@christianirack/create-brainllm 0.5.0 → 0.6.1

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 +47 -31
  2. package/package.json +2 -2
package/README.md CHANGED
@@ -10,7 +10,7 @@ npm run dev
10
10
 
11
11
  Runs the same pinned BRAINLLM compiler and installs the generated app dependencies. Pass `-- --no-install` to skip dependency installation.
12
12
 
13
- <p align="center"><img src="https://raw.githubusercontent.com/chrisifm/BRAINLLM/v0.5.0/docs/site/assets/logo.png" width="88" alt="BRAINLLM brain mark"></p>
13
+ <p align="center"><img src="https://raw.githubusercontent.com/chrisifm/BRAINLLM/v0.6.1/docs/site/assets/logo.png" width="88" alt="BRAINLLM brain mark"></p>
14
14
 
15
15
  # BRAINLLM
16
16
 
@@ -25,10 +25,10 @@ Runs the same pinned BRAINLLM compiler and installs the generated app dependenci
25
25
  <img src="https://img.shields.io/badge/built%20with-Rust-dea584?logo=rust&logoColor=white" alt="Built with Rust">
26
26
  <a href="https://chrisifm.github.io/BRAINLLM/"><img src="https://img.shields.io/badge/website-chrisifm.github.io%2FBRAINLLM-0071e3" alt="Website"></a>
27
27
  <a href="https://www.npmjs.com/package/@christianirack/brainllm"><img src="https://img.shields.io/npm/v/@christianirack/brainllm?color=cb3837" alt="npm version"></a>
28
- <a href="https://github.com/chrisifm/BRAINLLM/blob/v0.5.0/LICENSE"><img src="https://img.shields.io/github/license/chrisifm/BRAINLLM" alt="License"></a>
28
+ <a href="https://github.com/chrisifm/BRAINLLM/blob/v0.6.1/LICENSE"><img src="https://img.shields.io/github/license/chrisifm/BRAINLLM" alt="License"></a>
29
29
  </p>
30
30
 
31
- <p align="center"><a href="https://chrisifm.github.io/BRAINLLM/"><img src="https://raw.githubusercontent.com/chrisifm/BRAINLLM/v0.5.0/docs/site/assets/cover.png" alt="BRAINLLM — The web compiler for LLMs. Open the website: chrisifm.github.io/BRAINLLM"></a></p>
31
+ <p align="center"><a href="https://chrisifm.github.io/BRAINLLM/"><img src="https://raw.githubusercontent.com/chrisifm/BRAINLLM/v0.6.1/docs/site/assets/cover.png" alt="BRAINLLM — The web compiler for LLMs. Open the website: chrisifm.github.io/BRAINLLM"></a></p>
32
32
 
33
33
  <p align="center"><b>🌐 <a href="https://chrisifm.github.io/BRAINLLM/">chrisifm.github.io/BRAINLLM</a></b></p>
34
34
 
@@ -43,14 +43,30 @@ code generation, bundling and minification. The agent can operate it through the
43
43
  a confusing diagnostic. The agent can turn that finding into a tested proposal and, when configured, push it
44
44
  automatically to a review branch. Maintainers decide what merges.
45
45
 
