# TinyRustLM Full Agent Text > Full machine-readable site bundle for TinyRustLM plain PHP package 1.3.0. Full report bodies are linked from the report index rather than duplicated here. # TinyRustLM > TinyRustLM is a plain PHP project website explaining a zero-dependency Rust/WebAssembly browser-local small language model runtime built around custom .slm artifacts, strict validation, quantized execution, adapter sidecars, selector registries, deterministic test evidence, UAI file memory, durable reports, and a direct project contact route for Mike Kappel. ## Core Pages - [Overview](https://TinyRustLM.mirust.com/): Project summary, constraints, runtime surfaces, and deployment posture. - [Architecture](https://TinyRustLM.mirust.com/architecture/): System map covering the static browser UI, Rust/WASM runtime, offline packer, local server, harness, and claim boundaries. - [Runtime](https://TinyRustLM.mirust.com/runtime/): Rust/WASM runtime responsibilities, memory transfer, generation, diagnostics, and explicit error states. - [.slm Format](https://TinyRustLM.mirust.com/slm-format/): Custom model artifact contract for header, tensor directory, tokenizer metadata, quantization fields, and checksum validation. - [Quantization](https://TinyRustLM.mirust.com/quantization/): f32, q8_0, and q4_0 memory math under the 33,554,432-byte browser selector budget. - [Browser Runtime](https://TinyRustLM.mirust.com/browser-runtime/): Local browser app behavior, selector registry routing, local-only fetches, transcript state, and reset boundaries. - [Adapters](https://TinyRustLM.mirust.com/adapters/): ADP1, ASP1, and ALR1 adapter sidecars with Rust validation-before-apply. - [Model Breeding](https://TinyRustLM.mirust.com/model-breeding/): Offline candidate lineage, parent compatibility, operator receipts, manifests, runtime-smoke, eval evidence, and selector admission. - [Testing](https://TinyRustLM.mirust.com/testing/): Rust tests, browser harness checks, WASM ABI smoke, browser smoke modes, and performance soak. - [Roadmap](https://TinyRustLM.mirust.com/roadmap/): Proof-first expansion plan and explicit future boundaries. - [Glossary](https://TinyRustLM.mirust.com/glossary/): Definitions for .slm, q8_0, q4_0, ADP1, ASP1, ALR1, selector registry, and runtime-smoke. - [Docs + UAI Memory](https://TinyRustLM.mirust.com/docs/): Durable report archive, long-term memory body, report index, and .uai read order. - [Contact Mike Kappel](https://TinyRustLM.mirust.com/contact/): Direct project contact route with email, phone, portfolio, contact hub, LinkedIn, GitHub, and NuGet links. ## Durable Memory - [Long-term memory](https://TinyRustLM.mirust.com/docs/long-term-memory.md): Durable project memory body for current scope, public claim boundaries, report routing, and next recursive direction. - [Report index](https://TinyRustLM.mirust.com/docs/report-index.md): Preserved report manifest with source filenames, roles, byte counts, and checksums. - [.uai index](https://TinyRustLM.mirust.com/.uai/index.uai): Agent file-memory read order. - [.uai long-term pointer ledger](https://TinyRustLM.mirust.com/.uai/long-term-memory.uai): Pointer ledger deep-linking every report and durable memory target. ## Preserved Reports - [Engineering Tiny Language Models for Deterministic WebAssembly and Rust Runtimes](https://TinyRustLM.mirust.com/docs/reports/tiny-language-models-for-wasm.md): Core tiny-model feasibility, micro-model tiers, quantization constraints, deterministic WASM smoke testing, and Rust/WASM runtime pressure. - [Architecting Minimalist Neural Inference in