Open Source●Mid
Self-hosted Raspberry Pi wall display (no cloud, no subscription)
Convenience script wrapping nginx and Chromium — no novel technical approach.
CozyShip It
g_33_k
793mo ago
Back to browse
GitHub Repository
Pure-PHP Web Server. No NGinX or PHP-FPM needed. Handle 10x more traffic instead!
35 starsPHP
Pure PHP server, has 10x throughput of NGINX+FPM, now support socket.io
by EGreg·Jul 21, 2026·4 points·0 comments
AI Analysis
●●●BangerWizardryBig Brain
Copy-on-write forking after class load slashes PHP memory from 50MB to 5MB per worker.
Strengths
- •Forks workers after framework load, sharing code memory via copy-on-write efficiently.
- •Built-in WebSocket support handles 40K concurrent connections without separate server.
- •X-Cache-Tree enables granular component invalidation instead of full-page purges.
Weaknesses
- •PHP ecosystem inertia means most teams won't swap nginx for an unknown server.
- •Lacks the battle-tested monitoring and tooling ecosystem around nginx and Apache.
Category
Target Audience
PHP developers running high-traffic applications
Similar To
nginx · php-fpm · RoadRunner
Similar Projects
Developer Tools●●Solid
PHP-ruler – strict rule engine in pure PHP, zero deps, explain mode
Explain mode traces rule evaluation node-by-node when Symfony can't.
Big BrainNiche Gem
asmodios
101mo ago
Developer Tools●●Solid
PHP-fts – Full-text search engine in pure PHP, no extensions
BM25 scoring and trigram indexing in pure PHP when Elasticsearch isn't an option.
Big BrainSolve My Problem
asmodios
89272mo ago
Developer Tools●Mid
Montmark – A lightweight, fast pure-Python Markdown parser
Hand-coded parser beats established libraries on speed but remains alpha quality.
CozyShip It
desgeeko
201mo ago
Security●●Solid
Detecting running processes using AF_ALG
Faster JSON output for AF_ALG detection than piping lsof through grep.
Niche GemShip It
Nullence
102mo ago
Finance●●Solid
We Made Nasdaq Parsing Even Faster (and More Reliable)
They stopped pretending chunking at arbitrary byte offsets was fine and instead scan once to build message boundaries, then binary-search for clean split points — that simple change eliminates the OOM-by-design scenario. Couple that with SIMD-aware prefetch tuning (different distances for AVX2 vs AVX-512) and you get practical microarch-aware engineering, not just benchmark stunts; I want this shipped as a library or tool so other firms can stop reinventing the same footguns.
WizardryNiche Gem
sundancegh
205mo ago