DROPGoogle launches Gemini 3.8 Flash TTS and Flash-Lite TTS///DROPGemini Omni brings 1080p generation to Google Vids///BREAKClaude Opus 5.5 is here: 1M context, $4 input / $20 output///BREAKOpenAI adds GPT-6 Sol and Luna to the GPT-6 family///PAPEROpus 5.5's system card documents gains—and evaluation limits///BREAKGrok 4.7 launches at $2 input / $6 output per million tokens///DROPGrok Voice Transcribe 2.0 targets difficult real-world audio///TRENDGoogle steers new Gemini API projects to 3.8 Flash or 3.5 Flash-Lite///DROPGoogle launches Gemini 3.8 Flash TTS and Flash-Lite TTS///DROPGemini Omni brings 1080p generation to Google Vids///BREAKClaude Opus 5.5 is here: 1M context, $4 input / $20 output///BREAKOpenAI adds GPT-6 Sol and Luna to the GPT-6 family///PAPEROpus 5.5's system card documents gains—and evaluation limits///BREAKGrok 4.7 launches at $2 input / $6 output per million tokens///DROPGrok Voice Transcribe 2.0 targets difficult real-world audio///TRENDGoogle steers new Gemini API projects to 3.8 Flash or 3.5 Flash-Lite///
DARC.DEV

[ 07 — 4 learning paths · 24 available lessons ]

From curious to capable

Read something useful. Build or test something small. Keep the evidence. Four self-paced paths with real guides, practical exercises and saved progress—no video graveyard and no empty course promises.

[ Now reading / Open-source AI landscape ]

56 open-source AI agent projects, ranked

Explore OpenClaw, ECC, Hermes, Paperclip, Ruflo and 51 more projects. Verified GitHub star counts, category filters and an individual profile for every repository.

Explore ranking ↗

Read the guide, do the exercise, then mark the lesson complete. Progress is saved for this browser—not an account or cross-device sync.

Your reading list ↗
01Start here

AI Foundations

Build the mental models behind useful AI: tokens, context, sources, capability boundaries and a defensible model choice. Finish with a small evidence-backed comparison.

  • Explain context versus memory
  • Verify claims and citations
  • Choose models with a decision matrix
6 lessons · ~3h with exercisesLoading progress…
Start learning
02Developer

Build with LLMs

Turn model responses into reliable software. Build validation, retrieval, evaluations, observability and cost accounting around one small application.

  • Validate structured output
  • Measure retrieval and generation separately
  • Ship with tests, traces and a budget
6 lessons · ~4.2h with exercisesLoading progress…
Start learning
03Advanced

Agents & Automation

Build an inspectable agent and then give it durable state, scoped tools, human approval and enforceable spending limits. Learn where deterministic workflows are the better choice.

  • Bound agent actions and spend
  • Review MCP trust boundaries
  • Recover without duplicate side effects
6 lessons · ~4.7h with exercisesLoading progress…
Start learning
04Maker

AI Creator Studio

Use image, video and voice tools in a repeatable production workflow. Learn to control references, continuity, consent, asset provenance and publishable quality.

  • Create a testable visual brief
  • Evaluate voice and media outputs
  • Publish with rights and quality checks
6 lessons · ~3.5h with exercisesLoading progress…
Start learning