- refresh.sh: idempotent script, auto-discovers repos, updates symlinks + copies docs/workflows
- launchd plist: scheduled daily at 11 PM + on login
- /refresh-chat-history workflow for on-demand Cascade runs
- README updated with auto-refresh docs and full data inventory
- Repo docs and workflows refreshed from all 4 repos
Add a helper script to quickly verify Ollama reachability across localhost, WSL gateway, and nameserver paths to speed up Windows+WSL troubleshooting.
Co-authored-by: Cursor <cursoragent@cursor.com>
Stabilize Windows+WSL setup by fixing script line-ending pitfalls, WSL Ollama host detection, and dashboard startup behavior so models are detected reliably in Mission Control.
Co-authored-by: Cursor <cursoragent@cursor.com>
Covers: what it is, architecture diagram, prerequisites (Python 3.12,
Bun, Rust), step-by-step install for macOS and WSL2, running backend
+ web frontend, first use (model download, voice profiles, story editor),
Make commands reference, platform performance table, troubleshooting
(proxy workaround, MPS/CUDA, transformers conflict), file structure,
and relevance to LysnrAI
- HP Z240 spec: expanded from 7-line raw info to full spec document
with hardware details, capabilities assessment, OpenClaw server
use case, home lab services table, GPU upgrade path, machine
comparison, and setup recommendations
- README: added Machines table (Razer/HP Z240/Dell P16s), expanded
files table, added Related: OpenClaw section with links to OPEN_CLAW/
- Move openclaw-personal-ai-assistant.md from windows_specific/ to OPEN_CLAW/
- Add validate-security.sh: cross-platform security scanner with visual output
- 7 check categories: installation, gateway config, file permissions,
network security, API keys, system security, openclaw doctor
- Green ticks (pass), red crosses (fail), yellow warnings
- Numbered recommendations list with fix commands
- Works on macOS, Linux, and WSL2
Covers: what it is, installation on Windows/WSL2 and macOS, channels,
models, configuration, security, HP Z240 as always-on gateway host,
Tailscale remote access, troubleshooting, CLI reference, and skills.
New capabilities/ subfolder with detailed guides:
- 01: GPU inference speed (benchmarks, Ollama tuning, API usage)
- 02: Whisper batch transcription (scripts, Python integration, use cases)
- 03: TTS generation at scale (Orpheus + Qwen3, batch scripts, voice cloning)
- 04: Fine-tuning / training (LoRA, QLoRA, data prep, Ollama export)
- 05: CUDA / TensorRT / ML research (toolchain setup, Triton kernels, profiling)
- 06: Stable Diffusion / image gen (ComfyUI, SDXL, FLUX, batch generation)
- 07: Multi-GPU workloads (scaling path, eGPU, cloud, cost planning)
- README: index with learning order and prerequisites
Each guide covers: what it is, how to use it, benefits, skills to learn
E1: Per-message action bar (copy, regenerate dropdown, rating) on hover
E2: Per-code-block copy button in MarkdownResponse with 'Copied!' feedback
E3: 'Try with other model' — regenerate dropdown shows loaded models
E4: Live streaming metrics (token count + tok/s during stream)
E5: Rating (thumbs up/down) persisted per message in IndexedDB
- add lib/router.ts with task classifier, model hint mapping, resolve fallback chain, and auto-detect defaults
- integrate auto-routing mode in conversation model selector with __auto__ option
- persist/read model defaults from localStorage (llm-model-defaults)
- route prompts to selected/routed model before streaming
- add multi-modal input controls (attach file, image, voice)
- support attachment chips, removal, drag-and-drop file attach
- add audio transcription flow via /api/whisper/transcribe and append result to input
- support sending attachments payload alongside text from InputBar
- add idb dependency and create typed db layer (conversations/messages/agents/etc)
- extend app/lib/types.ts with v4 workspace interfaces
- move existing dashboard to /mission-control route group
- create / workspace route group with sidebar shell and conversation pages
- implement conversation list grouping + search in sidebar
- implement conversation view with streaming via /api/ollama/chat
- add context bar and token/context utilities
- add /api/ollama/title endpoint for auto-title generation
- add v3->v4 migration utility (llm-inference-log + llm-chat-* to indexeddb)
- wire migration in workspace layout and cmd+/ sidebar toggle
Implements roadmap Phase A tasks A1-A8.
F29: Export/import settings — gear icon in header opens settings popover,
export downloads all llm-* localStorage as JSON, import validates
and merges, both with toast feedback
F30: Inference history log — saves prompt/response/model/metrics to
llm-inference-log (capped 100 FIFO), searchable panel with replay
button, count badge in header toggle
F31: Factory reset — confirm dialog clears all llm-* localStorage keys,
resets all component state to defaults
F24: Vision image upload — file picker for vision models, base64 encoding,
passed through stream API to Ollama generate endpoint
F25: Markdown rendering — ReactMarkdown replaces raw <pre> for all
prompt responses and chat assistant messages
F26: Syntax highlighting — Prism-based code blocks with language labels
and oneDark theme via react-syntax-highlighter
F27: <think> block collapse — auto-detect and collapse DeepSeek R1
reasoning traces into expandable details with word count
F28: Ollama library link — button next to Pull input opens ollama.com/library
N11: Persist tok/s per model to localStorage (llm-model-benchmarks),
display on model card as faded accent text
N12: Live countdown to auto-unload — 1s interval, color-coded
(green >5m, yellow 1-5m, red <1m 'Unloading soon')
N13: Session stats per model (prompts + tokens) in expanded details
N14: Co-load suggestions strip below models list showing which
unloaded models fit in remaining free memory
N6: <think> warning badge for DeepSeek R1 and distilled variants
N7: Vision model indicator for llava, bakllava, moondream, qwen-vl, etc.
N8: Architecture/family badge as pill on every model card
N9: Sort dropdown (A-Z, size, params, running, recent) with localStorage persist
N10: Ollama server version fetched from /api/version, shown in stats card
N1: Estimated RAM per model with quant-aware multipliers (Q4=1.2x, Q5=1.25x, Q8=1.1x, F16=1.05x)
N2: Will-it-fit indicator (green/yellow/red dot) next to Load button
N3: Aggregate loaded model VRAM in panel header badge
BN1: Compare buttons now filter to running models only
BN2: AbortController on compare stream, cancel on modal close
BN5: Delete confirmation shows model name + disk reclaim size
- Created DASHBOARD_PRD.md — full updated PRD with current 19-file
architecture, all 10 API routes, UI layout, data flow, localStorage
keys, security model, and v1-v3 changelog.
- Created DASHBOARD_ROADMAP.md — phased implementation plan for N1-N15
improvements across 4 phases: pre-load intelligence, rich metadata,
model intelligence badges, runtime metrics. Includes acceptance
criteria and implementation details per item.
- Updated DASHBOARD_REVIEW.md — refreshed file inventory to 19 files
(~2,930 lines), fixed broken Tier B markdown table, added cross-links.
- Replaced __LOCAL_LLMs/docs/05-mission-control-dashboard.md with
redirect pointer to new dashboard/docs/ location.
Dashboard docs are now co-located at __LOCAL_LLMs/dashboard/docs/:
- DASHBOARD_PRD.md (product requirements)
- DASHBOARD_REVIEW.md (audit + 39 completed items + N1-N15 proposals)
- DASHBOARD_ROADMAP.md (phased implementation plan)
