@magnitudedev/cli 0.0.1-alpha.12 → 0.0.1-alpha.14
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 -64
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -3,91 +3,61 @@
|
|
|
3
3
|
</p>
|
|
4
4
|
|
|
5
5
|
<p align="center">
|
|
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/
|
|
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> <a href="https://app.magnitude.dev" target="_blank"><img src="https://img.shields.io/badge/%F0%9F%96%A5-Console-232f41?style=flat-square&labelColor=0369a1&color=gray" alt="Console" /></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/badge/-Join%20community-gray?style=flat-square&logo=discord&logoColor=white&labelColor=5865F2" alt="Join community" /></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>
|
|
7
7
|
</p>
|
|
8
8
|
|
|
9
|
-
Magnitude is an **open source coding agent** with a built-in engineering process. A lead agent understands your intent, maps it into engineering tasks, and delegates to specialized workers.
|
|
10
|
-
|
|
11
|
-
- **Follows your intent**. The process stays accountable to your goal and clarifies when it isn't clear.
|
|
12
|
-
- **Less babysitting**. The lead drives the process so you don't have to.
|
|
13
|
-
- **Holds up on long tasks**. The lead coordinates but doesn't code, so its context stays focused.
|
|
14
|
-
- **Verifies everything**. Plans get challenged, code gets reviewed, UI gets checked in the browser.
|
|
15
|
-
- **Full model control**. Balance cost, speed, and intelligence across the lead and each worker.
|
|
16
|
-
|
|
17
9
|
<p align="center">
|
|
18
|
-
<
|
|
10
|
+
<strong>Opinionated coding agent for open models</strong>
|
|
19
11
|
</p>
|
|
20
12
|
|
|
21
|
-
|
|
22
|
-
|
|
23
|
-
```bash
|
|
24
|
-
npm install -g @magnitudedev/cli
|
|
25
|
-
```
|
|
13
|
+
Magnitude is the best way to code with open models. We continuously test and optimize so you don't have to.
|
|
26
14
|
|
|
27
|
-
|
|
15
|
+
- **Multi-model** - GLM, Kimi, MiniMax, DeepSeek all used for the right job.
|
|
16
|
+
- **Verified providers** - Only the ones serving the models correctly and fast.
|
|
17
|
+
- **Purpose-built** — Agent harness built from scratch around open models.
|
|
18
|
+
- **Sustainable** - Pass-through API pricing with no markup. $5 free credits.
|
|
28
19
|
|
|
29
|
-
|
|
30
|
-
|
|
31
|
-
|
|
32
|
-
|
|
33
|
-
This will launch Magnitude with a setup wizard for configuring providers and models.
|
|
34
|
-
|
|
35
|
-
Magnitude works with most major model providers out of the box, including open source and local models. You can use your **ChatGPT Plus/Pro** or **GitHub Copilot** subscription.
|
|
36
|
-
|
|
37
|
-
See the [provider docs](https://docs.magnitude.dev/configuration/providers) for full provider support.
|
|
20
|
+
<p align="center">
|
|
21
|
+
<img src="interface.png" alt="Magnitude interface" width="100%" />
|
|
22
|
+
</p>
|
|
38
23
|
|
|
39
|
-
##
|
|
24
|
+
## Get started
|
|
40
25
|
|
|
41
|
-
|
|
26
|
+
1. Run `npm i -g @magnitudedev/cli` in the terminal
|
|
27
|
+
2. Run `magnitude` which will ask for an API key
|
|
28
|
+
3. Sign up at [app.magnitude.dev](https://app.magnitude.dev) to get your free API key
|
|
42
29
|
|
|
43
|
-
|
|
30
|
+
> If you are on Windows, you will need to use `wsl`.
|
|
44
31
|
|
|
45
|
-
|
|
32
|
+
$5 of free credits to start, no card required. Pass-through API pricing with no markup after that.
