@christianirack/create-brainllm 0.8.2 → 0.8.4

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 +31 -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/v0.8.2/docs/site/assets/logo.png" width="88" alt="BRAINLLM brain mark"></p>
13
+ <p align="center"><img src="https://raw.githubusercontent.com/chrisifm/BRAINLLM/v0.8.4/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/v0.8.2/LICENSE"><img src="https://img.shields.io/github/license/chrisifm/BRAINLLM" alt="License"></a>
28
+ <a href="https://github.com/chrisifm/BRAINLLM/blob/v0.8.4/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/v0.8.2/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/v0.8.4/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
 
@@ -61,14 +61,14 @@ the baseline here:
61
61
  - **Real-time evidence while developing.** Compiler feedback, impact per save (diagnostics and bytes per view),
62
62
  runtime errors mapped to `.brain` lines, memory and leak inspection, over CLI and MCP.
63
63
 
64
- **[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/v0.8.2/SPEC.md)** · **[See the benchmarks](#show-me-the-numbers)** · **[Contribute](#build-the-tool-your-agent-needs)**
64
+ **[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/v0.8.4/SPEC.md)** · **[See the benchmarks](#show-me-the-numbers)** · **[Contribute](#build-the-tool-your-agent-needs)**
65
65
 
66
66
  ## A frontend language with the model in mind
67
67
 
68
68
  An agent writing your app needs a contract it can follow and feedback it can act on. BRAINLLM makes that loop
69
69
  explicit: read the spec, generate a component, check it, apply the fix, test the result.
70
70
 
71
- ![An agent reads the BRAINLLM contract, writes a component and uses compiler feedback to validate the app](https://github.com/chrisifm/BRAINLLM/raw/v0.8.2/docs/site/assets/agent-loop.png)
71
+ ![An agent reads the BRAINLLM contract, writes a component and uses compiler feedback to validate the app](https://github.com/chrisifm/BRAINLLM/raw/v0.8.4/docs/site/assets/agent-loop.png)
72
72
 
73
73
  - **Less to guess.** `brain spec` defines the supported language. One component format, a prescribed project
74
74
  structure and generators keep the model working inside a known contract.
@@ -96,7 +96,7 @@ agent has to reconstruct while preserving code that a developer can read and rev
96
96
  | Verification and delivery | Tests, `brain doctor` and the production build make validation part of the workflow |
97
97
  | Tested compiler improvements | Isolated proposals, validation gates and optional review-branch pushes let the agent contribute fixes |
98
98
 
99
- Use [SPEC.md](https://github.com/chrisifm/BRAINLLM/blob/v0.8.2/SPEC.md), the served `brain spec` and [EVOLUTION.md](https://github.com/chrisifm/BRAINLLM/blob/v0.8.2/docs/EVOLUTION.md) for exact contracts and limits.
99
+ Use [SPEC.md](https://github.com/chrisifm/BRAINLLM/blob/v0.8.4/SPEC.md), the served `brain spec` and [EVOLUTION.md](https://github.com/chrisifm/BRAINLLM/blob/v0.8.4/docs/EVOLUTION.md) for exact contracts and limits.
100
100
 
101
101
  ## Where it fits in the frontend stack
102
102
 
@@ -155,8 +155,8 @@ stack. Builds run serially on a shared machine. Variance matters: inspect the ra
155
155
  The output strategies differ (including SSR, client rendering and an Astro React island); this comparison measures
156
156
  production build duration for this fixture, not universal app performance or feature equivalence.
157
157
 
158
- Read the [expanded method, versions, payloads and results](https://github.com/chrisifm/BRAINLLM/blob/v0.8.2/bench/build/expanded.md). The original three-stack
159
- [historical results](https://github.com/chrisifm/BRAINLLM/blob/v0.8.2/bench/build/results/summary.md) remain available unchanged. Use `bench/build/expanded.mjs`
158
+ Read the [expanded method, versions, payloads and results](https://github.com/chrisifm/BRAINLLM/blob/v0.8.4/bench/build/expanded.md). The original three-stack
159
+ [historical results](https://github.com/chrisifm/BRAINLLM/blob/v0.8.4/bench/build/results/summary.md) remain available unchanged. Use `bench/build/expanded.mjs`
160
160
  with the documented frozen binary and scratch-directory setup to reproduce this seven-stack run.
161
161
 
