<p align="center">
|
|
8
|
-
<a href="https://docs.magnitude.dev" target="_blank"><img src="https://img.shields.io/badge/📕-Docs-232f41?style=flat-square&labelColor=
|
|
6
|
+
<a href="https://docs.magnitude.dev" target="_blank"><img src="https://img.shields.io/badge/📕-Docs-232f41?style=flat-square&labelColor=0369a1&color=gray" alt="Documentation" /></a> <img src="https://img.shields.io/badge/License-Apache%202.0-232f41?style=flat-square&labelColor=0369a1&color=gray" alt="License" /> <a href="https://discord.gg/VcdpMh9tTy" target="_blank"><img src="https://img.shields.io/discord/1305570963206836295?style=flat-square&logo=discord&logoColor=white&label=Discord&labelColor=5865F2&color=gray" alt="Discord" /></a> <a href="https://x.com/usemagnitude" target="_blank"><img src="https://img.shields.io/badge/-Follow%20Magnitude-000000?style=flat-square&labelColor=000000&color=gray&logo=x&logoColor=white" alt="Follow Magnitude" /></a>
|
|
9
7
|
</p>
|
|
10
8
|
|
|
11
|
-
|
|
9
|
+
Magnitude is an **open source coding agent** built from the ground up around subagents. You chat with a lead agent that coordinates specialized subagents on your behalf: explorers, planners, builders, reviewers, debuggers, and a browser agent.
|
|
10
|
+
|
|
11
|
+
- Building happens in subagents, so the **lead stays focused on you**
|
|
12
|
+
- Subagents are **long-lived** and **resumable**, not disposable
|
|
13
|
+
- The lead can **redirect subagents mid-task** without starting over
|
|
14
|
+
- Subagents are spun up in **parallel** for faster work
|
|
15
|
+
- A **shared workspace** keeps handoffs between agents lossless
|
|
16
|
+
- **Mix and match models** by role to balance intelligence and speed
|
|
12
17
|
|
|
13
18
|
<p align="center">
|
|
14
19
|
<img src="interface.png" alt="Magnitude Interface" width="100%" />
|
|
@@ -20,7 +25,7 @@ Open source coding agent where everything happens in specialized subagents. We c
|
|
|
20
25
|
npm install -g @magnitudedev/cli
|
|
21
26
|
```
|
|
22
27
|
|
|
23
|
-
|
|
28
|
+
Then navigate to the directory you want to work in and launch the TUI:
|
|
24
29
|
|
|
25
30
|
```bash
|
|
26
31
|
magnitude
|
|
@@ -30,68 +35,48 @@ This will launch Magnitude with a setup wizard for configuring providers and mod
|
|
|
30
35
|
|
|
31
36
|
### Providers
|
|
32
37
|
|
|
33
|
-
Magnitude works with most major model providers out of the box.
|
|
34
|
-
|
|
35
|
-
**Subscription-based** — Use models you already pay for, no API key needed.
|
|
36
|
-
- **ChatGPT Plus/Pro** — Sign in with your OpenAI account
|
|
37
|
-
- **GitHub Copilot** — Sign in with your GitHub account
|
|
38
|
-
|
|
39
|
-
**API key** — Bring your own key from any of these providers.
|
|
40
|
-
- Anthropic, OpenAI, Google Gemini, OpenRouter, Vercel AI Gateway, Google Vertex AI, Amazon Bedrock, MiniMax, Z.AI, Cerebras
|
|
38
|
+
Magnitude works with most major model providers out of the box, including open source and local models.
|
|
41
39
|
|
|
42
|
-
|
|
40
|
+
You can use your **ChatGPT Plus/Pro** or **GitHub Copilot** subscription.
|
|
43
41
|
|
|
44
|
-
See the [
|
|
42
|
+
See the [provider docs](https://docs.magnitude.dev/configuration/providers) for full provider support.
|
|
45
43
|
|
|
46
|
-
##
|
|
44
|
+
## How it works
|
|
47
45
|
|
|
48
|
-
|
|
49
|
-
- **Steerable subagents.** Subagents can surface blockers, ask clarifying questions, and be paused, resumed, or redirected mid-task.
|
|
50
|
-
- **Throw out the skills files.** Plan, review, debug, and browse are built-in subagents. No configuration needed, and the main agent actually uses them consistently.
|
|
51
|
-
- **Mix your models.** Chat with Claude, build with Codex, or use whatever combination fits your preferences for intelligence, speed, and cost.
|
|
52
|
-
- **Scoped toolsets, not modes.** Real coding jumps between planning and building too often for explicit mode toggles. Each subagent gets tools scoped to its role instead.
|
|
53
|
-
- **Talk to it while it works.** The main agent isn't blocked by implementation. Ask questions, clarify mid-build, or start planning what's next without interrupting anything.