46
- **[Visit the site](https://chrisifm.github.io/BRAINLLM/)** · **[Build your first app](#give-your-agent-its-first-task)** · **[Read the spec](https://github.com/chrisifm/BRAINLLM/blob/v0.5.0/SPEC.md)** · **[See the benchmarks](#show-me-the-numbers)** · **[Contribute](#build-the-tool-your-agent-needs)**
46
+ ## Built for agents that change code safely
47
+
48
+ BRAINLLM is not another React, Next or Node. It is a compiler whose first user is an LLM, and it is designed to
49
+ improve itself: when an agent hits a compiler gap, `scripts/evolve.mjs` turns it into an isolated, tested proposal
50
+ for human review. The tools other stacks sell as advanced analysis are the baseline here:
51
+
52
+ - **Locate without reading.** `brain map`, `brain card`, `brain graph`, `brain context` and symbol search give an
53
+ agent the contract and the exact location of what it must touch, never a 2,000-line file.
54
+ - **Measured risk before every edit.** `brain risk <target>` returns a deterministic score, the factors behind it
55
+ (dependents, routes, public contracts, backend schema, covering tests, SEO/i18n/a11y, budget headroom) and the
56
+ checks that will prove the edit safe.
57
+ - **Atomic changes.** Leased, revision-checked changesets validate the whole app on a private snapshot before
58
+ writing and recover cleanly; a stale revision is rejected instead of overwriting another agent's work.
59
+ - **Real-time evidence while developing.** Compiler feedback, impact per save (diagnostics and bytes per view),
60
+ runtime errors mapped to `.brain` lines, memory and leak inspection, over CLI and MCP.
61
+
62
+ **[Visit the site](https://chrisifm.github.io/BRAINLLM/)** · **[Build your first app](#give-your-agent-its-first-task)** · **[Read the spec](https://github.com/chrisifm/BRAINLLM/blob/v0.6.1/SPEC.md)** · **[See the benchmarks](#show-me-the-numbers)** · **[Contribute](#build-the-tool-your-agent-needs)**
47
63
 
48
64
  ## A frontend language with the model in mind
49
65
 
50
66
  An agent writing your app needs a contract it can follow and feedback it can act on. BRAINLLM makes that loop
51
67
  explicit: read the spec, generate a component, check it, apply the fix, test the result.
52
68
 
53
- ![An agent reads the BRAINLLM contract, writes a component and uses compiler feedback to validate the app](https://github.com/chrisifm/BRAINLLM/raw/v0.5.0/docs/site/assets/agent-loop.png)
69
+ ![An agent reads the BRAINLLM contract, writes a component and uses compiler feedback to validate the app](https://github.com/chrisifm/BRAINLLM/raw/v0.6.1/docs/site/assets/agent-loop.png)
54
70
 
55
71
  - **Less to guess.** `brain spec` defines the supported language. One component format, a prescribed project
56
72
  structure and generators keep the model working inside a known contract.
@@ -78,7 +94,7 @@ agent has to reconstruct while preserving code that a developer can read and rev
78
94
  | Verification and delivery | Tests, `brain doctor` and the production build make validation part of the workflow |
79
95
  | Tested compiler improvements | Isolated proposals, validation gates and optional review-branch pushes let the agent contribute fixes |
80
96
 
81
- Use [SPEC.md](https://github.com/chrisifm/BRAINLLM/blob/v0.5.0/SPEC.md), the served `brain spec` and [EVOLUTION.md](https://github.com/chrisifm/BRAINLLM/blob/v0.5.0/docs/EVOLUTION.md) for exact contracts and limits.
97
+ Use [SPEC.md](https://github.com/chrisifm/BRAINLLM/blob/v0.6.1/SPEC.md), the served `brain spec` and [EVOLUTION.md](https://github.com/chrisifm/BRAINLLM/blob/v0.6.1/docs/EVOLUTION.md) for exact contracts and limits.
82
98
 
83
99
  ## Where it fits in the frontend stack
84
100
 
@@ -137,8 +153,8 @@ stack. Builds run serially on a shared machine. Variance matters: inspect the ra
137
153
  The output strategies differ (including SSR, client rendering and an Astro React island); this comparison measures
138
154
  production build duration for this fixture, not universal app performance or feature equivalence.
139
155
 
140
- Read the [expanded method, versions, payloads and results](https://github.com/chrisifm/BRAINLLM/blob/v0.5.0/bench/build/expanded.md). The original three-stack
141
- [historical results](https://github.com/chrisifm/BRAINLLM/blob/v0.5.0/bench/build/results/summary.md) remain available unchanged. Use `bench/build/expanded.mjs`
156
+ Read the [expanded method, versions, payloads and results](https://github.com/chrisifm/BRAINLLM/blob/v0.6.1/bench/build/expanded.md). The original three-stack
157
+ [historical results](https://github.com/chrisifm/BRAINLLM/blob/v0.6.1/bench/build/results/summary.md) remain available unchanged. Use `bench/build/expanded.mjs`
142
158
  with the documented frozen binary and scratch-directory setup to reproduce this seven-stack run.
143
159
 