162
162
  **Ask your agent to challenge the result:**
@@ -179,11 +179,11 @@ numbers support it. Do not upload results or publish anything automatically.
179
179
  Clean up only the temporary resources this run created.
180
180
  ```
181
181
 
182
- A separate [cache-key microbenchmark](https://github.com/chrisifm/BRAINLLM/blob/v0.8.2/bench/build/results/compiler-cache-lookup.json) measured **43.3× faster key
182
+ A separate [cache-key microbenchmark](https://github.com/chrisifm/BRAINLLM/blob/v0.8.4/bench/build/results/compiler-cache-lookup.json) measured **43.3× faster key
183
183
  lookup** after removing an unnecessary parse: 10,000 lookups of a 1,050-byte input. That number measures this
184
184
  internal operation only. It is not a full-build speedup or a webpack comparison.
185
185
 
186
- The [benchmark report](https://github.com/chrisifm/BRAINLLM/blob/v0.8.2/bench/REPORT.md) also tracks agent-generated apps, browser behavior, payload size and
186
+ The [benchmark report](https://github.com/chrisifm/BRAINLLM/blob/v0.8.4/bench/REPORT.md) also tracks agent-generated apps, browser behavior, payload size and
187
187
  failure recovery. Historical LLM results describe their frozen model/spec/compiler runs; they do not guarantee
188
188
  that a new prompt or compiler revision will pass. This project is open to developers and researchers who want to
189
189
  investigate how language design and compiler feedback affect agent behavior. Bring a hypothesis and a reproducer.
@@ -207,7 +207,7 @@ what each result actually establishes.
207
207
 
208
208
  Browser tooling and the preview supervisor currently require macOS or Linux. Screenshot baselines need stable browser,
209
209
  font and app-data inputs. Runtime mount-time/heap budgets remain planned; the compiler rejects those settings rather
210
- than pretending to measure them. See the [implemented contract](https://github.com/chrisifm/BRAINLLM/blob/v0.8.2/SPEC.md) and [tool internals](https://github.com/chrisifm/BRAINLLM/blob/v0.8.2/docs/INTERNALS.md).
210
+ than pretending to measure them. See the [implemented contract](https://github.com/chrisifm/BRAINLLM/blob/v0.8.4/SPEC.md) and [tool internals](https://github.com/chrisifm/BRAINLLM/blob/v0.8.4/docs/INTERNALS.md).
211
211
 
212
212
  ## Give your agent its first task
213
213
 
@@ -301,11 +301,11 @@ For an existing app, run `brain agent setup` to merge local registrations, or
301
301
  The hook checks the app after `.brain`, `.jsbrain` and `.cssbrain` edits; it does not run tests or download packages.
302
302
  Use `brain mcp --profile minimal` for six core tools, or `--profile backend` for resource/job contracts and generators.
303
303
  With a source installation, change the registration to command `brain` and arguments `["mcp"]`.
304
- Other clients use their own MCP settings. See [the backend/agent contract](https://github.com/chrisifm/BRAINLLM/blob/v0.8.2/docs/BACKEND.md).
304
+ Other clients use their own MCP settings. See [the backend/agent contract](https://github.com/chrisifm/BRAINLLM/blob/v0.8.4/docs/BACKEND.md).
305
305
 
306
306
  </details>
307
307
 
308
- For an existing frontend, start with the [migration workflow](https://github.com/chrisifm/BRAINLLM/blob/v0.8.2/docs/MIGRATION.md). Its read-only planner recognizes
308
+ For an existing frontend, start with the [migration workflow](https://github.com/chrisifm/BRAINLLM/blob/v0.8.4/docs/MIGRATION.md). Its read-only planner recognizes
309
309
  React, Angular, Vue, Svelte, Next and Nuxt projects. Port one tested route or component at a time, preserve its
310
310
  behavior and keep a rollback path. It is an incremental workflow, not an automatic transpiler.
311
311
 
@@ -323,7 +323,7 @@ behavior and keep a rollback path. It is an incremental workflow, not an automat
323
323
  ```
324
324
 
325
325
  The compiler handles signal reads and writes. Derived values update when their inputs change. Styles can live in
326
- the same file and are scoped to the component. The [served spec](https://github.com/chrisifm/BRAINLLM/blob/v0.8.2/SPEC.md) defines the supported syntax.
326
+ the same file and are scoped to the component. The [served spec](https://github.com/chrisifm/BRAINLLM/blob/v0.8.4/SPEC.md) defines the supported syntax.
327
327
 
328
328
  ## Readable intent. Lean browser output.
329
329
 
@@ -331,7 +331,7 @@ An internal function named `back_to_home` can become a short identifier in produ
331
331
  on scope and the other names in the module. Keep meaningful names where the agent reasons about the code; let the
332
332
  compiler shorten eligible bindings in what the browser receives.
333
333
 
334
- This example comes from the [minifier's scope regression tests](https://github.com/chrisifm/BRAINLLM/blob/v0.8.2/crates/brain-min/src/mangle.rs):
334
+ This example comes from the [minifier's scope regression tests](https://github.com/chrisifm/BRAINLLM/blob/v0.8.4/crates/brain-min/src/mangle.rs):
335
335
 
