Curated Open-Source AI Repositories

“The definitive gold standard for how LLM agents interact with local databases, system tools, and APIs cleanly without messy custom glue code.”

“The MCP POSIX — I scaffold every Surat/Rajkot tool server with FastMCP because the Python SDK already ships it. One decorator, one schema, one gateway. When NOT to use: If you need TypeScript MCP, pair with the TS SDK — FastMCP is Python-centric.”

“My default GitHub MCP — I run it behind our FastAPI gateway with short-lived JWT and OPA, and it gives agents repo, PR and issue tools without custom glue. When NOT to use: For symbol-level code search I pair it with jcodemunch-mcp — this server is for GitHub-native tools, not deep code archaeology.”

“The browser tool that finally works reliably — I give our QA swarm a live Chrome with AT-SPI/Wayland control for performance traces without flaky Selenium. When NOT to use: Headless only — for API-only agents skip the browser overhead.”

“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 measured 42 minutes of agent exploration per unfamiliar repo in my Junagadh lab before codebase-memory-mcp cut it to milliseconds. Code-review-graph doing the same local-first map with benchmarked context reductions, purpose-built for reviews, is the exact pre-filter I bolt in front of expensive reasoning calls. I would wire its MCP server into Cursor morning scans beside trace-mcp.”

“Single index to plug n8n, RAG, GitHub, Chrome to any agent — discover MCP servers that keep data in Gujarat VPC.”

“Connects our ₹500 n8n VPS to every AI IDE (Claude Code, Cursor, Windsurf) — 30 tools in one MCP gateway for Gujarat SMEs.”

“I audit Laravel 13 codebases with pgvector — trace-mcp cuts my exploration from 42 min to one MCP call with typed traces. Its observation-driven approach pairs exactly with my Pydantic+OPA+HITL ledger.”

“I route MCP via one FastMCP gateway for Next.js + Laravel — agentskills-proxy is the remote proxy that isolates skill execution the same way I sandbox per-tenant JWT. Its discovery + execute split is the pattern I use for stateless MCP 2026-03-26.”

“I maintain a 41-skill catalog where 26% of trending skills request broad permissions per my SkillSpector audit — agent-skills validates every skill before install, the same sign-before-ship gate in my Junagadh catalog. Its cross-harness registry (Claude Code to Copilot) is the distribution shape my library pages follow.”

“I self-host research stacks so client queries never leak to third parties. The trending and compare tools feed my brief pipeline directly. I run it with Hishel caching to keep re-crawls cheap.”

“I maintain a 41-skill Junagadh catalog where discovery across 11 scattered repos wastes an hour per seat setup. Skills-mcp collapsing 9000 skills into one searchable MCP call is the index shape I want in front of my library pages, and I run it with tight install approvals to block broad-permission skills.”