WebAssembly](https://TinyRustLM.mirust.com/docs/reports/rust-wasm-neural-model-patterns.md): WASM heap planning, zero-copy tensor views, tokenizer data structures, SIMD matrix-vector kernels, and deterministic neural inference design. - [Architecture and Engineering of TinyRustLM](https://TinyRustLM.mirust.com/docs/reports/understanding-tinyrustlm-creation-and-purpose.md): Primary TinyRustLM explanation: browser-local runtime, .slm format, q8/q4 quantization, adapters, selector registries, and offline model breeding. - [Tiny Language Models for Rust/WASM](https://TinyRustLM.mirust.com/docs/reports/tiny-language-models-for-rust-wasm.md): Candidate model analysis, 33.5 MB budget math, Llama and GPT-NeoX topology notes, tokenizer constraints, and converter requirements. - [GGUF MiRust All Source Review Bundle](https://TinyRustLM.mirust.com/docs/reports/gguf-mirust-all-source-review-bundle.txt): Large source review bundle containing the TinyRustLM source inventory, hot .uai memory files, docs, runtime, packer, harness, and model-breeding artifacts. - [Memory Systems Domains Research](https://TinyRustLM.mirust.com/docs/reports/memory-systems-domains-research.md): Background research on AI memory domains, UAIX-style short-term handoff, long-term governed memory, and machine-readable knowledge routing. - [Future-Proof Native HTML5 Techniques](https://TinyRustLM.mirust.com/docs/reports/future-proof-native-html5-techniques.md): Native HTML5, semantic structure, progressive enhancement, declarative shadow DOM, popovers, dialogs, and accessible no-framework web patterns. - [Future-Proof JavaScript Without Dependencies](https://TinyRustLM.mirust.com/docs/reports/vanilla-js-future-proof-techniques.md): Native JavaScript standards, import maps, async control flow, reactive stores, navigation, view transitions, and security primitives. - [Innovative Vanilla Web Design](https://TinyRustLM.mirust.com/docs/reports/innovative-vanilla-web-design.md): Advanced vanilla design ideas, view transitions, Web Components, Houdini, WebGPU, Web Audio, and immersive zero-dependency interaction patterns. - [Agent-Native Vanilla Web Architecture](https://TinyRustLM.mirust.com/docs/reports/mememtech-vanilla-web-architecture.md): Agent-readable web architecture, semantic HTML, llms.txt, content negotiation, robots policy, and machine-readable site surfaces. - [Analyzing Website Virality](https://TinyRustLM.mirust.com/docs/reports/analyzing-website-virality.md): Sharing psychology, growth loops, friction reduction, dark social, interactive microsites, and resilient infrastructure for public project sites. ## Machine Formats - [Full text](https://TinyRustLM.mirust.com/llms-full.txt): Bundled Markdown content for agent readers. - [Sitemap](https://TinyRustLM.mirust.com/sitemap.xml): Canonical route list. - [Robots](https://TinyRustLM.mirust.com/robots.txt): Crawl policy. ## Boundaries - This is a plain PHP site, not WordPress. - Do not infer cloud inference or remote model execution. - Do not infer trained assistant quality from runtime-smoke claims. - Treat model and adapter licenses as artifact-specific. - The contact page is for project and professional routing, not an automated support system. --- # TinyRustLM Long-Term Memory > Durable project memory for TinyRustLM plain PHP site package 1.3.0. This file is the body memory target for `.uai/long-term-memory.uai`; the `.uai` file stays pointer-first and routes agents here for full context. ## Current truth boundary TinyRustLM is presented as a browser-local Rust/WebAssembly small language model runtime project, not as a cloud assistant, hosted