336
336
  ```js
337
337
  // Before
@@ -366,29 +366,29 @@ BRAINLLM includes protections at several stages of the app loop:
366
366
  tests and diagnostics; failed stages remain visible to the agent.
367
367
 
368
368
  These are implemented mechanisms, not a promise to catch every bug or repair every failure. The agent still needs
369
- to test the user's workflow. See [runtime behavior in the spec](https://github.com/chrisifm/BRAINLLM/blob/v0.8.2/SPEC.md#errors-at-runtime),
370
- [component boundaries](https://github.com/chrisifm/BRAINLLM/blob/v0.8.2/runtime/brain-guard.js) and [compiler diagnostics](https://github.com/chrisifm/BRAINLLM/blob/v0.8.2/crates/brain-check/).
369
+ to test the user's workflow. See [runtime behavior in the spec](https://github.com/chrisifm/BRAINLLM/blob/v0.8.4/SPEC.md#errors-at-runtime),
370
+ [component boundaries](https://github.com/chrisifm/BRAINLLM/blob/v0.8.4/runtime/brain-guard.js) and [compiler diagnostics](https://github.com/chrisifm/BRAINLLM/blob/v0.8.4/crates/brain-check/).
371
371
 
372
372
  ## Build the tool your agent needs
373
373
 
374
374
  **Build with it. Let your LLM make it better.**
375
375
 
376
- ![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/v0.8.2/docs/site/assets/improvement-loop.png)
376
+ ![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/v0.8.4/docs/site/assets/improvement-loop.png)
377
377
 
378
378
  A failed compilation can become a regression test. A repeated slow step can become a benchmark. A fix made while
379
379
  building your app can become a contribution that helps the next developer and their agent.
380
380
 
381
381
  Found a compiler gap while building an app? Turn the smallest reproducible case into a regression test and a
382
- contribution. BRAINLLM includes an [evolution workflow](https://github.com/chrisifm/BRAINLLM/blob/v0.8.2/docs/EVOLUTION.md) for isolated proposals, validated compiler
382
+ contribution. BRAINLLM includes an [evolution workflow](https://github.com/chrisifm/BRAINLLM/blob/v0.8.4/docs/EVOLUTION.md) for isolated proposals, validated compiler
383
383
  binaries and reversible activation. Configured automatic pushes go to review branches; merges require the
384
384
  principal author's review. This is an explicit development workflow, not a compiler that silently rewrites itself
385
- on every build. Read the [agent improvement playbook](https://github.com/chrisifm/BRAINLLM/blob/v0.8.2/docs/AGENT-IDEAS.md) for an opt-in prompt and concrete ideas
385
+ on every build. Read the [agent improvement playbook](https://github.com/chrisifm/BRAINLLM/blob/v0.8.4/docs/AGENT-IDEAS.md) for an opt-in prompt and concrete ideas
386
386
  to investigate.
387
387
 
388
388
  Human developers and LLM contributors are welcome. Useful first contributions include reproducible compiler bugs,
389
389
  behavior-preserving migration examples, clearer diagnostics and performance improvements with before/after data.
390
390
 
391
- 1. Read [CONTRIBUTING.md](https://github.com/chrisifm/BRAINLLM/blob/v0.8.2/CONTRIBUTING.md) and the relevant [internals](https://github.com/chrisifm/BRAINLLM/blob/v0.8.2/docs/INTERNALS.md).
391
+ 1. Read [CONTRIBUTING.md](https://github.com/chrisifm/BRAINLLM/blob/v0.8.4/CONTRIBUTING.md) and the relevant [internals](https://github.com/chrisifm/BRAINLLM/blob/v0.8.4/docs/INTERNALS.md).
392
392
  2. Make a focused change with a regression test and synthetic sample data.
393
393
  3. Run `bash scripts/verify.sh`. It builds the CLI and checks Rust, runtime, tooling, diagnostic fixtures, privacy
394
394
  and repository language. Verification also requires ripgrep.
@@ -399,7 +399,7 @@ Never include app secrets, private source or customer data in a contribution.
399
399
 
400
400
  ## Know what you are adopting
401
401
 
402
- BRAINLLM is **0.8.2** (see [CHANGELOG.md](https://github.com/chrisifm/BRAINLLM/blob/v0.8.2/CHANGELOG.md)). Start with a small app or an isolated route and test the behavior you need. Features marked
402