144
160
  **Ask your agent to challenge the result:**
@@ -161,11 +177,11 @@ numbers support it. Do not upload results or publish anything automatically.
161
177
  Clean up only the temporary resources this run created.
162
178
  ```
163
179
 
164
- A separate [cache-key microbenchmark](https://github.com/chrisifm/BRAINLLM/blob/v0.5.0/bench/build/results/compiler-cache-lookup.json) measured **43.3× faster key
180
+ A separate [cache-key microbenchmark](https://github.com/chrisifm/BRAINLLM/blob/v0.6.1/bench/build/results/compiler-cache-lookup.json) measured **43.3× faster key
165
181
  lookup** after removing an unnecessary parse: 10,000 lookups of a 1,050-byte input. That number measures this
166
182
  internal operation only. It is not a full-build speedup or a webpack comparison.
167
183
 
168
- The [benchmark report](https://github.com/chrisifm/BRAINLLM/blob/v0.5.0/bench/REPORT.md) also tracks agent-generated apps, browser behavior, payload size and
184
+ The [benchmark report](https://github.com/chrisifm/BRAINLLM/blob/v0.6.1/bench/REPORT.md) also tracks agent-generated apps, browser behavior, payload size and
169
185
  failure recovery. Historical LLM results describe their frozen model/spec/compiler runs; they do not guarantee
170
186
  that a new prompt or compiler revision will pass. This project is open to developers and researchers who want to
171
187
  investigate how language design and compiler feedback affect agent behavior. Bring a hypothesis and a reproducer.
@@ -189,7 +205,7 @@ what each result actually establishes.
189
205
 
190
206
  Browser tooling and the preview supervisor currently require macOS or Linux. Screenshot baselines need stable browser,
191
207
  font and app-data inputs. Runtime mount-time/heap budgets remain planned; the compiler rejects those settings rather
192
- than pretending to measure them. See the [implemented contract](https://github.com/chrisifm/BRAINLLM/blob/v0.5.0/SPEC.md) and [tool internals](https://github.com/chrisifm/BRAINLLM/blob/v0.5.0/docs/INTERNALS.md).
208
+ than pretending to measure them. See the [implemented contract](https://github.com/chrisifm/BRAINLLM/blob/v0.6.1/SPEC.md) and [tool internals](https://github.com/chrisifm/BRAINLLM/blob/v0.6.1/docs/INTERNALS.md).
193
209
 
194
210
  ## Give your agent its first task
195
211
 
@@ -283,11 +299,11 @@ For an existing app, run `brain agent setup` to merge local registrations, or
283
299
  The hook checks the app after `.brain`, `.jsbrain` and `.cssbrain` edits; it does not run tests or download packages.
284
300
  Use `brain mcp --profile minimal` for six core tools, or `--profile backend` for resource/job contracts and generators.
285
301
  With a source installation, change the registration to command `brain` and arguments `["mcp"]`.
286
- Other clients use their own MCP settings. See [the backend/agent contract](https://github.com/chrisifm/BRAINLLM/blob/v0.5.0/docs/BACKEND.md).
302
+ Other clients use their own MCP settings. See [the backend/agent contract](https://github.com/chrisifm/BRAINLLM/blob/v0.6.1/docs/BACKEND.md).
287
303
 
288
304
  </details>
289
305
 
290
- For an existing frontend, start with the [migration workflow](https://github.com/chrisifm/BRAINLLM/blob/v0.5.0/docs/MIGRATION.md). Its read-only planner recognizes
306
+ For an existing frontend, start with the [migration workflow](https://github.com/chrisifm/BRAINLLM/blob/v0.6.1/docs/MIGRATION.md). Its read-only planner recognizes
291
307
  React, Angular, Vue, Svelte, Next and Nuxt projects. Port one tested route or component at a time, preserve its
292
308
  behavior and keep a rollback path. It is an incremental workflow, not an automatic transpiler.
293
309
 
@@ -305,7 +321,7 @@ behavior and keep a rollback path. It is an incremental workflow, not an automat
305
321
  ```
306
322
 
