@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.
Files changed (2) hide show
  1. package/README.md +32 -47
  2. 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=232f41&color=gray" alt="Documentation" /></a> <img src="https://img.shields.io/badge/License-Apache%202.0-232f41?style=flat-square&labelColor=232f41&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>
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
- Open source coding agent where everything happens in specialized subagents. We call this *subagent driven development*. The main agent stays focused on your intent, leading to stronger performance on longer tasks and higher quality code.
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
- After installation, navigate to the directory you want to work in and launch the TUI:
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
- **Local models** Connect to Ollama or any OpenAI-compatible endpoint. No auth required.
40
+ You can use your **ChatGPT Plus/Pro** or **GitHub Copilot** subscription.
43
41
 
44
- See the [providers docs](https://docs.magnitude.dev/configuration/providers) for setup instructions. If you would like another provider to be supported, please feel free to create an issue or raise a PR yourself.
42
+ See the [provider docs](https://docs.magnitude.dev/configuration/providers) for full provider support.
45
43
 
46
- ## Why Magnitude?
44
+ ## How it works
47
45
 
48
- - **Avoids the dumb zone.** Since building happens in subagents, the main agent stays focused on your intent and effective even on longer, messier tasks.
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
- ## Features
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
- ### Main agent subagent architecture
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
- ### Two-way agent communication
61
- The main agent and subagents have full bidirectional messaging. The main agent can steer, redirect, or interrupt subagents mid-work. Subagents can message back when they hit blockers or need clarification. Not fire-and-forget delegation.
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
- ### Progressive disclosure of tool output
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
- ### Sensible default permissions
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
- ### Built-in browser agent
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
- ### Persistent memory
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
- ### Philosophy
72
+ ### Documentation
84
73
 
85
- The coding agent primitive is not solved. Most failures come from two recurring patterns: **context degradation** over long sessions, and **local maximum traps** where the agent settles for the nearest plausible fix. Magnitude is built around those failure modes. Read more in our [manifesto](https://magnitude.dev/manifesto).
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).
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@magnitudedev/cli",
3
- "version": "0.0.1-alpha.5",
3
+ "version": "0.0.1-alpha.6",
4
4
  "description": "Magnitude AI coding agent",
5
5
  "license": "Apache-2.0",
6
6
  "repository": {