+ BRAINLLM is **0.8.4** (see [CHANGELOG.md](https://github.com/chrisifm/BRAINLLM/blob/v0.8.4/CHANGELOG.md)). Start with a small app or an isolated route and test the behavior you need. Features marked
403
403
  as planned in the source specification are not a supported promise; `brain spec` serves the implemented contract.
404
404
  Third-party React, Angular and Vue components do not become BRAINLLM components automatically. Benchmark wins in
405
405
  build time do not imply that every runtime workload is faster.
@@ -408,15 +408,15 @@ build time do not imply that every runtime workload is faster.
408
408
 
409
409
  | You want to… | Start here |
410
410
  |---|---|
411
- | Give an agent the project context | [llms.txt](https://github.com/chrisifm/BRAINLLM/blob/v0.8.2/llms.txt) |
412
- | Write an app | [SPEC.md](https://github.com/chrisifm/BRAINLLM/blob/v0.8.2/SPEC.md) and `brain spec` |
413
- | Migrate an existing frontend | [Migration guide](https://github.com/chrisifm/BRAINLLM/blob/v0.8.2/docs/MIGRATION.md) |
414
- | Improve the compiler while using it | [Evolution workflow](https://github.com/chrisifm/BRAINLLM/blob/v0.8.2/docs/EVOLUTION.md) and [agent ideas](https://github.com/chrisifm/BRAINLLM/blob/v0.8.2/docs/AGENT-IDEAS.md) |
415
- | Understand the implementation | [Internals](https://github.com/chrisifm/BRAINLLM/blob/v0.8.2/docs/INTERNALS.md) and [crates](https://github.com/chrisifm/BRAINLLM/blob/v0.8.2/crates/) |
416
- | Inspect examples and reproduce measurements | [Examples](https://github.com/chrisifm/BRAINLLM/blob/v0.8.2/examples/) and [benchmarks](https://github.com/chrisifm/BRAINLLM/blob/v0.8.2/bench/) |
417
- | Contribute a change | [Contributor guide](https://github.com/chrisifm/BRAINLLM/blob/v0.8.2/CONTRIBUTING.md) |
411
+ | Give an agent the project context | [llms.txt](https://github.com/chrisifm/BRAINLLM/blob/v0.8.4/llms.txt) |
412
+ | Write an app | [SPEC.md](https://github.com/chrisifm/BRAINLLM/blob/v0.8.4/SPEC.md) and `brain spec` |
413
+ | Migrate an existing frontend | [Migration guide](https://github.com/chrisifm/BRAINLLM/blob/v0.8.4/docs/MIGRATION.md) |
414
+ | Improve the compiler while using it | [Evolution workflow](https://github.com/chrisifm/BRAINLLM/blob/v0.8.4/docs/EVOLUTION.md) and [agent ideas](https://github.com/chrisifm/BRAINLLM/blob/v0.8.4/docs/AGENT-IDEAS.md) |
415
+ | Understand the implementation | [Internals](https://github.com/chrisifm/BRAINLLM/blob/v0.8.4/docs/INTERNALS.md) and [crates](https://github.com/chrisifm/BRAINLLM/blob/v0.8.4/crates/) |
416
+ | Inspect examples and reproduce measurements | [Examples](https://github.com/chrisifm/BRAINLLM/blob/v0.8.4/examples/) and [benchmarks](https://github.com/chrisifm/BRAINLLM/blob/v0.8.4/bench/) |
417
+ | Contribute a change | [Contributor guide](https://github.com/chrisifm/BRAINLLM/blob/v0.8.4/CONTRIBUTING.md) |
418
418
 
419
- Released under the [MIT license](https://github.com/chrisifm/BRAINLLM/blob/v0.8.2/LICENSE).
419
+ Released under the [MIT license](https://github.com/chrisifm/BRAINLLM/blob/v0.8.4/LICENSE).
420
420
 
421
421
  Created and maintained by **Christian Irack Flores Maldonado**, principal author.
422
422
  [ingenieria.dev](https://ingenieria.dev) · [irack.mx](https://irack.mx) · [christian@irack.mx](mailto:christian@irack.mx)
@@ -428,5 +428,5 @@ Every merged contribution helps the next developer and their agent. Thank you to
428
428
 
429
429
  [<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)
430
430
 
431
- Attribution is refreshed through a reviewed pull request. [How it works](https://github.com/chrisifm/BRAINLLM/blob/v0.8.2/docs/CONTRIBUTORS.md).
431
+ Attribution is refreshed through a reviewed pull request. [How it works](https://github.com/chrisifm/BRAINLLM/blob/v0.8.4/docs/CONTRIBUTORS.md).
432
432
  <!-- contributors:end -->
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@christianirack/create-brainllm",
3
- "version": "0.8.2",
3
+ "version": "0.8.4",
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": "0.8.2"
17
+ "@christianirack/brainllm": "0.8.4"
18
18
  },
19
19
  "keywords": [
20
20
  "create",