307
323
  The compiler handles signal reads and writes. Derived values update when their inputs change. Styles can live in
308
- the same file and are scoped to the component. The [served spec](https://github.com/chrisifm/BRAINLLM/blob/v0.5.0/SPEC.md) defines the supported syntax.
324
+ the same file and are scoped to the component. The [served spec](https://github.com/chrisifm/BRAINLLM/blob/v0.6.1/SPEC.md) defines the supported syntax.
309
325
 
310
326
  ## Readable intent. Lean browser output.
311
327
 
@@ -313,7 +329,7 @@ An internal function named `back_to_home` can become a short identifier in produ
313
329
  on scope and the other names in the module. Keep meaningful names where the agent reasons about the code; let the
314
330
  compiler shorten eligible bindings in what the browser receives.
315
331
 
316
- This example comes from the [minifier's scope regression tests](https://github.com/chrisifm/BRAINLLM/blob/v0.5.0/crates/brain-min/src/mangle.rs):
332
+ This example comes from the [minifier's scope regression tests](https://github.com/chrisifm/BRAINLLM/blob/v0.6.1/crates/brain-min/src/mangle.rs):
317
333
 
318
334
  ```js
319
335
  // Before
@@ -348,29 +364,29 @@ BRAINLLM includes protections at several stages of the app loop:
348
364
  tests and diagnostics; failed stages remain visible to the agent.
349
365
 
350
366
  These are implemented mechanisms, not a promise to catch every bug or repair every failure. The agent still needs
351
- to test the user's workflow. See [runtime behavior in the spec](https://github.com/chrisifm/BRAINLLM/blob/v0.5.0/SPEC.md#errors-at-runtime),
352
- [component boundaries](https://github.com/chrisifm/BRAINLLM/blob/v0.5.0/runtime/brain-guard.js) and [compiler diagnostics](https://github.com/chrisifm/BRAINLLM/blob/v0.5.0/crates/brain-check/).
367
+ to test the user's workflow. See [runtime behavior in the spec](https://github.com/chrisifm/BRAINLLM/blob/v0.6.1/SPEC.md#errors-at-runtime),
368
+ [component boundaries](https://github.com/chrisifm/BRAINLLM/blob/v0.6.1/runtime/brain-guard.js) and [compiler diagnostics](https://github.com/chrisifm/BRAINLLM/blob/v0.6.1/crates/brain-check/).
353
369
 
354
370
  ## Build the tool your agent needs
355
371
 
356
372
  **Build with it. Let your LLM make it better.**
357
373
 
358
- ![An LLM turns an observed problem into an isolated fix, runs validation and submits a contribution for human review](https://github.com/chrisifm/BRAINLLM/raw/v0.5.0/docs/site/assets/improvement-loop.png)
374
+ ![An LLM turns an observed problem into an isolated fix, runs validation and submits a contribution for human review](https://github.com/chrisifm/BRAINLLM/raw/v0.6.1/docs/site/assets/improvement-loop.png)
359
375
 
360
376
  A failed compilation can become a regression test. A repeated slow step can become a benchmark. A fix made while
361
377
  building your app can become a contribution that helps the next developer and their agent.
362
378
 
363
379
  Found a compiler gap while building an app? Turn the smallest reproducible case into a regression test and a
364
- contribution. BRAINLLM includes an [evolution workflow](https://github.com/chrisifm/BRAINLLM/blob/v0.5.0/docs/EVOLUTION.md) for isolated proposals, validated compiler
380
