Nunna Consulting GroupNunna Rao: SalesChai Nunna: AIAI Library
Collection

Research notes

Free-text findings from past research batches. 64 items.

Top 15

Ordered by verdict, then GitHub stars.

agentFramework note 1

Filter: orchestration stays in n8n, routing in LiteLLM, state in Supabase, building in Claude Code. A framework must do something that stack cannot.

agentFramework

agentFramework note 2

dspy is the standout: the golden set + accuracy guard give it a pass/fail metric to optimize local Qwen prompts against.

agentFramework

agentFramework note 3

e2b gives generated code a disposable sandbox instead of running beside Sierra Chart or next to keys on the laptop.

agentFramework

agentFramework note 4

Speech-to-text is a genuine gap: local Whisper on the RTX 4060 first, Deepgram as the paid fallback; feeds ESP32-S3 recorder audio and consulting call transcripts.

agentFramework

agentFramework note 6

Risk: crewai, autogen and langchain each want to own orchestration; running one alongside n8n means two drifting descriptions of the same workflow.

agentFramework

agentSkill note 1

The post's '776K combined stars' claim is not supported: humanizer 31.5k and napkin 575 verified on GitHub 2026-09-17; the other 18 links were truncated and are unverified.

agentSkill

agentSkill note 2

Skills add procedure; MCP servers add tools. Our stack is tool-heavy and procedure-light.

agentSkill

agentSkill note 3

Install safety: read SKILL.md fully, install per-project, pin a commit, never load unvetted skills in a session holding Supabase service keys or API keys, review diffs before updating.

agentSkill

agentSkill note 4

Humanizer improves style but does not remove KDP/Etsy duties to disclose AI-generated content.

agentSkill

agentSkill note 5

Adoption order: napkin, humanizer -> ffmpeg-skill, video-shotcraft -> graphify, tech-debt-audit -> claude-seo, scroll-world, user-research.

agentSkill

agentToolkit note 1

Verified 2026-09-17: obra/superpowers ships via Anthropic's official plugin marketplace; steveyegge/beads is a git-backed issue tracker for agents. The other 38 were not individually verified.

agentToolkit

agentToolkit note 2

Adopt order: superpowers, beads, serena, repomix, planning-with-files, karpathy-skills, codex-plugin-cc, taste-skill, addyosmani skills, mattpocock skills, claude-hud, rtk.

agentToolkit

agentToolkit note 3

Risk: headroom/rtk/caveman compress context or output; the accuracy guard rejects numbers missing from source, so never use them on the daily data pipeline or publishing paths.

agentToolkit

agentToolkit note 4

Risk: terse-output tools strip disclaimers required for finance, health-adjacent and gambling content.

agentToolkit

Ask your assistant instead

Connect the MCP and ask Claude to search this collection for you.