Curated Open-Source AI Repositories

“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 WhatsApp-first vernacular voice agents (Hindi/Gujarati) for Gujarat SMEs — VoiceStudio gave me a local-first TTS stack that runs 62 tok/s on Pi 5 without cloud latency. Its voice-cloning pipeline mirrors my HITL ledger: generate → OPA gate → human approve before irreversible Razorpay.”

“I publish 30 journal posts/month via Curro where Google AI Overviews cites extractable Indian sources — humanizer taught me how detector evasion fails EEAT. I use its style-transfer eval to harden my own audit-blog.mjs anti-fluff check before publishing from Junagadh.”

“I build map-pack + AI citation stacks for Gujarat local SEO — gods-eye-view showed me how to fuse satellite tiles with pgvector HNSW 42ms for hyperlocal context. Its JS dashboard is the geo layer I bolt onto my Junagadh → Gujarat → India 4-tier ranking.”

“I audit MCP skills where 26% request broad permissions per SkillSpector — obscura gives my Junagadh ledger a Rust path to test obfuscation before OPA denies. Its deobfuscation flow is the pre-flight I run before any HITL-gated shell tool.”

“I ship archify-style verifiable diagrams as self-contained HTML for Gujarat SME blueprints — diagram-design is the HTML gallery that replaced my Mermaid snapshots. Its HTML+SVG export is how I keep 90-day ledger diagrams auditable without image drift.”

“I forecast Gujarat SME demand (textile seasonality, UPI retry windows) — TimesFM lets me do zero-shot forecasting on Pi 5 without training, fitting my offline-first 78% on-device rule. Its foundation model beats ARIMA when my Junagadh data has gaps.”

“I ship from Junagadh on a ₹6K VPS where dotfiles drift kills P95 — omarchy gave me a deterministic Hyprland + hooks setup I containerize for Pi 5. Its opinionated Arch is the dev env I snapshot before n8n + MCP deploys.”

“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 serve Next.js + Laravel from one FastMCP gateway where codebase context costs 42 min of agent exploration — codebase-memory-mcp replaces that with a traced knowledge graph in milliseconds. Its single static binary with zero deps is the deploy shape I ship on ₹6K VPS.”

“I built Curro to write in my own voice — career-ops applies the same local-first agent harness to job search, scoring listings with a structured rubric instead of cloud SaaS. Its runs-in-your-CLI design is the pattern I recommend to Junagadh devs who distrust cloud resume tools.”

“I split memory (MemPalace), RAG (pgvector HNSW 42ms) and skills (catalog) across three systems — OpenViking unifies all three into one self-evolving store. Its memory+RAG+skills convergence is the architecture I am migrating my Junagadh ledger toward for Gujarat SME agents.”

“I run 70B offline on laptop and Pi 5 at 62 tok/s where every dependency is a failure point — colibri streams MoE experts from disk in pure C with zero deps, the same no-dependency discipline I enforce on ₹6K VPS deploys. Its run-on-hardware-you-own shape is exactly how I keep 78% of Gujarat SME calls inside the VPC.”

“I run autonomous QA swarms that cut production bugs 87% where pure-LLM review hallucinates approvals — open-code-review pairs deterministic rules (NPE, XSS, SQLi) with an LLM agent for judgment calls, the same two-gate pattern in my CI/CD harness. Its line-level precision is what I demand before any agent touches a Surat client repo.”

“I write system prompts for governed agents where one leaked instruction pattern teaches more than ten tutorials — this repo shows exactly how frontier labs structure tool-use, HITL, and refusal rails. I study these prompts from Junagadh to harden my own Pydantic + OPA harnesses against the same injection classes.”