+ contribution. BRAINLLM includes an [evolution workflow](https://github.com/chrisifm/BRAINLLM/blob/v0.6.1/docs/EVOLUTION.md) for isolated proposals, validated compiler
365
381
  binaries and reversible activation. Configured automatic pushes go to review branches; merges require the
366
382
  principal author's review. This is an explicit development workflow, not a compiler that silently rewrites itself
367
- on every build. Read the [agent improvement playbook](https://github.com/chrisifm/BRAINLLM/blob/v0.5.0/docs/AGENT-IDEAS.md) for an opt-in prompt and concrete ideas
383
+ on every build. Read the [agent improvement playbook](https://github.com/chrisifm/BRAINLLM/blob/v0.6.1/docs/AGENT-IDEAS.md) for an opt-in prompt and concrete ideas
368
384
  to investigate.
369
385
 
370
386
  Human developers and LLM contributors are welcome. Useful first contributions include reproducible compiler bugs,
371
387
  behavior-preserving migration examples, clearer diagnostics and performance improvements with before/after data.
372
388
 
373
- 1. Read [CONTRIBUTING.md](https://github.com/chrisifm/BRAINLLM/blob/v0.5.0/CONTRIBUTING.md) and the relevant [internals](https://github.com/chrisifm/BRAINLLM/blob/v0.5.0/docs/INTERNALS.md).
389
+ 1. Read [CONTRIBUTING.md](https://github.com/chrisifm/BRAINLLM/blob/v0.6.1/CONTRIBUTING.md) and the relevant [internals](https://github.com/chrisifm/BRAINLLM/blob/v0.6.1/docs/INTERNALS.md).
374
390
  2. Make a focused change with a regression test and synthetic sample data.
375
391
  3. Run `bash scripts/verify.sh`. It builds the CLI and checks Rust, runtime, tooling, diagnostic fixtures, privacy
376
392
  and repository language. Verification also requires ripgrep.
@@ -381,7 +397,7 @@ Never include app secrets, private source or customer data in a contribution.
381
397
 
382
398
  ## Know what you are adopting
383
399
 
384
- BRAINLLM is **0.5.0** (see [CHANGELOG.md](https://github.com/chrisifm/BRAINLLM/blob/v0.5.0/CHANGELOG.md)). Start with a small app or an isolated route and test the behavior you need. Features marked
400
+ BRAINLLM is **0.6.1** (see [CHANGELOG.md](https://github.com/chrisifm/BRAINLLM/blob/v0.6.1/CHANGELOG.md)). Start with a small app or an isolated route and test the behavior you need. Features marked
385
401
  as planned in the source specification are not a supported promise; `brain spec` serves the implemented contract.
386
402
  Third-party React, Angular and Vue components do not become BRAINLLM components automatically. Benchmark wins in
387
403
  build time do not imply that every runtime workload is faster.
@@ -390,15 +406,15 @@ build time do not imply that every runtime workload is faster.
390
406
 
391
407
  | You want to… | Start here |
392
408
  |---|---|
393
- | Give an agent the project context | [llms.txt](https://github.com/chrisifm/BRAINLLM/blob/v0.5.0/llms.txt) |
394
- | Write an app | [SPEC.md](https://github.com/chrisifm/BRAINLLM/blob/v0.5.0/SPEC.md) and `brain spec` |
395
- | Migrate an existing frontend | [Migration guide](https://github.com/chrisifm/BRAINLLM/blob/v0.5.0/docs/MIGRATION.md) |
396
- | Improve the compiler while using it | [Evolution workflow](https://github.com/chrisifm/BRAINLLM/blob/v0.5.0/docs/EVOLUTION.md) and [agent ideas](https://github.com/chrisifm/BRAINLLM/blob/v0.5.0/docs/AGENT-IDEAS.md) |