|
|
46
|
+
The lead agent manages all subagents on your behalf. It can message, stop, resume, or redirect them and run many in parallel. You can also message subagents directly.
|
|
54
47
|
|
|
55
|
-
|
|
48
|
+
Magnitude comes out of the box with the following subagents:
|
|
49
|
+
- **Explorer**: for doing codebase or web research, both broad and narrow
|
|
50
|
+
- **Planner**: for evaluating various implementation strategies
|
|
51
|
+
- **Builder**: for implementing code changes directly in your files
|
|
52
|
+
- **Reviewer**: for strict, independent review of code changes
|
|
53
|
+
- **Debugger**: for root causing bugs and fixing them
|
|
54
|
+
- **Browser**: for verifying UI changes with a built-in browser agent
|
|
56
55
|
|
|
57
|
-
|
|
58
|
-
The main agent manages the conversation and delegates to specialized subagents (explorer, planner, builder, reviewer, browser, debugger), each with its own context window, toolset, and permissions. Subagents do focused work and report back, keeping the main agent's context clean.
|
|
56
|
+
Magnitude may use none or all of these in a given session. For a quick fix in a single file, it may edit it directly. For a very in-depth change, it may use the whole team. For most tasks, it will use some combination of explorer, planner, builder, and reviewer.
|
|
59
57
|
|
|
60
|
-
|
|
61
|
-
|
|
62
|
-
|
|
63
|
-
### Context sharing via artifacts
|
|
64
|
-
Shared markdown documents pass context between agents directly. An explorer writes findings, a planner reads them and produces a plan, a builder reads the plan and implements. No context is lost to summarization, and the main agent doesn't burn output tokens on handoff.
|
|
65
|
-
|
|
66
|
-
### Parallel by default
|
|
67
|
-
The main agent spins up multiple subagents concurrently and keeps working while they run. Exploring separate areas of the codebase, implementing unrelated features, or debugging multiple issues all happen in parallel.
|
|
58
|
+
<p align="center">
|
|
59
|
+
<img src="architecture.png" alt="Magnitude Architecture" width="100%" />
|
|
60
|
+
</p>
|
|
68
61
|
|
|
69
|
-
|
|
70
|
-
Tool output does not enter the context window by default. Agents inspect results explicitly and pull in only what they need, keeping noisy output out of the conversation.
|
|
62
|
+
## Why we built this
|
|
71
63
|
|
|
72
|
-
|
|
73
|
-
Commands are classified by risk. Read-only commands run freely. Normal commands are allowed in your project directory but blocked outside it. Dangerous commands are always blocked. No `--dangerously-skip-permissions`, no stuck permission prompts.
|
|
64
|
+
We became fully subagent-pilled the first time we saw Claude Code use an explore agent. We expected it to continue getting better and better. **But it didn't.**
|
|
74
65
|
|
|
75
|
-
|
|
76
|
-
A vision-based browser agent built on [browser-agent](https://github.com/magnitudedev/browser-agent) runs natively in the same runtime for verifying UI changes and behavior as part of the workflow.
|
|
66
|
+
The community clearly feels the same — projects like Superpowers have hit 100k+ GitHub stars augmenting Claude Code with more subagents. But they're plugging into an existing primitive that wasn't designed for deep subagent orchestration.
|
|
77
67
|
|
|
78
|
-
|
|
79
|
-
Magnitude learns your preferences and codebase conventions over time, storing them in `.magnitude/memory.md` and applying them automatically to future sessions. Skills and AGENTS.md are also supported.
|
|
68
|
+
Instead of plugging into an existing primitive, we built a new one from the ground up. That's the difference between bolting on subagents and building around them.
|
|
80
69
|
|
|
81
70
|
## Additional Info
|
|
82
71
|
|
|
83
|
-
###
|
|
72
|
+
### Documentation
|
|
84
73
|
|
|
85
|
-
|
|
74
|
+
Full documentation is available at [docs.magnitude.dev](https://docs.magnitude.dev).
|
|
86
75
|
|
|
87
76
|
### Contributing
|
|
88
77
|
|
|
89
78
|
See the [contributing guide](https://docs.magnitude.dev/contributing) to get started.
|
|
90
79
|
|
|
91
|
-
### Documentation
|
|
92
|
-
|
|
93
|
-
Full documentation is available at [docs.magnitude.dev](https://docs.magnitude.dev).
|
|
94
|
-
|
|
95
80
|
### Acknowledgements
|
|
96
81
|
|
|
97
82
|
Built on top of [BAML](https://boundaryml.com), [Effect](https://effect.website), and [OpenTUI](https://github.com/anomalyco/opentui).
|