chatbot, WordPress theme, generic Rust site, or GGUF runtime claim. The public site explains the current architecture and its proof surfaces: custom `.slm` artifacts, f32/q8_0/q4_0 quantization, deterministic validation, ADP1/ASP1/ALR1 adapter sidecars, selector registries, module-plan receipts, local-only browser diagnostics, and evidence-first model-breeding workflows. ## Site implementation memory - Current package version: `1.3.0`. - Site type: plain PHP 8, no WordPress, no database, no Composer, no npm. - Frontend: custom CSS and small vanilla JavaScript only. - Public routes: `/`, `/architecture/`, `/runtime/`, `/slm-format/`, `/quantization/`, `/browser-runtime/`, `/adapters/`, `/model-breeding/`, `/testing/`, `/roadmap/`, `/glossary/`, `/docs/`, and `/contact/`. - Machine routes: `/llms.txt`, `/llms-full.txt`, `/robots.txt`, `/sitemap.xml`, plus Markdown negotiation via `?format=md` or `Accept: text/markdown` on PHP-rendered pages. - Durable docs: `/docs/`, `/docs/report-index.md`, `/docs/long-term-memory.md`, and `/docs/reports/*`. ## Technical memory TinyRustLM should be described through concrete engineering surfaces: 1. **Runtime** — Rust owns `.slm` parsing, tokenizer behavior, tensor validation, quantization math, KV cache state, sampling, generation, diagnostics, error codes, adapter validation, and adapter application. 2. **Browser shell** — JavaScript owns local file fetches, manifest checks, byte transfer into WASM memory, controls, transcript rendering, and diagnostics display. It must not parse tensor payloads or make model-quality claims. 3. **Artifact format** — `.slm` is the custom local model artifact, with strict header, tensor directory, tokenizer metadata, quantization fields, dimension checks, checksums, and bounded runtime state. 4. **Memory envelope** — public copy should keep the 33,554,432-byte selector model budget visible because it explains vocabulary pressure, q8/q4 tradeoffs, scratch buffers, adapter stack limits, and browser viability. 5. **Adapters** — ADP1, ASP1, and ALR1 are validated sidecars. They are not replacement models and are not applied until Rust validates shape, identity, checksums, tokenizer agreement, tensor layout, and finite payload values. 6. **Model breeding** — model breeding is offline and receipt-bound. Operators can produce candidates, sparse/low-rank sidecars, and evidence records, but public assistant-quality claims require additional runtime-smoke and evaluation sidecars. ## Public copy boundaries - Do not claim trained assistant quality unless an evaluation sidecar with passed cases exists. - Do not claim GGUF import support as a TinyRustLM feature unless a specific conversion path and smoke evidence are added. - Do not describe the project as WordPress; this package is plain PHP. - Do not introduce Bootstrap, jQuery, Tailwind, React, Vue, Composer, npm, CDN dependencies, analytics, telemetry, remote inference APIs, or external model downloads by default. - Keep TinyRustLM centered on local agency, deterministic proof, inspectable artifacts, and constrained browser execution. ## Report memory index | Durable report | Source file | Type | SHA-256 | |---|---:|---|---| | [Engineering Tiny Language Models for Deterministic WebAssembly and Rust Runtimes](/docs/reports/tiny-language-models-for-wasm.md) | `Tiny Language Models for WASM.md` | report | `B823A12562F6DB288C6B16A38A6A9A8C6DD2AF8C02F783BBF34E3C54836FF6FB` | | [Architecting Minimalist Neural Inference in WebAssembly](/docs/reports/rust-wasm-neural-model-patterns.md) | `Rust WASM Neural Model Patterns.md` | report | `53E988FBCDD51A06A6155A8293CA85113543F20D9F78AF52EE50997B23E5F618` | | [Architecture and Engineering of TinyRustLM](/docs/reports/understanding-tinyrustlm-creation-and-purpose.md) | `Understanding TinyRustLM_ Creation and Purpose.md` | report | `69A94B184F4876B293EF268F22DF5DB63F1DFF5413AFEF03F7A9C6BAB397440D` | | [Tiny Language Models for Rust/WASM](/docs/reports/tiny-language-models-for-rust-wasm.md) | `Tiny Language Models for Rust_WASM.md` | report | `37D6B47ED4284F65C591921F653F3AA4E17672593AE84C09C84E4222FC808AE9` | | [GGUF MiRust All Source Review Bundle](/docs/reports/gguf-mirust-all-source-review-bundle.txt) | `GGUF_MiRust_All_Source_Review_Bundle(1).txt` | source-review-bundle | `2B2D72AC23F1D63919C0B744E9586C8AE73C45B26891E8F698DAD1417E8DE931` | | [Memory Systems Domains Research](/docs/reports/memory-systems-domains-research.md) | `Memory Systems Domains Research(2).md` | report | `B400312F9FEB5F5D5D2BF0C77B221B925B7AC091BC618E1B6964D38885D8C9B9` | | [Future-Proof Native HTML5 Techniques](/docs/reports/future-proof-native-html5-techniques.md) | `Future-Proof Native HTML5 Techniques(3).md` | report | `A152A89B4575DDB990DDB5300DAE0AC44BC424ABDED40C9ADB7CA87045461879` | | [Future-Proof JavaScript Without Dependencies](/docs/reports/vanilla-js-future-proof-techniques.md) | `Vanilla JS Future-Proof Techniques(3).md` | report | `5BCC36711C08D1072C857B01E025D7FFF946615349BDEEB340E70FA8677F92B3` | | [Innovative Vanilla Web Design](/docs/reports/innovative-vanilla-web-design.md) | `Innovative Vanilla Web Design(3).md` | report | `FE68269F39258FA1E3BFECB7F78C153F4CA24C0F08432D3F193F91087B12122C` | | [Agent-Native Vanilla Web Architecture](/docs/reports/mememtech-vanilla-web-architecture.md) | `Mememtech Vanilla Web Architecture(3).md` | report | `4E3ACAA0D568C201C56E8F74E0016004743D04E553B9AEC8E83152E0F8B4E47A` | | [Analyzing Website Virality](/docs/reports/analyzing-website-virality.md) | `Analyzing Website Virality(3).md` | report | `5CDB3C8C9FA714AF0C44B48EC58B3C885846D5C8D7B1E5DDE869442B83DA95EF` | ## Next recursive direction Continue by improving the docs surface and public evidence flow without widening claims. Good next work: add a public support matrix, add code snippets that mirror current source behavior, add downloadable checksums for source evidence, add a `/docs/proof/` page, and keep `.uai/long-term-memory.uai` synchronized whenever reports or source boundaries change. --- # TinyRustLM Report Index > Durable report map for TinyRustLM plain PHP site package 1.3.0. Every source report copied into `/docs/reports/` is listed with a source filename, durable route, role, byte count, and checksum. | Report | Source filename | Role | Bytes | SHA-256 | |---|---|---|---:|---| | [Engineering Tiny Language Models for Deterministic WebAssembly and Rust Runtimes](/docs/reports/tiny-language-models-for-wasm.md) | `Tiny Language Models for WASM.md` | Core tiny-model feasibility, micro-model tiers, quantization constraints, deterministic WASM smoke testing, and Rust/WASM runtime pressure. | 46105 | `B823A12562F6DB288C6B16A38A6A9A8C6DD2AF8C02F783BBF34E3C54836FF6FB` | | [Architecting Minimalist Neural Inference in WebAssembly](/docs/reports/rust-wasm-neural-model-patterns.md) | `Rust WASM Neural Model Patterns.md` | WASM heap planning, zero-copy tensor views, tokenizer data structures, SIMD matrix-vector kernels, and deterministic neural inference design. | 69793 | `53E988FBCDD51A06A6155A8293CA85113543F20D9F78AF52EE50997B23E5F618` | | [Architecture and Engineering of TinyRustLM](/docs/reports/understanding-tinyrustlm-creation-and-purpose.md) | `Understanding TinyRustLM_ Creation and Purpose.md` | Primary TinyRustLM explanation: browser-local runtime, .slm format, q8/q4 quantization, adapters, selector registries, and offline model breeding. | 31890 | `69A94B184F4876B293EF268F22DF5DB63F1DFF5413AFEF03F7A9C6BAB397440D` | | [Tiny Language Models for Rust/WASM](/docs/reports/tiny-language-models-for-rust-wasm.md) | `Tiny Language Models for Rust_WASM.md` | Candidate model analysis, 33.5 MB budget math, Llama and GPT-NeoX topology notes, tokenizer constraints, and converter requirements. | 44102 | `37D6B47ED4284F65C591921F653F3AA4E17672593AE84C09C84E4222FC808AE9` | | [GGUF MiRust All Source Review Bundle](/docs/reports/gguf-mirust-all-source-review-bundle.txt) | `GGUF_MiRust_All_Source_Review_Bundle(1).txt` | Large source review bundle containing the TinyRustLM source inventory, hot .uai memory files, docs, runtime, packer, harness, and model-breeding artifacts. | 4922808 | `2B2D72AC23F1D63919C0B744E9586C8AE73C45B26891E8F698DAD1417E8DE931` | | [Memory Systems Domains Research](/docs/reports/memory-systems-domains-research.md) | `Memory Systems Domains Research(2).md` | Background research on AI memory domains, UAIX-style short-term handoff, long-term governed memory, and machine-readable knowledge routing. | 39530 | `B400312F9FEB5F5D5D2BF0C77B221B925B7AC091BC618E1B6964D38885D8C9B9` | | [Future-Proof Native HTML5 Techniques](/docs/reports/future-proof-native-html5-techniques.md) | `Future-Proof Native HTML5 Techniques(3).md` | Native HTML5, semantic structure, progressive enhancement, declarative shadow DOM, popovers, dialogs, and accessible no-framework web patterns. | 53751 | `A152A89B4575DDB990DDB5300DAE0AC44BC424ABDED40C9ADB7CA87045461879` | | [Future-Proof JavaScript Without Dependencies](/docs/reports/vanilla-js-future-proof-techniques.md) | `Vanilla JS Future-Proof Techniques(3).md` | Native JavaScript standards, import maps, async control flow, reactive stores, navigation, view transitions, and security primitives. | 47621 | `5BCC36711C08D1072C857B01E025D7FFF946615349BDEEB340E70FA8677F92B3` | | [Innovative Vanilla Web Design](/docs/reports/innovative-vanilla-web-design.md) | `Innovative Vanilla Web Design(3).md` | Advanced vanilla design ideas, view transitions, Web Components, Houdini, WebGPU, Web Audio, and immersive zero-dependency interaction patterns. | 47461 | `FE68269F39258FA1E3BFECB7F78C153F4CA24C0F08432D3F193F91087B12122C` | | [Agent-Native Vanilla Web Architecture](/docs/reports/mememtech-vanilla-web-architecture.md) | `Mememtech Vanilla Web Architecture(3).md` | Agent-readable web architecture, semantic HTML, llms.txt, content negotiation, robots policy, and machine-readable site surfaces. | 42941 | `4E3ACAA0D568C201C56E8F74E0016004743D04E553B9AEC8E83152E0F8B4E47A` | | [Analyzing Website Virality](/docs/reports/analyzing-website-virality.md) | `Analyzing Website Virality(3).md` | Sharing psychology, growth loops, friction reduction, dark social, interactive microsites, and resilient infrastructure for public project sites. | 62253 | `5CDB3C8C9FA714AF0C44B48EC58B3C885846D5C8D7B1E5DDE869442B83DA95EF` | ## Related durable memory - [Long-term memory](/docs/long-term-memory.md): Durable body memory for project state, boundaries, report routing, and next recursive direction. SHA-256: `E930670CE12380A29218ADE238D3E3CCD1B9E0949C1FC9365BA075ED30060E45` - [.uai long-term pointer ledger](../.uai/long-term-memory.uai): Pointer-first memory ledger that deep-links to this report index and every preserved report. - [.uai file handoff](../.uai/file-handoff.uai): Active intake and disposition rules for future report drops.