397
- | Understand the implementation | [Internals](https://github.com/chrisifm/BRAINLLM/blob/v0.5.0/docs/INTERNALS.md) and [crates](https://github.com/chrisifm/BRAINLLM/blob/v0.5.0/crates/) |
398
- | Inspect examples and reproduce measurements | [Examples](https://github.com/chrisifm/BRAINLLM/blob/v0.5.0/examples/) and [benchmarks](https://github.com/chrisifm/BRAINLLM/blob/v0.5.0/bench/) |
399
- | Contribute a change | [Contributor guide](https://github.com/chrisifm/BRAINLLM/blob/v0.5.0/CONTRIBUTING.md) |
409
+ | Give an agent the project context | [llms.txt](https://github.com/chrisifm/BRAINLLM/blob/v0.6.1/llms.txt) |
410
+ | Write an app | [SPEC.md](https://github.com/chrisifm/BRAINLLM/blob/v0.6.1/SPEC.md) and `brain spec` |
411
+ | Migrate an existing frontend | [Migration guide](https://github.com/chrisifm/BRAINLLM/blob/v0.6.1/docs/MIGRATION.md) |
412
+ | Improve the compiler while using it | [Evolution workflow](https://github.com/chrisifm/BRAINLLM/blob/v0.6.1/docs/EVOLUTION.md) and [agent ideas](https://github.com/chrisifm/BRAINLLM/blob/v0.6.1/docs/AGENT-IDEAS.md) |
413
+ | Understand the implementation | [Internals](https://github.com/chrisifm/BRAINLLM/blob/v0.6.1/docs/INTERNALS.md) and [crates](https://github.com/chrisifm/BRAINLLM/blob/v0.6.1/crates/) |
414
+ | Inspect examples and reproduce measurements | [Examples](https://github.com/chrisifm/BRAINLLM/blob/v0.6.1/examples/) and [benchmarks](https://github.com/chrisifm/BRAINLLM/blob/v0.6.1/bench/) |
415
+ | Contribute a change | [Contributor guide](https://github.com/chrisifm/BRAINLLM/blob/v0.6.1/CONTRIBUTING.md) |
400
416
 
401
- Released under the [MIT license](https://github.com/chrisifm/BRAINLLM/blob/v0.5.0/LICENSE).
417
+ Released under the [MIT license](https://github.com/chrisifm/BRAINLLM/blob/v0.6.1/LICENSE).
402
418
 
403
419
  Created and maintained by **Christian Irack Flores Maldonado**, principal author.
404
420
  [ingenieria.dev](https://ingenieria.dev) · [irack.mx](https://irack.mx) · [christian@irack.mx](mailto:christian@irack.mx)
@@ -410,5 +426,5 @@ Every merged contribution helps the next developer and their agent. Thank you to
410
426
 
411
427
  [<img src="https://avatars.githubusercontent.com/u/1562002?v=4" width="48" height="48" alt="chrisifm">](https://github.com/chrisifm) [chrisifm](https://github.com/chrisifm)
412
428
 
413
- Attribution is refreshed through a reviewed pull request. [How it works](https://github.com/chrisifm/BRAINLLM/blob/v0.5.0/docs/CONTRIBUTORS.md).
429
+ Attribution is refreshed through a reviewed pull request. [How it works](https://github.com/chrisifm/BRAINLLM/blob/v0.6.1/docs/CONTRIBUTORS.md).
414
430
  <!-- contributors:end -->
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@christianirack/create-brainllm",
3
- "version": "0.5.0",
3
+ "version": "0.6.1",
4
4
  "description": "npm create @christianirack/brainllm <app>: a new BRAINLLM app (the Rust-powered full-stack web compiler for LLMs and AI agents) with its brain version pinned.",
5
5
  "bin": {
6
6
  "create-brainllm": "bin/create.js"
@@ -14,7 +14,7 @@
14
14
  "node": ">=22"
15
15
  },
16
16
  "dependencies": {
17
- "@christianirack/brainllm": "0.5.0"
17
+ "@christianirack/brainllm": "0.6.1"
18
18
  },
19
19
  "keywords": [
20
20
  "create",