|
|
46
33
|
|
|
47
|
-
|
|
34
|
+
Want to chat about your use case for open models? [Book a call with our founder](https://calendly.com/tom-magnitude/30min)
|
|
48
35
|
|
|
49
|
-
|
|
50
|
-
- **Explorer**: for doing codebase or web research, both broad and narrow
|
|
51
|
-
- **Planner**: for evaluating various implementation strategies
|
|
52
|
-
- **Builder**: for implementing code changes directly in your files
|
|
53
|
-
- **Reviewer**: for strict, independent review of code changes
|
|
54
|
-
- **Debugger**: for root causing bugs and fixing them
|
|
55
|
-
- **Browser**: for verifying UI changes with a built-in browser agent
|
|
36
|
+
## Specialized agents
|
|
56
37
|
|
|
57
|
-
Magnitude
|
|
38
|
+
Magnitude is a curated system of specialized agents, each with its own defined role. These agents are made up of a system prompt, specific context, scoped toolsets, and a dedicated model + reasoning level. Here's the agents we include:
|
|
58
39
|
|
|
59
|
-
|
|
60
|
-
|
|
61
|
-
|
|
40
|
+
- **Leader.** Talks to the user and delegates work. **Model:** GLM 5.1.
|
|
41
|
+
- **Scout.** Fast and efficient exploration. **Model:** MiniMax M2.7.
|
|
42
|
+
- **Architect.** Plans and high-level design thinking. **Model:** GLM 5.1.
|
|
43
|
+
- **Engineer.** Concrete planning and implementation. **Model:** Kimi K2.6.
|
|
44
|
+
- **Critic.** Critical and detail-oriented analysis. **Model:** GLM 5.1.
|
|
45
|
+
- **Scientist.** Empirical debugging and information gathering. **Model:** GLM 5.1.
|
|
46
|
+
- **Artisan.** Tasteful and creative work. **Model:** Kimi K2.6.
|
|
47
|
+
- **Advisor.** Smart peer of the leader, always available. **Model:** GLM 5.1.
|
|
62
48
|
|
|
63
|
-
|
|
64
|
-
There's a lot of *harness engineering* that makes this all possible:
|
|
65
|
-
- Robust agent lifecycle control with multiple context injection points
|
|
66
|
-
- Topic-specific reasoning traces to improve task adherence
|
|
67
|
-
- Two way communication between the lead and workers
|
|
68
|
-
- Long-lived workers that can be resumed when context is still relevant
|
|
69
|
-
- Shared workspace between the lead and workers (outside the project)
|
|
70
|
-
- Sensible permissions system for safer shell execution
|
|
71
|
-
- True model agnostic XML syntax
|
|
49
|
+
We test these constantly. New models drop, the lineup updates.
|
|
72
50
|
|
|
73
51
|
## Why we built this
|
|
74
52
|
|
|
75
|
-
|
|
76
|
-
|
|
77
|
-
Projects like Superpowers (which gives CC more skills) have gained a lot of momentum because people want agents to follow better software development practices. But in practice, the results are mixed. You often have to keep prompting the agent to actually use the skills, especially as tasks get longer.
|
|
78
|
-
|
|
79
|
-
This is because these skills are layered on top of an underlying agent primitive that wasn't built to use them consistently. So instead, **we built the engineering process into the primitive itself**.
|
|
80
|
-
|
|
81
|
-
## Documentation
|
|
82
|
-
|
|
83
|
-
Full documentation is available at [docs.magnitude.dev](https://docs.magnitude.dev).
|
|
53
|
+
Open models are now good enough for serious coding. But it's the wild west. You need to choose a harness, then a model, then a provider. And hope they all play nicely together. Often they don't, and you get broken tool calls or subpar performance.
|
|
84
54
|
|
|
85
|
-
|
|
55
|
+
Magnitude bundles the harness, models, and provider into one stack that we continuously test and optimize. We benchmark model combinations to find the best setups, tune our harness to each model's quirks, and route only to providers serving them correctly and fast.
|
|
86
56
|
|
|
87
|
-
|
|
57
|
+
We know this isn't for everyone. Some people want the flexibility. Some people want to hack together their own setups. And we respect that. But we want to offer a path to using open models that just works. One that will stay on the frontier, without you having to do a thing.
|
|
88
58
|
|
|
89
|
-
##
|
|
59
|
+
## Acknowledgments
|
|
90
60
|
|
|
91
|
-
Built on top of [
|
|
61
|
+
Built on top of [Effect](https://effect.website) and [OpenTUI](https://github.com/anomalyco/opentui).
|
|
92
62
|
|
|
93
|
-
Inspired by other open
|
|
63
|
+
Inspired by other open source coding agents, including [OpenCode](https://github.com/anomalyco/opencode) and [Codex](https://github.com/openai/codex).
|