AI/ML●●Solid
Memwright – Self-hosted memory for multi-agent teams, no LLM in path
No LLM in the critical path — deterministic retrieval beats vector search latency.
Big BrainNiche Gem
Bolnet
301mo ago
Back to browse
GitHub Repository
Deterministic byte-exact retrieval over static corpora. Website:https://glyph.rs
2 starsPython
Glyph – byte-exact substring retrieval (~1.5ms, FM-index)
by EMPTYCONTOUR·May 1, 2026·1 point·0 comments
AI Analysis
●●SolidBig BrainNiche Gem
FM-index implementation delivers 1.5ms exact matches where grep chokes on scale.
Strengths
- •Deterministic byte-exact matching eliminates false positives from tokenization.
- •Sub-2ms query latency on 4GB shards enables real-time forensic analysis.
- •Explicitly rejects fuzzy logic to guarantee reproducible search results.
Weaknesses
- •Experimental prototype status means no production binaries or cloud hosting yet.
- •Patent risk audit file suggests potential IP concerns for commercial adoption.
Category
Target Audience
Backend engineers building log search, forensic tools, or RAG pre-filters
Similar To
ripgrep · Elasticsearch · Lucene
Similar Projects
Developer Tools●Mid
Prompt Indexing for ChatGPT Session
ChatGPT prompt indexer, but unclear what problem this solves over native search.
Ship It
rushil_b_patel
103mo ago
Developer Tools●●Solid
A sparse, compressed bitmap index in C. Better than Roaring Bitmaps?
Beats Roaring Bitmaps on sparse runs with 8-byte descriptors for billion-bit sequences.
Big BrainNiche Gem
gregburd
2025d ago
Other●●Solid
My attempt to make Vector search engine in Rust(350k Items, ~3.5ms Qs)
Self-managed vector DB in Rust with <5ms queries; Pinecone/Weaviate already own this space.
WizardryNiche GemBig Brain
ronakgh97
403mo ago
AI/ML●●Solid
Deterministic symbolic memory layer for grounding LLMs
Identity-based memory vs similarity—clean separation of deterministic truth from probabilistic reasoning.
Big BrainZero to One
Th3Hypn0tist
103mo ago
AI/ML●●Solid
Nano-RAG – Agentic multi-hog retrieval without graph database
SQLite-only RAG with multi-hop retrieval is a clever constraint for a solved problem.
Big Brain
freakynit
2025d ago