Curated Open-Source AI Repositories

“My terminal baseline for vibe coding 2.0 — I benchmark every harness (98.4% infra paper) against Codex to keep token hunger honest.”

“OpenBot governs an agent via AG-UI — I run LangGraph, Mastra or ADK bots as coworkers with separate computers, audit after decision before action.”

“I use it to unify security tooling across agents — one skill pack replaces per-agent glue for RE, pentest and CTF; the routing + memory design is why it topped GitHub Trending Aug 1 over openwork and chatwoot. Rating: 4.6/5. When NOT to use: Avoid on production customer data — it is built for authorized lab/CTF scopes, not for compliance-bound pen-tests without isolated VPC.”

“I curate it over generic agent lists because it gives you a real org chart — frontend, community, reality-checker — each pre-prompted for Claude/Cursor/Codex. The 143k-star flip past semantica on Aug 12 proves the persona model stuck. Rating: 4.8/5. When NOT to use: Not for single-agent loops — overhead is real until you actually run a team-of-agents with shared MCP state.”

“Unlike toy skill demos, Addy’s pack is production-grade — installable via skills CLI into Claude/Cursor with tests. That is why it held steady #4 on Aug 12 while paperclip and orca churned. Rating: 4.7/5. When NOT to use: Not if you want pure prompt tricks — these are opinionated engineering workflows with guardrails, not one-liner hacks.”

“It is the first ASF-incubating agent workspace to nail local-first: append-only log of model messages/tool calls, one Runtime Host for Desktop/TUI/eval. +1,978 stars last week and +3,848 total proves teams want recoverable execution facts, not just chat. Rating: 4.7/5. When NOT to use: Skip if you need cloud multi-tenant now — Maka is macOS-first, Windows unsigned preview, no Linux yet, incubation WIP.”

“After skills went viral (218k+ stars for skills repo), Anthropic shipped the official marketplace — immutable slugs, renames map, strict skill-bundle plugins. 35.3k stars + 3,438 commits is the canonical registry I wire in Curro. Rating: 4.9/5. When NOT to use: Not for non-Claude harnesses — it is Claude Code plugin directory; wire via MCP if you need cross-harness.”

“Most skill packs are coding-centric; this one targets science workflows — hypothesis, experiment, paper — which is where Gujarat research SMEs actually need agents. Trending #2 on GitHub today alongside archify proves niche skills are winning. Rating: 4.4/5. When NOT to use: Avoid if you only need web-dev personas — scientific skills add overhead without bench tasks.”

“I run agent swarms for Gujarat SMEs — OpenMAIC showed me how to orchestrate 30+ classroom agents with shared memory and turn-taking. Its MIT classroom loop is the cleanest multi-agent handoff I have seen for education + meeting simulation.”

“I repurpose journal → video → podcast — notebooklm-py gives my n8n workflow direct NotebookLM source ingestion and audio overview generation without browser clicks. Its skill wrapper is how I auto-test MCP handshakes.”

“I run SEO & AEO Services where Google AI Overviews need cited answers — marketingskills gave my Claude Code an AEO checklist that maps to FAQPage + JSON-LD I ship for Gujarat SMEs. Its CRO/SEO skills turn my journal posts into 120% more clicks when cited.”

“I orchestrate autonomous swarms with Supervisor + Pydantic + HITL — deer-flow showed me how ByteDance layers sandboxes + memories + message gateway so one harness runs research→code→create for hours without token blowout. Its pattern informs my OPA+HITL gate before ₹15K Razorpay.”

“I curate awesome-claude-skills alongside Codex — openai/skills is the canonical catalog that standardizes skill installation for Codex the way MCP does for tools. Its catalog format is what I now validate against before publishing any of my 41 skills.”

“I run Pydantic + OmniRoute pipelines where 22% thinking calls eat token budgets — headroom compresses tool output 60-95% before it hits the LLM, the same quota discipline I enforce from Junagadh on Pi 5 62 tok/s. Its compress-before-LLM rail is the pre-filter I bolt in front of my 90-day OTel ledger.”

“I red-team every MCP server with JWT + OPA + HITL before it touches Razorpay — pentagi automates that adversarial loop as a swarm instead of a checklist. Its autonomous pentest pattern is the pre-deploy gate I am adding to my Junagadh ship pipeline for Gujarat fintech clients.”

“I built Curro as an AI content studio that writes like its owner — openhuman pushes the same idea further with local-first life memory plus fleet orchestration in Rust. Its memory-of-your-life architecture is the direction I am taking Curro for Junagadh founders who refuse cloud journals.”