Repository lifecycle: Active → Maintained → Experimental/Incubating → Archived. Component repos stay separate only when independent versioning, reuse, access control, CI, or deployment boundaries justify it. See PORTFOLIO.md.

• agentic-vault — agent-agnostic knowledge infrastructure for Obsidian, including graph-aware retrieval, provenance, and multi-agent governance
• agentic-analytics — MCP-native analytical runtime with reproducible execution and evidence provenance
• Agent infrastructure (agent-*) — host-neutral, independently usable layers for running AI agents under real constraints: agent-relay (roles, handoffs, verification), agent-router (cost-aware model and executor routing), agent-control (lifecycle, budgets, policy, audit), and agent-toolchain (distribution across harnesses, in progress)
• litert-lm-plugin-cc — local/on-device LiteRT-LM integration for Claude Code
• DIMER model pipelines — model integrations for the DIMER platform spanning tabular, vision, vision-language, time-series, audio, and language tasks, each pinning one immutable model revision, verifying weight checksums before load, and shipping machine-readable provenance with every result

• market-study-template — a scaffold for structured market research studies: a Quarto book rendering to PDF/DOCX, a TypeScript survey instrument, and pre-specified analysis contracts so the output tables exist before any data is collected
• citation-audit — audits a finished reference list against the bibliographic record, catching fabricated, misattributed, and misdirected citations — including identifiers that resolve cleanly to an entirely different paper. Keyless; the calls that change what a document claims stay with the human
• agentic-research — 23-skill PRISMA 2020 / GRADE systematic-review pipeline: a question → a defensible synthesis
• agentic-analytics — an agent-agnostic, MCP-native analytical runtime: reproducible sandboxed execution with source→execution→evidence provenance and deterministic validation, so an agent's analysis can be re-run and checked instead of taken on trust

• keynote-builder — a governed, human-gated pipeline that turns a brief into a stage-ready keynote (slide deck + speaker script)
• office-reports — agent skills for institutional document drafting: travel reports, minutes, and a weekly → terminal M&E reporting pipeline, evidence-only with gap flags
• presentation-builder — composable skills for finished presentations: Marp, native PPTX, HTML slides, talk scripts
• research-deck-builder — a research/training module → a presenter-ready, source-checked deck
• agentic-vault — an Obsidian vault template for working with AI agents (PARA + multi-agent governance)

• ai-readiness-assessment — an AI-readiness assessment chatbot for Philippine government agencies & NGOs

• litert-lm-plugin-cc — an unofficial Claude Code plugin for a local, on-device model served by LiteRT-LM: offline, no API tokens, nothing leaving the machine — and a metadata repair for the silent CPU fallback that costs a measured 4.3×
• mlops-lite — a full-lifecycle, single-GPU MLOps platform (data → train → serve → monitor → retrain)
• DIMER model pipelines — model integrations for the DIMER platform, all built to one contract: a pinned immutable model revision, checksum-verified weights, validation before inference, machine-readable provenance on every result, and a model card recording intended use, out-of-scope use, and decision thresholds. Each repository publishes its own release status; most sit at candidate/source-complete pending recorded clean-runtime evidence
  • Tabular — Mitra, TabICL, TabPFN, TabDPT classifier/regressor pairs
  • Vision — Swin classification, detection, and segmentation; SAM 2 and SAM ViT promptable segmentation; Grounding DINO zero-shot detection; Depth Anything V2; DINOv2 features; Swin2SR super-resolution; and ViT / EVA02 / ConvNeXt / ResNet-50 / MobileNetV4 classifiers
  • Vision-language — SigLIP 2, Florence-2, SmolVLM
  • Time series — Chronos-2 and TiRex / Toto forecasting; MOMENT embeddings, imputation, and anomaly scoring
  • Audio and multimodal — Whisper ASR, AST audio classification, Kokoro TTS, and Phi-4 multimodal
  • Language — LoRA/QLoRA fine-tuning contracts for compatible causal LMs, GLiNER NER, Qwen3 embedding and reranking, plus BERT / GPT-2 / T5 baselines
  • Text tasks — extractive question answering over SQuAD2, table question answering over WikiTableQuestions, abstractive summarization, zero-shot classification via NLI entailment, and English→Tagalog translation

• Agent infrastructure (agent-*) — four independently usable layers for running AI agents under real constraints: agent-relay hands work between agents through durable artifacts and a verifier gate; agent-router routes each subtask to the cheapest executor that can satisfy it, then escalates on failed verification; agent-control owns lifecycle, budgets, policy, and an append-only audit trail; agent-toolchain (in progress) installs and validates all of it across harnesses
• pdf-signer-pwa — private, offline PKCS#12 PDF signing that never leaves your device